{ "schema": "commons-catalogue/1", "note": "Pre-release preview: includes garden records (not yet reviewed). Release packages ship reviewed core records only.", "count": 97, "resources": [ { "id": "res-anthropic-ai-assistance-skill-formation", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "How AI assistance impacts the formation of coding skills", "url": "https://www.anthropic.com/research/AI-assistance-coding-skills", "provider": "anthropic", "authors": [ "Shen", "Tamkin" ], "type": "research study", "summary": "A controlled experiment in which people learned a new programming tool with or without AI help. Those who leaned on AI scored lower on a follow-up quiz, but people who used AI to ask questions and understand ideas kept their learning and still worked fast. The finding applies beyond coding: the way you use AI affects how much you learn.\n", "teaches": [ "cmp-steering", "cmp-check-the-result" ], "concepts": [ "con-cognitive-offloading", "con-productive-friction", "con-human-in-the-loop" ], "audience": "mixed", "language": "en", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-01-29", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "unknown" }, "notes": "Small sample (52), immediate quiz only. Paper: arXiv 2601.20245. Add authors' full names from the paper.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Thinking-with-AI reading list: strongest evidence that conceptual questioning preserves learning at little time cost." }, "page": "/catalogue/#res-anthropic-ai-assistance-skill-formation" }, { "id": "res-anthropic-ai-capabilities-limitations", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "AI Capabilities and Limitations", "url": "https://academy.claude.com/courses/ai-capabilities-and-limitations", "provider": "anthropic", "authors": [ "Anthropic" ], "type": "course", "summary": "A plain-language course on how AI chat tools work: why they predict text, why their knowledge stops at a certain date, how much they can hold in mind at once, and how to figure out what went wrong when an answer surprises you. It is for anyone who uses AI at work or school and wants to judge its output with more confidence.\n", "teaches": [ "cmp-check-the-result", "cmp-describe-the-task" ], "concepts": [ "con-large-language-model", "con-context-window", "con-hallucination", "con-jagged-frontier", "con-verification" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "about 3.5 hours, 13 lessons", "access": { "cost": "free", "login": "optional", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "sitemap", "signal": "https://academy.claude.com/sitemap.xml" }, "notes": "Licence not found; research assumed all rights reserved. Check the per-course notice.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Durable concepts about how models behave; the best provider fit for the check-the-result competency." }, "page": "/catalogue/#res-anthropic-ai-capabilities-limitations" }, { "id": "res-anthropic-ai-fluency-foundations", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "AI Fluency: Framework & Foundations", "url": "https://academy.claude.com/courses/ai-fluency-framework-foundations", "provider": "anthropic", "authors": [ "Rick Dakan", "Joseph Feller", "Anthropic" ], "type": "course", "summary": "A free self-paced course that gives you a simple way to think about working with AI: deciding what to hand over, explaining the job clearly, judging what comes back, and taking responsibility for how you use it. It suits anyone starting out, with no technical background needed, and ends with a short quiz and a badge.\n", "teaches": [ "cmp-frame-the-outcome", "cmp-describe-the-task", "cmp-check-the-result", "cmp-use-responsibly" ], "concepts": [ "con-generative-ai", "con-prompting", "con-verification", "con-human-in-the-loop", "con-automation" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "about 4 hours, 14 lessons", "access": { "cost": "free", "login": "optional", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "CC BY-NC-SA 4.0", "evidence": "https://www-cdn.anthropic.com/334975cdec18f744b4fa511dc8518bd8d119d29d.pdf", "use": "link-and-summarise", "attribution": "© 2025 Rick Dakan, Joseph Feller, and Anthropic" }, "freshness": { "method": "sitemap", "signal": "https://academy.claude.com/sitemap.xml" }, "notes": "Licence confirmed only in the official course PDF, not on the course web page. NC + SA terms: link and summarise only, never adapt.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Strongest single foundation in the provider research; maps onto four of the six competencies." }, "page": "/catalogue/#res-anthropic-ai-fluency-foundations" }, { "id": "res-anthropic-ai-fluency-index", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "The AI Fluency Index", "url": "https://academy.claude.com/tutorials/the-ai-fluency-index", "provider": "anthropic", "authors": [ "Anthropic" ], "type": "research report", "summary": "Anthropic studied about ten thousand real Claude conversations to see which good habits people show. People who kept refining their request were far more likely to question the AI's reasoning, while polished outputs got less scrutiny, and very few people checked facts. Read it for the evidence behind two habits: keep refining your request, and check polished output as closely as rough drafts.\n", "teaches": [ "cmp-check-the-result", "cmp-steering", "cmp-describe-the-task" ], "concepts": [ "con-verification", "con-steering", "con-artifacts", "con-productive-friction" ], "audience": "nontechnical", "language": "en", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-02-23", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "sitemap", "signal": "https://academy.claude.com/sitemap.xml" }, "notes": "Original URL https://www.anthropic.com/research/AI-fluency-index now redirects here. Findings are correlational, one week of early-adopter data.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Thinking-with-AI reading list: evidence behind 'distrust polish' and 'stay in the conversation'." }, "page": "/catalogue/#res-anthropic-ai-fluency-index" }, { "id": "res-anthropic-ai-fluency-nonprofits", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "AI Fluency for Nonprofits", "url": "https://academy.claude.com/courses/ai-fluency-for-nonprofits", "provider": "anthropic", "authors": [ "Anthropic" ], "type": "course", "summary": "Applies the AI Fluency habits to nonprofit work such as fundraising, communications, programs and operations. You practise research, writing and data tasks, think through privacy and data handling, and work toward an AI policy for your organisation. Best taken after the Framework & Foundations course.\n", "teaches": [ "cmp-frame-the-outcome", "cmp-describe-the-task", "cmp-check-the-result", "cmp-use-responsibly" ], "concepts": [ "con-prompting", "con-privacy-and-data", "con-verification", "con-automation" ], "audience": "nontechnical", "language": "en", "prerequisites": "AI Fluency: Framework & Foundations recommended", "effort": "about 4 hours, 9 lessons", "access": { "cost": "free", "login": "optional", "checked": "unknown" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "sitemap", "signal": "https://academy.claude.com/sitemap.xml" }, "notes": "Research guessed CC BY-NC-SA 4.0 from the series pattern, but the page shows only an Anthropic copyright notice. Verify. Sister courses exist for small businesses, students and educators.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Role-specific follow-on to AI Fluency, close to the commons' nonprofit and community audience." }, "page": "/catalogue/#res-anthropic-ai-fluency-nonprofits" }, { "id": "res-anthropic-claude-101", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Claude 101", "url": "https://academy.claude.com/courses/claude-101", "provider": "anthropic", "authors": [ "Anthropic" ], "type": "course", "summary": "A guided tour of Claude for people starting to use it at work. It walks through everyday prompting, then features such as Projects, artifacts, Skills, connectors to other apps and research, with examples by job role.\n", "teaches": [ "cmp-describe-the-task", "cmp-make-it-repeatable" ], "concepts": [ "con-prompting", "con-projects-and-knowledge", "con-artifacts", "con-skills", "con-tools-and-connectors" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "about 2.5 hours, 13 lessons", "access": { "cost": "free course; some hands-on features need a paid Claude plan", "login": "optional", "checked": "unknown" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "sitemap", "signal": "https://academy.claude.com/sitemap.xml" }, "notes": "Tool-specific and fast-changing. Research only confirmed the URL loads; contents read by the seed agent, not a human.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Official orientation for Claude users; gives concrete names for features the concept cards explain." }, "page": "/catalogue/#res-anthropic-claude-101" }, { "id": "res-anthropic-education-report-students", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Anthropic Education Report: How university students use Claude", "url": "https://www.anthropic.com/news/anthropic-education-report-how-university-students-use-claude", "provider": "anthropic", "authors": [ "Anthropic" ], "type": "research report", "summary": "A look at how university students use Claude. Nearly half of conversations were quick answer-seeking, and the AI was most often doing the higher-level thinking, such as creating and analysing, rather than the student. It asks what students lose when they hand the hard parts to the AI.\n", "teaches": [ "cmp-use-responsibly", "cmp-steering" ], "concepts": [ "con-cognitive-offloading", "con-productive-friction" ], "audience": "nontechnical", "language": "en", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2025-04-08", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "unknown" }, "notes": "Descriptive usage data, not a learning-outcome study.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Thinking-with-AI reading list: shows how often AI ends up doing the thinking." }, "page": "/catalogue/#res-anthropic-education-report-students" }, { "id": "res-anthropic-intro-cowork", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Introduction to Claude Cowork", "url": "https://academy.claude.com/courses/introduction-to-claude-cowork", "provider": "anthropic", "authors": [ "Anthropic" ], "type": "course", "summary": "Shows people who shuffle information between files, apps and tools how to hand multi-step work to Claude's Cowork mode: setting up a workspace, giving it context, and running tasks on a schedule. No coding needed, but you need a paid Claude plan to follow along.\n", "teaches": [ "cmp-steering", "cmp-make-it-repeatable" ], "concepts": [ "con-agents", "con-scheduled-tasks", "con-skills", "con-context-engineering", "con-automation" ], "audience": "nontechnical", "language": "en", "prerequisites": "a paid Claude plan and the Claude desktop app for some lessons", "effort": "about 2.5 hours, 14 lessons", "access": { "cost": "free course; Cowork itself needs a paid Claude plan", "login": "optional", "checked": "unknown" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "sitemap", "signal": "https://academy.claude.com/sitemap.xml" }, "notes": "Paid plan needed to practise (course page lists Pro, Max, Team or Enterprise; confirm). Tool-specific and fast-changing.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "One of few provider courses on agentic work for non-coders; supports steering and make-it-repeatable." }, "page": "/catalogue/#res-anthropic-intro-cowork" }, { "id": "res-anthropic-prompt-design-intro", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Claude Help Center: Introduction to prompt design", "url": "https://support.claude.com/en/articles/7996853-introduction-to-prompt-design", "provider": "anthropic", "authors": [ "Anthropic" ], "type": "help article", "summary": "A short help article on writing requests to Claude. Its main point is that Claude knows nothing about you or your task, so you should brief it the way you would brief a new contractor, with clear and specific instructions.\n", "teaches": [ "cmp-describe-the-task" ], "concepts": [ "con-prompting", "con-prompt-engineering", "con-context-engineering" ], "audience": "mixed", "language": "en", "prerequisites": "none", "effort": "a few minutes", "access": { "cost": "free", "login": "none", "checked": "unknown" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "all rights reserved", "use": "link-and-summarise" }, "freshness": { "method": "llms-txt", "signal": "https://support.claude.com/llms.txt" }, "notes": "Filed under the API prompt-design collection, so it may lean technical; check fit. Help center release notes: https://support.claude.com/en/articles/12138966-release-notes", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Short, free entry point to describing a task well." }, "page": "/catalogue/#res-anthropic-prompt-design-intro" }, { "id": "res-google-ai-essentials", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Google AI Essentials", "url": "https://grow.google/ai-essentials/", "provider": "google", "authors": [ "Google" ], "type": "certificate course", "summary": "A short certificate course from Google, delivered through Coursera, for people with no AI experience. It runs across five modules in under five hours. Note that it is paid after a free trial.\n", "teaches": [ "cmp-describe-the-task", "cmp-use-responsibly" ], "concepts": [ "con-generative-ai", "con-prompting" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "under 5 hours, 5 modules", "access": { "cost": "paid: $49/month on Coursera after a 7-day free trial (US/Canada)", "login": "required", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "all rights reserved", "use": "link-and-summarise" }, "freshness": { "method": "unknown" }, "notes": "Paid flagship: show the cost clearly. Price recorded for US/Canada only.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Widely recognised beginner certificate; included with its cost flagged so learners can choose." }, "page": "/catalogue/#res-google-ai-essentials" }, { "id": "res-google-gemini-prompting-strategies", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Gemini API prompt design strategies", "url": "https://ai.google.dev/gemini-api/docs/prompting-strategies", "provider": "google", "authors": [ "Google" ], "type": "developer guide", "summary": "Google's guide to designing prompts for Gemini, written for developers but readable by confident nontechnical users. It covers giving clear instructions, adding examples, supplying context, breaking a request into parts and iterating on a prompt that isn't working.\n", "teaches": [ "cmp-describe-the-task" ], "concepts": [ "con-prompting", "con-prompt-engineering", "con-examples-in-prompts", "con-context-engineering" ], "audience": "developer", "language": "en", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-10-13", "rights": { "licence": "CC BY 4.0 (text); Apache-2.0 (code samples)", "evidence": "https://ai.google.dev/gemini-api/docs/prompting-strategies", "use": "link-and-summarise", "attribution": "Google, Gemini API documentation" }, "freshness": { "method": "manual", "signal": "'Last updated' date in the page footer" }, "notes": "Only provider prompting guide with an open text licence; could move to rights.use adapt after a human confirms.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Openly licensed prompting guidance that the commons may adapt with attribution." }, "page": "/catalogue/#res-google-gemini-prompting-strategies" }, { "id": "res-google-intro-generative-ai", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Introduction to Generative AI", "url": "https://www.skills.google/course_templates/536", "provider": "google", "authors": [ "Google" ], "type": "microlearning course", "summary": "A 45-minute introductory course explaining what generative AI is, what it is used for, and how it differs from older kinds of machine learning. It ends with a badge and needs no background.\n", "teaches": [ "cmp-frame-the-outcome" ], "concepts": [ "con-generative-ai", "con-large-language-model", "con-multimodal" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "45 minutes", "access": { "cost": "free (UNVERIFIED)", "login": "optional", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "all rights reserved", "use": "link-and-summarise" }, "freshness": { "method": "manual", "signal": "page shows a relative 'last updated' date" }, "notes": "Price not shown on the page; confirm it is free. Login needed only for the badge. Last section covers Google developer tools and may lose nontechnical readers.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Short, neutral overview of generative AI for the con-generative-ai card." }, "page": "/catalogue/#res-google-intro-generative-ai" }, { "id": "res-google-workspace-gemini-prompting-guide", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Gemini for Workspace prompting guide (PDF)", "url": "https://services.google.com/fh/files/misc/workspace_with_gemini_prompting_guide.pdf", "provider": "google", "authors": [ "Google Workspace" ], "type": "guide", "summary": "A downloadable guide from Google Workspace on writing prompts for Gemini inside everyday office tools. It is aimed at knowledge workers who use Gmail, Docs and similar apps.\n", "teaches": [ "cmp-describe-the-task" ], "concepts": [ "con-prompting", "con-prompt-engineering" ], "audience": "nontechnical", "language": "en", "access": { "cost": "free", "login": "none", "checked": "unknown" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "all rights reserved", "use": "link-and-summarise" }, "freshness": { "method": "unknown" }, "notes": "PDF contents and edition not checked. Landing page: https://workspace.google.com/learning/content/gemini-prompt-guide", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Prompting guidance for people who work in Google Workspace." }, "page": "/catalogue/#res-google-workspace-gemini-prompting-guide" }, { "id": "res-google-workspace-learning-center", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Google Workspace Learning Center", "url": "https://workspace.google.com/learning/content/learning-center", "provider": "google", "authors": [ "Google Workspace" ], "type": "help hub", "summary": "Google's help hub for Workspace apps, including how-to material on using Gemini in Docs, Gmail and other tools. Use it to look up a specific task rather than to learn concepts.\n", "teaches": [ "cmp-describe-the-task" ], "concepts": [ "con-tools-and-connectors" ], "audience": "nontechnical", "language": "en", "access": { "cost": "free", "login": "unknown", "checked": "unknown" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "all rights reserved", "use": "link-and-summarise" }, "freshness": { "method": "unknown" }, "notes": "Hub contents not reviewed; summary based on research notes.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Reference for Gemini-in-Workspace how-tos that project cards can point to." }, "page": "/catalogue/#res-google-workspace-learning-center" }, { "id": "res-huggingface-agents-course-intro", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Agents Course, Unit 0-1 (what an agent is)", "url": "https://huggingface.co/learn/agents-course/unit0/introduction", "provider": "huggingface", "authors": [ "Hugging Face" ], "type": "course", "summary": "The first units of Hugging Face's free agents course explain what an AI agent is: a model that can plan steps and use tools rather than only answer. The early units are conceptual; the rest of the course is aimed at developers.\n", "teaches": [ "cmp-steering" ], "concepts": [ "con-agents", "con-tools-and-connectors", "con-large-language-model" ], "audience": "mixed", "language": "en", "prerequisites": "none for units 0-1; later units need coding", "access": { "cost": "free", "login": "optional", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "Apache-2.0", "evidence": "https://github.com/huggingface/agents-course", "use": "link-and-summarise" }, "freshness": { "method": "manual", "signal": "https://github.com/huggingface/agents-course" }, "notes": "Recommend units 0-1 only for nontechnical readers. Account needed only for the certificate. Repo last pushed 2026-10-14.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Open-licence grounding for the agents concept card." }, "page": "/catalogue/#res-huggingface-agents-course-intro" }, { "id": "res-huggingface-huggingchat", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "HuggingChat (try open models)", "url": "https://huggingface.co/chat", "provider": "huggingface", "authors": [ "Hugging Face" ], "type": "tool", "summary": "A chat app where you can talk to many open models, either letting it pick one for you or choosing a model yourself. Use it for practice: try the same task on different models and compare what you get.\n", "teaches": [ "cmp-check-the-result" ], "concepts": [ "con-model-choice", "con-large-language-model" ], "audience": "nontechnical", "language": "en", "access": { "cost": "free tier", "login": "required", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "Hugging Face terms of service (proprietary site content)", "use": "link-and-summarise" }, "freshness": { "method": "manual", "signal": "app version shown on the page" }, "notes": "Login and free-tier limits taken from research notes; the page itself does not state them. Practice surface for prj-compare-models-on-a-real-task.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Free sandbox for comparing models on a real task." }, "page": "/catalogue/#res-huggingface-huggingchat" }, { "id": "res-huggingface-llm-course-intro", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "LLM Course, Chapter 1: Transformer models (intro)", "url": "https://huggingface.co/learn/llm-course/chapter1/1", "provider": "huggingface", "authors": [ "Hugging Face" ], "type": "course chapter", "summary": "The opening chapter of Hugging Face's free course on large language models, which explains what these models are and what they can do. Curious nontechnical readers can follow this first chapter; later chapters need Python.\n", "teaches": [ "cmp-check-the-result" ], "concepts": [ "con-large-language-model", "con-generative-ai", "con-model-choice" ], "audience": "mixed", "language": "en", "prerequisites": "none for chapter 1; later chapters need Python", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "Apache-2.0", "evidence": "https://github.com/huggingface/course", "use": "link-and-summarise" }, "freshness": { "method": "manual", "signal": "https://github.com/huggingface/course" }, "notes": "Only chapter 1 suits nontechnical readers. Source repo last pushed 2026-10-06.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Open, permissively licensed explanation of how language models work; shows open models exist." }, "page": "/catalogue/#res-huggingface-llm-course-intro" }, { "id": "res-openai-ai-at-work", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "OpenAI Academy: Apply AI at Work track", "url": "https://academy.openai.com/pages/ai-at-work-bcx7td", "provider": "openai", "authors": [ "OpenAI" ], "type": "course track", "summary": "A hub page collecting OpenAI Academy courses and events on using AI in everyday work, with separate groups for small businesses, nonprofits and government. Use it to find a role-based next step after a beginner course.\n", "teaches": [ "cmp-frame-the-outcome", "cmp-describe-the-task" ], "concepts": [ "con-prompting", "con-automation" ], "audience": "nontechnical", "language": "en", "access": { "cost": "free", "login": "unknown", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "all rights reserved", "use": "link-and-summarise" }, "freshness": { "method": "manual", "signal": "weekly blog and event listings on the hub" }, "notes": "Course list is JS-rendered, so individual items were not checked. Sign-in needed for some items (UNVERIFIED).", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Role-based tracks complement the commons' practice-first approach." }, "page": "/catalogue/#res-openai-ai-at-work" }, { "id": "res-openai-ai-foundations", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "OpenAI Academy: AI Foundations", "url": "https://academy.openai.com/public/courses/ai-foundations-juzjs", "provider": "openai", "authors": [ "OpenAI" ], "type": "course", "summary": "OpenAI's beginner course for people who use AI at work, which runs inside ChatGPT and ends with a certificate. Details of its contents and access come from secondary sources only, so treat this entry as a pointer until someone checks the course page.\n", "teaches": [ "cmp-describe-the-task" ], "concepts": [ "con-generative-ai", "con-prompting" ], "audience": "nontechnical", "language": "en", "access": { "cost": "free (secondary sources only)", "login": "unknown", "checked": "unknown" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "all rights reserved", "use": "link-and-summarise" }, "freshness": { "method": "sitemap", "signal": "OpenAI Academy content sitemap lastmod" }, "notes": "Page is JS-rendered; cost, ChatGPT-account requirement and public access (since about June 2026) all UNVERIFIED. Confirm in a browser.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "OpenAI's flagship beginner course; the commons should cover ChatGPT users too." }, "page": "/catalogue/#res-openai-ai-foundations" }, { "id": "res-openai-chatgpt-101-webinar", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "ChatGPT 101: A Guide to Your AI Super Assistant (recording)", "url": "https://academy.openai.com/public/videos/chatgpt-101-a-guide-to-your-ai-superassistant-recording", "provider": "openai", "authors": [ "OpenAI" ], "type": "recorded webinar", "summary": "A recorded introductory session from OpenAI Academy for people new to ChatGPT. It is a starting point for getting comfortable with the tool before moving on to role-specific material.\n", "teaches": [ "cmp-describe-the-task" ], "concepts": [ "con-generative-ai", "con-prompting" ], "audience": "nontechnical", "language": "en", "access": { "cost": "free", "login": "unknown", "checked": "unknown" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "all rights reserved", "use": "link-and-summarise" }, "freshness": { "method": "sitemap", "signal": "OpenAI Academy content sitemap lastmod" }, "notes": "Contents not reviewed; URL redirects to the work-users club. Sign-in may be required (UNVERIFIED). Companion: ChatGPT 102 recording.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Low-commitment beginner video for ChatGPT users." }, "page": "/catalogue/#res-openai-chatgpt-101-webinar" }, { "id": "res-openai-nonprofits-club", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "OpenAI Academy: Nonprofits club", "url": "https://academy.openai.com/public/clubs/nonprofits-8kc1e/overview", "provider": "openai", "authors": [ "OpenAI" ], "type": "community hub", "summary": "An OpenAI Academy community space for nonprofit staff, with dated events and sessions. Useful if you want to learn alongside peers in the sector rather than on your own.\n", "teaches": [ "cmp-use-responsibly" ], "concepts": [ "con-generative-ai" ], "audience": "nontechnical", "language": "en", "access": { "cost": "free", "login": "required", "checked": "unknown" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "all rights reserved", "use": "link-and-summarise" }, "freshness": { "method": "manual", "signal": "dated event listings" }, "notes": "Link seen on the Academy homepage; page itself not fetched. Sign-in needed to join.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Peer community for nonprofit staff, a core commons audience." }, "page": "/catalogue/#res-openai-nonprofits-club" }, { "id": "res-openai-prompt-best-practices", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Prompt engineering best practices for ChatGPT", "url": "https://help.openai.com/en/articles/10032626-prompt-engineering-best-practices-for-chatgpt", "provider": "openai", "authors": [ "OpenAI" ], "type": "help article", "summary": "OpenAI's help-center article on writing better requests to ChatGPT. It is the ChatGPT counterpart to the other providers' prompting guides; its contents have not been checked yet.\n", "teaches": [ "cmp-describe-the-task" ], "concepts": [ "con-prompting", "con-prompt-engineering" ], "audience": "nontechnical", "language": "en", "access": { "cost": "free", "login": "none", "checked": "unknown" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "all rights reserved", "use": "link-and-summarise" }, "freshness": { "method": "unknown", "bot_checkable": false }, "notes": "NOT VERIFIED: help.openai.com blocks fetchers. Open in a browser to confirm the page exists and write a real summary.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Official ChatGPT prompting guidance for the describe-the-task competency." }, "page": "/catalogue/#res-openai-prompt-best-practices" }, { "id": "res-other-bastani-guardrails-learning", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Generative AI without guardrails can harm learning", "url": "https://doi.org/10.1073/pnas.2422633122", "provider": "other-pnas", "authors": [ "Bastani", "et al." ], "type": "paper", "summary": "A field experiment with about a thousand high-school maths students. Plain ChatGPT helped them during practice but left them doing worse on the exam than students without it, because they used it as a crutch. A tutor version with guardrails removed the harm but did not improve results, so guardrails alone don't make people learn.\n", "teaches": [ "cmp-use-responsibly", "cmp-steering" ], "concepts": [ "con-cognitive-offloading", "con-productive-friction" ], "audience": "mixed", "language": "en", "access": { "cost": "unknown", "login": "unknown", "checked": "unknown" }, "accessibility": "unknown", "source_updated": "2025", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "unknown" }, "notes": "PNAS 122(26), 2025. Read from secondary summaries only; confirm the exact title and whether the article is open access.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Thinking-with-AI reading list: best evidence that easy answers can cost learning." }, "page": "/catalogue/#res-other-bastani-guardrails-learning" }, { "id": "res-other-bjork-desirable-difficulties", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Making things hard on yourself, but in a good way: Creating desirable difficulties to enhance learning", "url": "https://bjorklab.psych.ucla.edu/wp-content/uploads/sites/13/2016/04/EBjork_RBjork_2011.pdf", "provider": "other-ucla-bjork-lab", "authors": [ "Elizabeth Bjork", "Robert Bjork" ], "type": "book chapter", "summary": "A classic, readable chapter from learning science on why some struggle helps you remember: spacing practice out, mixing topics, testing yourself and producing answers before looking them up. Difficulty only helps if you can still succeed, so friction with AI should match the person.\n", "teaches": [ "cmp-steering" ], "concepts": [ "con-productive-friction", "con-cognitive-offloading" ], "audience": "mixed", "language": "en", "access": { "cost": "free", "login": "none", "checked": "unknown" }, "accessibility": "unknown", "source_updated": "2011", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "unknown" }, "notes": "Not fetched; summary from secondary notes. Confirm full title, authors and that the lab PDF is still online.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Thinking-with-AI reading list: the learning-science basis for productive friction." }, "page": "/catalogue/#res-other-bjork-desirable-difficulties" }, { "id": "res-other-claire-vo-adoption-rituals-podcast", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Why \"Get With the Program\" Doesn't Work: Claire Vo on AI That Actually Sticks (Agents of Scale)", "url": "https://agentsofscale.transistor.fm/23", "provider": "other-claire-vo", "authors": [ "Claire Vo" ], "type": "podcast episode", "summary": "A 51-minute conversation on Zapier's Agents of Scale podcast about why AI mandates and hiring freezes don't get a team using AI, and what does: regular rituals such as AI Fridays and hack weeks, leaders who build things themselves in the open, and treating AI skill as career growth rather than compliance. For anyone who has been asked to \"get the team using AI\".\n", "concepts": [ "con-vibe-coding", "con-adoption-rituals" ], "audience": "nontechnical", "language": "en", "effort": "51 minutes", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown (transcript not found on the episode page)", "source_updated": "2026-03-12", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Summary from the episode page notes, not the audio. Claire Vo was CPTO at LaunchDarkly and is now CEO of ChatPRD.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Her clearest public statement on team and organisation adoption; fills the commons gap on adoption practice." }, "page": "/catalogue/#res-other-claire-vo-adoption-rituals-podcast" }, { "id": "res-other-claire-vo-agent-glossary", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "The AI Agent Glossary", "url": "https://github.com/ChatPRD/agent-glossary", "provider": "other-claire-vo", "authors": [ "Claire Vo", "Brooke Lacey", "contributors" ], "type": "glossary", "summary": "A community glossary, started from a post by Claire Vo, of agent words such as agent, sandbox, context window, system prompt and MCP. Each term has a plain definition and an \"in practice\" example. It is one Markdown file, so you can hand it straight to your own AI. Some examples quote early-2026 prices and older models, so check numbers before you repeat them.\n", "concepts": [ "con-agents", "con-mcp", "con-context-window", "con-tools-and-connectors", "con-large-language-model" ], "audience": "nontechnical", "language": "en", "effort": "15 minutes", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "Plain Markdown on GitHub; a searchable web version is linked from the README", "source_updated": "2026-05-01", "rights": { "licence": "CC0-1.0 (declared in the README; the repo has no LICENSE file)", "evidence": "https://github.com/ChatPRD/agent-glossary#license", "use": "link-and-summarise", "attribution": "The AI Agent Glossary, ChatPRD and contributors, CC0" }, "freshness": { "method": "manual", "signal": "GitHub last push (2026-05-01)", "bot_checkable": true }, "notes": "6 stars on 2026-10-16; one burst of commits on 2026-05-01, so treat it as unmaintained. CC0 is stated only in the README; a human should confirm before adapting text.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Open, agent-readable glossary whose premise (every lab named the same primitives differently) matches the commons parallels map." }, "page": "/catalogue/#res-other-claire-vo-agent-glossary" }, { "id": "res-other-claire-vo-chat-to-reusable-skill", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "How to Turn a One-Off AI Chat Session into a Reusable Workflow for Your Team", "url": "https://www.chatprd.ai/how-i-ai/workflows/how-to-turn-a-one-off-ai-chat-session-into-a-reusable-workflow-for-your-team", "provider": "other-claire-vo", "authors": [ "ChatPRD" ], "type": "workflow guide", "summary": "Taken from the How I AI episode on Kai, Stripe's internal AI assistant. After a chat that produced something you want again, such as a dashboard, you ask the AI to package the session as a skill, edit its name and trigger phrases, add it to a shared library, then test it in a fresh session. Kai is internal to Stripe; you would need to try the same steps in an assistant that supports skills.\n", "teaches": [ "cmp-make-it-repeatable", "cmp-check-the-result" ], "concepts": [ "con-skills", "con-verification", "con-compound-loop" ], "audience": "mixed", "language": "en", "effort": "5 steps", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "unknown (© 2026 ChatPRD, Inc.)", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Episode: https://www.chatprd.ai/how-i-ai/how-stripe-built-kai-data-dashboards-reusable-skills-and-enterprise-ai-governance. The test-in-a-fresh-session step matches the commons make-it-repeatable skill.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Short, reproducible pattern for turning a good chat into a tested skill, shown inside a large company." }, "page": "/catalogue/#res-other-claire-vo-chat-to-reusable-skill" }, { "id": "res-other-claire-vo-cowork-daily-operating-system", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Claude Cowork 101: How to automate your workday without touching code (How I AI, with JJ Englert)", "url": "https://www.youtube.com/watch?v=jwGQ9CrqVdA", "provider": "other-claire-vo", "authors": [ "Claire Vo", "JJ Englert" ], "type": "podcast episode", "summary": "JJ Englert shows how someone who doesn't code can set up Claude Cowork: a \"brain\" file that tells Claude about you and your work, an email-writing skill built from your own sent mail, a panel of simulated reviewers that critique one draft from several angles, and a read-only morning plan. Good for knowledge workers who already use a chat assistant and want a first repeatable routine.\n", "teaches": [ "cmp-make-it-repeatable", "cmp-describe-the-task" ], "concepts": [ "con-skills", "con-projects-and-knowledge", "con-custom-instructions", "con-scheduled-tasks", "con-tools-and-connectors" ], "audience": "nontechnical", "language": "en", "access": { "cost": "free to watch; Claude Cowork and the connected tools have their own plans (not checked)", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-04-13", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Written summary with the steps: https://www.chatprd.ai/how-i-ai/jj-englerts-guide-to-a-daily-operating-system-with-claude-cowork. Sending email stays human-approved and the morning plan is read-only in his setup.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "One of the clearest How I AI episodes for nontechnical viewers; covers context files, skills and scheduled tasks in one sitting." }, "page": "/catalogue/#res-other-claire-vo-cowork-daily-operating-system" }, { "id": "res-other-claire-vo-how-i-ai-podcast", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "How I AI (podcast)", "url": "https://www.youtube.com/@howiaipodcast", "provider": "other-claire-vo", "authors": [ "Claire Vo" ], "type": "podcast", "summary": "A weekly video show hosted by Claire Vo where guests share their screen and show how they use AI in their actual job: product managers, designers, founders, engineers and parents. Because you watch the work happen, it is easier to copy than an interview. For a first episode, pick one aimed at people who don't code, such as the Claude Cowork tutorial with JJ Englert.\n", "teaches": [ "cmp-describe-the-task", "cmp-make-it-repeatable" ], "concepts": [ "con-agents", "con-skills", "con-automation", "con-vibe-coding" ], "audience": "mixed", "language": "en", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown (YouTube auto-captions likely; not checked)", "source_updated": "2026-10", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "feed", "signal": "YouTube channel uploads; episode hub at https://www.chatprd.ai/how-i-ai listed 112 episodes on 2026-10-16", "bot_checkable": true }, "notes": "Each episode also has a written page on chatprd.ai/how-i-ai. Lenny's Newsletter sends a free weekly roundup of new episodes.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Claire Vo's main body of work on AI workflows; the most reproducible format among the sources reviewed." }, "page": "/catalogue/#res-other-claire-vo-how-i-ai-podcast" }, { "id": "res-other-claire-vo-how-i-ai-workflows", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "How I AI workflow guides", "url": "https://www.chatprd.ai/how-i-ai/workflows", "provider": "other-claire-vo", "authors": [ "Claire Vo", "ChatPRD" ], "type": "workflow library", "summary": "About 290 short step-by-step guides, each taken from a How I AI episode where a guest shows a real AI workflow on screen. You can filter by tool, job function (operations, research, content and more) and difficulty, so a beginner can find something small to try this week. Each guide lists the tools, the inputs, the steps and how to check the result.\n", "teaches": [ "cmp-describe-the-task", "cmp-make-it-repeatable" ], "concepts": [ "con-skills", "con-automation", "con-agents", "con-custom-assistants" ], "audience": "mixed", "language": "en", "effort": "10 minutes to read a guide; the workflows themselves vary", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-10", "rights": { "licence": "unknown (pages say © 2026 ChatPRD, Inc.; downloadable skill files name no licence)", "use": "link-and-summarise" }, "freshness": { "method": "manual", "signal": "Workflow count on the listing page (289 on 2026-10-16) and newest guide dates", "bot_checkable": true }, "notes": "The guides read as ChatPRD write-ups of episodes, not transcripts. Some credit Claire Vo where the episode guest showed the workflow, so check the episode before saying who did what. Beginner guides worth starting with, all checked 2026-10-16: interview feedback with a custom GPT, standardising job descriptions with Claude Projects, rapid market research with Perplexity, writing a business plan with Claude.\n", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Largest free library of reproducible, screen-shared AI workflows from working people; filterable for nontechnical roles." }, "page": "/catalogue/#res-other-claire-vo-how-i-ai-workflows" }, { "id": "res-other-claire-vo-how-to-write-a-prd", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "How to Write a PRD: A Step-by-Step Guide for Product Managers", "url": "https://www.chatprd.ai/learn/how-to-write-a-prd", "provider": "other-claire-vo", "authors": [ "ChatPRD" ], "type": "guide", "summary": "A ten-step guide to writing a product requirements document: the problem, who it is for, goals, user stories, priorities, risks and how to get people to agree, with a good and a bad example and three free templates. It is written for product managers, but anyone who has to describe what should be built before asking a person or an AI to build it can use the problem and goal steps.\n", "teaches": [ "cmp-frame-the-outcome", "cmp-describe-the-task" ], "concepts": [ "con-context-engineering", "con-smallest-useful-version" ], "audience": "mixed", "language": "en", "effort": "20 minutes to read", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "unknown (© 2026 ChatPRD, Inc.)", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "No byline or date on the page. ChatPRD's template gallery (https://www.chatprd.ai/templates) has 24 templates marked free to use and share, with no licence named.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Already linked from WDAI course pipeline material; a plain guide to framing a build before handing it to AI." }, "page": "/catalogue/#res-other-claire-vo-how-to-write-a-prd" }, { "id": "res-other-claire-vo-interview-feedback-gpt", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "How to Improve Interview Feedback Consistency with a Custom GPT", "url": "https://www.chatprd.ai/how-i-ai/workflows/how-to-improve-interview-feedback-consistency-with-a-custom-gpt", "provider": "other-claire-vo", "authors": [ "ChatPRD" ], "type": "workflow guide", "summary": "A beginner guide to a custom GPT that holds your interview rubric plus strong and weak example scorecards, and reviews how well interviewers wrote up their evidence. The AI is kept to a narrow job: it rates the write-up, never the candidate, makes no hire decision, and flags claims tied to personal characteristics. A reviewer edits its note before sending. A good model for giving AI one bounded job with a rubric.\n", "teaches": [ "cmp-describe-the-task", "cmp-check-the-result", "cmp-use-responsibly" ], "concepts": [ "con-custom-assistants", "con-examples-in-prompts", "con-evals", "con-privacy-and-data", "con-human-in-the-loop" ], "audience": "nontechnical", "language": "en", "effort": "4 steps; labelled Beginner", "access": { "cost": "free to read; a custom GPT needs a ChatGPT plan that supports them (not checked)", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "unknown (© 2026 ChatPRD, Inc.)", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Candidate scorecards are personal data. The guide says to strip data that shouldn't enter the model and follow company policy; keep that warning in any project card built on it.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Clear example of scoping an AI to check the quality of human work against a rubric, with responsible-use limits built in." }, "page": "/catalogue/#res-other-claire-vo-interview-feedback-gpt" }, { "id": "res-other-claire-vo-openclaw-guide", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "OpenClaw: The complete guide to building, training, and living with your personal AI agent", "url": "https://www.lennysnewsletter.com/p/openclaw-the-complete-guide-to-building", "provider": "other-claire-vo", "authors": [ "Claire Vo" ], "type": "article", "summary": "Claire Vo's guest post on setting up OpenClaw, an open-source personal agent you message through apps such as Telegram. She explains why it should run on a separate machine with its own accounts, how its identity and rules live in a few text files, and six starter jobs such as pre-meeting briefs and weekend logistics. The setup part is free to read; the section on running several agents is for paid subscribers.\n", "teaches": [ "cmp-use-responsibly", "cmp-steering" ], "concepts": [ "con-agents", "con-scheduled-tasks", "con-skills", "con-privacy-and-data", "con-tools-and-connectors", "con-onboard-ai-like-a-new-hire", "con-prompt-injection" ], "audience": "mixed", "language": "en", "access": { "cost": "paid (Lenny's Newsletter subscription) for the full post; first part free", "login": "required", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-03-31", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Companion episode, free: Lenny's Podcast \"From skeptic to true believer: How OpenClaw changed my life\" (2026-03-29). There she describes giving the agent its own email and calendar, like a new employee, and widening its access only after a trust-building period. Setup needs a terminal.\n", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Pipeline-linked post; the best written account of Claire Vo's personal-agent practice, including the safety setup." }, "page": "/catalogue/#res-other-claire-vo-openclaw-guide" }, { "id": "res-other-claire-vo-self-improving-pm-system", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Claude Cowork for PMs: My Self-Improving Productivity System (How I AI, with Daniel Blum)", "url": "https://www.chatprd.ai/how-i-ai/claude-cowork-for-pms-my-self-improving-productivity-system", "provider": "other-claire-vo", "authors": [ "Claire Vo", "Daniel Blum" ], "type": "podcast episode", "summary": "Daniel Blum, a product manager at Melio, shows a Claude Cowork setup that preps his week, writes a morning brief from meeting notes and messages, and asks him to define internal terms it doesn't know before saving them. A weekly pass compares its drafts with his edits and suggests new skills. Watch it to see an assistant improve through many small confirmed corrections instead of one big setup.\n", "teaches": [ "cmp-make-it-repeatable", "cmp-steering", "cmp-check-the-result" ], "concepts": [ "con-memory", "con-context-engineering", "con-scheduled-tasks", "con-skills", "con-human-in-the-loop", "con-compound-loop" ], "audience": "mixed", "language": "en", "access": { "cost": "free to watch; tools shown (Claude Cowork, Notion, Granola) have their own plans", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-08-27", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Source for prj-teach-your-assistant-your-jargon. He treats the Notion dashboard as read-only and confirms changes before the assistant writes them.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Concrete, step-by-step example of a self-correcting context loop with the person approving each change." }, "page": "/catalogue/#res-other-claire-vo-self-improving-pm-system" }, { "id": "res-other-claire-vo-tradclaw", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Tradclaw: a household starter kit for OpenClaw", "url": "https://github.com/ChatPRD/tradclaw", "provider": "other-claire-vo", "authors": [ "ChatPRD" ], "type": "repository", "summary": "A starter set of files for running a personal AI agent as a family manager: calendar briefs, school email triage, meal plans and shopping lists, home maintenance reminders and stories for kids. The agent interviews you first and switches on only the modules you choose. Worth reading for its safety rules even if you never install it: it asks before sharing anything about children, and it never treats text from email, web pages or calendar invites as an instruction.\n", "teaches": [ "cmp-use-responsibly", "cmp-make-it-repeatable" ], "concepts": [ "con-agents", "con-scheduled-tasks", "con-privacy-and-data", "con-memory", "con-skills", "con-onboard-ai-like-a-new-hire", "con-prompt-injection" ], "audience": "mixed", "language": "en", "prerequisites": "Running OpenClaw needs a spare computer or server and some terminal use", "access": { "cost": "free; model and hosting costs depend on your setup", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-04-15", "rights": { "licence": "none (GitHub reports no licence)", "use": "link-and-summarise" }, "freshness": { "method": "manual", "signal": "GitHub last push", "bot_checkable": true }, "notes": "331 stars, last push 2026-04-15 on the 2026-10-16 check. No licence, so link only; nothing can be adapted.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Rare personal-life agent example with explicit privacy and prompt-injection rules written for non-engineers to read." }, "page": "/catalogue/#res-other-claire-vo-tradclaw" }, { "id": "res-other-every-agent-that-saved-my-brain", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "The Agent That Saved My Brain", "url": "https://every.to/p/the-agent-that-saved-my-brain", "provider": "other-every", "authors": [ "Austin Tedesco" ], "type": "essay", "summary": "Every's head of growth, who says he has no technical background, describes the \"command center\" he built in Claude Code: a set of notes about the business, connections to the tools he uses, and dozens of small skills for jobs he repeats, such as turning a voice note into a campaign brief. He released part of it as the Compound Knowledge plugin. A case study of a non-engineer growing a personal agent one task at a time.\n", "teaches": [ "cmp-make-it-repeatable", "cmp-describe-the-task" ], "concepts": [ "con-agents", "con-skills", "con-tools-and-connectors", "con-projects-and-knowledge", "con-mcp", "con-compound-loop" ], "audience": "nontechnical", "language": "en", "prerequisites": "none to read", "effort": "about 15 minutes", "access": { "cost": "unknown", "login": "unknown", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-03-23", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Fetched 2026-10-16; text visible, page metadata says audience 'everyone'. The plugin it mentions (EveryInc/compound-knowledge-plugin) has no licence file: link only.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Rare first-person account from a non-engineer of building up an agent through repeated small skills." }, "page": "/catalogue/#res-other-every-agent-that-saved-my-brain" }, { "id": "res-other-every-ai-style-guide", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "AI Style Guides: How to Help AI Write Like You", "url": "https://every.to/guides/ai-style-guide", "provider": "other-every", "authors": [ "Katie Parrott" ], "type": "guide", "summary": "A step-by-step guide to writing a style guide that an AI reads before it drafts for you. You gather a few writing samples, let the AI interview you about your voice and what you dislike in AI prose, react to sample lines, and turn the answers into a guide you test and revise over a week. Useful for anyone who keeps rewriting AI drafts to sound like themselves.\n", "teaches": [ "cmp-describe-the-task", "cmp-make-it-repeatable", "cmp-check-the-result" ], "concepts": [ "con-custom-instructions", "con-examples-in-prompts", "con-clarifying-questions", "con-ai-writing-tells", "con-projects-and-knowledge" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "about 20 minutes for a first draft, then a week of use and revision", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-03-17", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual", "signal": "https://every.to/guides" }, "notes": "Fetched 2026-10-16; full guide visible without sign-in. Date from the every.to/guides index. Basis for project card prj-ai-style-guide-from-your-samples.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "A free, concrete, repeatable workflow a nontechnical writer can finish in one sitting." }, "page": "/catalogue/#res-other-every-ai-style-guide" }, { "id": "res-other-every-allocation-economy", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "The Knowledge Economy Is Over. Welcome to the Allocation Economy.", "url": "https://every.to/chain-of-thought/the-knowledge-economy-is-over-welcome-to-the-allocation-economy", "provider": "other-every", "authors": [ "Dan Shipper" ], "type": "essay", "summary": "Dan Shipper argues that as AI takes over more of the making, people get paid less for what they know and more for how well they direct models. He names four skills a \"model manager\" needs: a clear goal, the taste to say exactly what is wrong with a result, judging which model suits which job, and knowing when to get into the details and when to leave the work alone. A short, readable framing for anyone starting to delegate to AI.\n", "teaches": [ "cmp-frame-the-outcome", "cmp-steering", "cmp-check-the-result" ], "concepts": [ "con-steering", "con-model-choice", "con-human-in-the-loop", "con-allocation-economy" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "about 10 minutes", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2024-01-18", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Fetched 2026-10-16; full text visible without sign-in. Opinion essay and forecast, not a study.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Coins the allocation economy and model-manager framing; four named skills map directly onto framing, steering and checking." }, "page": "/catalogue/#res-other-every-allocation-economy" }, { "id": "res-other-every-chatgpt-knowledge-work", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "ChatGPT for Knowledge Work", "url": "https://every.to/guides/codex-for-knowledge-work", "provider": "other-every", "authors": [ "Katie Parrott" ], "type": "guide", "summary": "A guide to using ChatGPT's agent features for office work, split into tasks you can hand off and tasks you should work through together. It moves through five levels from one-off tasks to recurring workflows and ends with a library of sixteen worked workflows, such as a weekly KPI report, a research brief and a recruiting shortlist, plus a seven-day starter plan. For managers and small teams who already use ChatGPT.\n", "teaches": [ "cmp-describe-the-task", "cmp-make-it-repeatable", "cmp-steering" ], "concepts": [ "con-agents", "con-tools-and-connectors", "con-scheduled-tasks", "con-skills", "con-automation" ], "audience": "nontechnical", "language": "en", "prerequisites": "A ChatGPT plan with agent features; the Codex sections assume some comfort with code.", "effort": "unknown", "access": { "cost": "paid Every subscription (price not checked)", "login": "required", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-07", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual", "signal": "https://every.to/guides" }, "notes": "PAYWALLED. Fetched 2026-10-16: introduction and Part 1 visible, the rest is for paid subscribers. Summary of later parts is from visible headings only. First listed 2026-05-26, page says updated July 2026.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Paid, but the only Every guide with a large library of named office workflows for non-engineers; include with cost marked." }, "page": "/catalogue/#res-other-every-chatgpt-knowledge-work" }, { "id": "res-other-every-claude-code-second-brain", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "How to Use Claude Code as a Second Brain", "url": "https://every.to/podcast/how-to-use-claude-code-as-a-thinking-partner", "provider": "other-every", "authors": [ "Dan Shipper", "Noah Brier" ], "type": "podcast episode", "summary": "An AI & I episode where Noah Brier shows how he points Claude Code at his folder of notes and tells it he is in \"thinking mode\", so it asks him questions and finds his past research instead of drafting. He keeps a project folder with saved chats, a daily progress log and sources, and asks the agent to recap recent days when he picks the work back up. For people who think through writing and keep notes.\n", "teaches": [ "cmp-describe-the-task", "cmp-steering" ], "concepts": [ "con-clarifying-questions", "con-agents", "con-projects-and-knowledge", "con-cognitive-offloading", "con-productive-friction" ], "audience": "mixed", "language": "en", "prerequisites": "A notes folder (he uses Obsidian) and Claude Code installed.", "effort": "unknown", "access": { "cost": "unknown", "login": "unknown", "checked": "2026-10-16" }, "accessibility": "A full transcript page exists: https://every.to/podcast/transcript-how-to-use-claude-code-as-a-thinking-partner", "source_updated": "2025-09-10", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Fetched 2026-10-16. The page doesn't say whether the episode is free. The remote-access part (home server, private network, phone terminal) is advanced and optional.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "A reproducible way to use an agent to think rather than to write for you; ties to productive friction." }, "page": "/catalogue/#res-other-every-claude-code-second-brain" }, { "id": "res-other-every-compound-engineering-guide", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Compound Engineering", "url": "https://every.to/guides/compound-engineering", "provider": "other-every", "authors": [ "Kieran Klaassen" ], "type": "guide", "summary": "Every's long guide to working with AI agents so that each job leaves the next one easier. It walks through a plan, work, review and \"compound\" loop, where the last step writes down what you learned so the agent catches the same problem next time, and a six-stage ladder from doing everything by hand to running several agents at once. Written for software teams, but the loop and the ladder carry over to any repeated knowledge work.\n", "teaches": [ "cmp-make-it-repeatable", "cmp-steering", "cmp-check-the-result" ], "concepts": [ "con-agents", "con-skills", "con-custom-instructions", "con-steering", "con-human-in-the-loop", "con-context-engineering", "con-compound-loop" ], "audience": "developer", "language": "en", "prerequisites": "Some comfort with an AI coding agent such as Claude Code helps for the plugin sections; the loop itself needs none.", "effort": "long read, about an hour", "access": { "cost": "free", "login": "optional", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-01-17", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual", "signal": "https://every.to/guides" }, "notes": "Fetched 2026-10-16. Main text readable; a free sign-in prompt appears near the end. Date is the one shown on the every.to/guides index. The companion plugin is MIT-licensed (see field skill proposal fld-every-compound-engineering); the guide text itself states no licence.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Source of the named compound-engineering loop; the clearest public account of writing lessons back into the agent's instructions after each job." }, "page": "/catalogue/#res-other-every-compound-engineering-guide" }, { "id": "res-other-every-compound-writing-guide", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Compound Writing: The Ultimate Guide", "url": "https://every.to/guides/compound-writing", "provider": "other-every", "authors": [ "Katie Parrott" ], "type": "guide", "summary": "Applies the compound loop to writing: interview, outline, draft, review, finish, then save what you learned so the next piece goes faster. It keeps your voice and project rules in plain files the agent reads each time. For people who write at work and are willing to run an agent like Claude Code or Codex.\n", "teaches": [ "cmp-make-it-repeatable", "cmp-describe-the-task" ], "concepts": [ "con-custom-instructions", "con-skills", "con-projects-and-knowledge", "con-agents", "con-compound-loop" ], "audience": "mixed", "language": "en", "prerequisites": "Comfort running an AI coding agent such as Claude Code or Codex.", "effort": "unknown", "access": { "cost": "paid Every subscription (price not checked)", "login": "required", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-09-02", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual", "signal": "https://every.to/guides" }, "notes": "PAYWALLED. Fetched 2026-10-16; only the outline is visible. The page names a compound writing plugin but links no repo. EveryInc/compound-writing on GitHub (356 stars, pushed 2026-09-15) has no licence file, so link only.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Shows the compound loop outside engineering; the free AI style guide is the better entry point." }, "page": "/catalogue/#res-other-every-compound-writing-guide" }, { "id": "res-other-every-eight-levels-ai-adoption", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "The Eight Levels of AI Adoption", "url": "https://every.to/guides/the-eight-levels-of-ai-adoption", "provider": "other-every", "authors": [ "Mike Taylor", "Laura Entis" ], "type": "guide", "summary": "Lays out eight levels of handing work to AI, from a chatbot that answers one request, through an agent that checks in before each step and one that works without approvals, up to a manager agent directing others. It says most knowledge workers get the most from the first four levels and that a higher level is not automatically better. Helps you name where you are and what the next step up would ask of you.\n", "teaches": [ "cmp-steering", "cmp-frame-the-outcome" ], "concepts": [ "con-agents", "con-human-in-the-loop", "con-automation", "con-solution-ladder", "con-steering", "con-delegating-to-ai" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "unknown", "access": { "cost": "free", "login": "required", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-06-02", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual", "signal": "https://every.to/guides" }, "notes": "Fetched 2026-10-16. Free Every account needed to read past the level list; the level names are visible without it. Page also credits Claude as a co-author.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "A delegation ladder written for knowledge workers rather than engineers; parallels the commons solution ladder." }, "page": "/catalogue/#res-other-every-eight-levels-ai-adoption" }, { "id": "res-other-every-every-employee-ai-agent", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "We Gave Every Employee an AI Agent. Here's What Happened.", "url": "https://every.to/podcast/transcript-we-gave-every-employee-an-ai-agent-here-s-what-happened", "provider": "other-every", "authors": [ "Dan Shipper", "Brandon Gell", "Willie Williams" ], "type": "podcast transcript", "summary": "Every's COO and head of platform talk through giving each staff member their own agent. Lessons include starting with personal chores so the value is obvious, running agents in shared channels so people learn from each other and owners stay accountable, and expecting agents in group chats to pile on or loop. They treat it as a culture change, because people differ a lot in how well they delegate.\n", "teaches": [ "cmp-use-responsibly", "cmp-steering", "cmp-make-it-repeatable" ], "concepts": [ "con-agents", "con-memory", "con-human-in-the-loop", "con-skills" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "about an hour to read or listen", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "Full transcript on the page.", "source_updated": "2026-04-08", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Fetched 2026-10-16; transcript fully visible, metadata audience 'everyone'. Mentions Every's own hosted product; summary keeps to the adoption lessons.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Team adoption seen from inside one company, including what went wrong." }, "page": "/catalogue/#res-other-every-every-employee-ai-agent" }, { "id": "res-other-every-executive-guide-implementing-ai", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "An Executive's Guide to Implementing AI", "url": "https://every.to/guides/an-executive-s-guide-to-implementing-ai", "provider": "other-every", "authors": [ "Natalia Quintero" ], "type": "guide", "summary": "A five-step plan for leaders bringing AI into an organisation: use the tools yourself first, give named champions protected time, pick one frequent and painful workflow, build it with good examples, checks and a named owner, then spread what works and drop what fails. It argues for maintained, owned skills libraries over loose prompt collections. For leaders and the operators who run adoption day to day.\n", "teaches": [ "cmp-make-it-repeatable", "cmp-check-the-result", "cmp-use-responsibly" ], "concepts": [ "con-skills", "con-evals", "con-human-in-the-loop", "con-smallest-useful-version", "con-adoption-rituals" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "unknown", "access": { "cost": "free", "login": "required", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-06-01", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual", "signal": "https://every.to/guides" }, "notes": "Fetched 2026-10-16. Only the introduction and five-step overview are visible without a free Every account; the 60-day plan and lessons sit behind sign-in. Written by Every's consulting lead, so it reflects their client practice.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Team and org adoption: one-workflow-first rollout with owners and checks, matching the commons smallest-useful-version idea." }, "page": "/catalogue/#res-other-every-executive-guide-implementing-ai" }, { "id": "res-other-every-securing-always-on-agent", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Securing an Always-on AI Employee", "url": "https://every.to/guides/securing-an-always-on-ai-employee", "provider": "other-every", "authors": [ "Nityesh Agarwal" ], "type": "guide", "summary": "How Every limits the risk of an agent that runs all day with real accounts. It covers three threats (poisoned software packages, instructions hidden in content the agent reads, and leaks of internal data) and four layers of defence: give the agent its own accounts and only the access it needs, add hard blocks it cannot talk its way past, write rules into its instructions, and log everything. Best for whoever decides how much access a team's agent gets.\n", "teaches": [ "cmp-use-responsibly", "cmp-check-the-result" ], "concepts": [ "con-agents", "con-privacy-and-data", "con-human-in-the-loop", "con-tools-and-connectors", "con-onboard-ai-like-a-new-hire", "con-prompt-injection" ], "audience": "mixed", "language": "en", "prerequisites": "Easier to follow if you have set up an agent with tool access.", "effort": "unknown", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-08-14", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual", "signal": "https://every.to/guides" }, "notes": "Fetched 2026-10-16; full text visible. Date from the every.to/guides index. Technical in places; the gap check at the end (which layer catches each risky action) is usable by non-engineers.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Practical, layered safety thinking for agents with access, a gap in the current catalogue." }, "page": "/catalogue/#res-other-every-securing-always-on-agent" }, { "id": "res-other-kosmyna-your-brain-on-chatgpt", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Your Brain on ChatGPT", "url": "https://arxiv.org/abs/2506.08872", "provider": "other-mit-media-lab", "authors": [ "Kosmyna", "et al." ], "type": "paper", "summary": "An MIT Media Lab study that measured brain activity while people wrote essays with ChatGPT, a search engine or nothing. The ChatGPT group felt least ownership and often could not quote their own essays. People who wrote alone first and then used AI stayed more engaged, which supports thinking before you prompt.\n", "teaches": [ "cmp-frame-the-outcome", "cmp-use-responsibly" ], "concepts": [ "con-cognitive-offloading", "con-productive-friction", "con-ai-writing-tells" ], "audience": "mixed", "language": "en", "access": { "cost": "free", "login": "none", "checked": "unknown" }, "accessibility": "unknown", "source_updated": "2025", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "unknown" }, "notes": "Small sample (54, only 18 in the last session), not peer reviewed at the time, EEG methods disputed. Present as suggestive, not proof. Research read the MIT project page, not this arXiv link.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Thinking-with-AI reading list: widely cited study behind 'write first, then use AI'." }, "page": "/catalogue/#res-other-kosmyna-your-brain-on-chatgpt" }, { "id": "res-other-lee-critical-thinking", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "The Impact of Generative AI on Critical Thinking", "url": "https://doi.org/10.1145/3706598.3713778", "provider": "other-chi", "authors": [ "Lee", "Sarkar", "et al." ], "type": "paper", "summary": "A survey of 319 knowledge workers about when they think critically while using AI. People who trusted the AI more tended to think less critically, and people more confident in their own skills tended to think more. Their critical effort moved toward checking, combining and overseeing AI work.\n", "teaches": [ "cmp-check-the-result", "cmp-steering" ], "concepts": [ "con-cognitive-offloading", "con-verification", "con-human-in-the-loop" ], "audience": "mixed", "language": "en", "access": { "cost": "free (open access, per research notes)", "login": "none", "checked": "unknown" }, "accessibility": "unknown", "source_updated": "2025", "rights": { "licence": "CC BY", "evidence": "https://doi.org/10.1145/3706598.3713778", "use": "link-and-summarise" }, "freshness": { "method": "unknown" }, "notes": "Read from the abstract only. CHI 2025 paper; confirm full title, author list and CC BY version. Self-reported, correlational.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Thinking-with-AI reading list: links trust in AI to less critical thinking." }, "page": "/catalogue/#res-other-lee-critical-thinking" }, { "id": "res-other-lenny-ai-agent-categories", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Not all AI agents are created equal", "url": "https://www.lennysnewsletter.com/p/not-all-ai-agents-are-created-equal", "provider": "other-lenny", "authors": [ "Hamza Farooq", "Jaya Rajwani" ], "type": "article", "summary": "Sorts agent ideas into three kinds before you compare effort or value: fixed step-by-step automations where AI fills in content at set points, agents that choose their own next step from a set of tools, and networks of agents owned by different teams. The authors advise starting with the first kind for the quickest measurable return. Most of the post, including the third kind, is for paid subscribers.\n", "teaches": [ "cmp-frame-the-outcome" ], "concepts": [ "con-agents", "con-automation", "con-solution-ladder" ], "audience": "mixed", "language": "en", "access": { "cost": "paid (Lenny's Newsletter subscription); opening sections free", "login": "required", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-04-14", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Not in the free starter pack. Summary from the free preview only.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Pipeline-linked; a plain sorting rule that matches the commons solution ladder (start with the simplest kind that works)." }, "page": "/catalogue/#res-other-lenny-ai-agent-categories" }, { "id": "res-other-lenny-ai-glossary", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "An AI glossary", "url": "https://www.lennysnewsletter.com/p/an-ai-glossary", "provider": "other-lenny", "authors": [ "Lenny Rachitsky" ], "type": "glossary", "summary": "Plain-language definitions of about 20 AI terms, from model, token and training to RAG, MCP, agents, evals and hallucination, written for people in meetings where these words fly past. Lenny says he adds terms as new ones appear. If you need text you can reuse, use the open AI Agent Glossary instead.\n", "concepts": [ "con-large-language-model", "con-generative-ai", "con-hallucination", "con-mcp", "con-agents", "con-evals" ], "audience": "nontechnical", "language": "en", "effort": "20 minutes", "access": { "cost": "paid on lennysnewsletter.com; full text free in Lenny's public data starter pack (personal, non-commercial use)", "login": "required", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2025-06-24", "rights": { "licence": "all rights reserved (Lenny Rachitsky)", "evidence": "https://github.com/LennysNewsletter/lennys-newsletterpodcastdata/blob/main/LICENSE.md", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Free copy: https://github.com/LennysNewsletter/lennys-newsletterpodcastdata/blob/main/newsletters/an-ai-glossary.md.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Widely read plain-English glossary; pairs with the commons concept map as a reading companion." }, "page": "/catalogue/#res-other-lenny-ai-glossary" }, { "id": "res-other-lenny-ai-prototyping-guide", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "A guide to AI prototyping for product managers", "url": "https://www.lennysnewsletter.com/p/a-guide-to-ai-prototyping-for-product", "provider": "other-lenny", "authors": [ "Colin Matthews" ], "type": "article", "summary": "Colin Matthews compares three kinds of tool for turning an idea into a clickable prototype: chat assistants, browser builders such as Bolt, v0, Lovable and Replit, and coding assistants such as Cursor, and says when to use each. He gives prompt templates for common jobs, like turning a sketch or a requirements doc into a prototype, and ways to get unstuck without coding: ask it to reflect, change one thing at a time, be specific, and start fresh when it loses track.\n", "teaches": [ "cmp-describe-the-task", "cmp-steering" ], "concepts": [ "con-vibe-coding", "con-artifacts", "con-solution-ladder" ], "audience": "mixed", "language": "en", "access": { "cost": "paid on lennysnewsletter.com; full text free in Lenny's public data starter pack (personal, non-commercial use)", "login": "required", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2025-01-07", "rights": { "licence": "all rights reserved (Lenny Rachitsky)", "evidence": "https://github.com/LennysNewsletter/lennys-newsletterpodcastdata/blob/main/LICENSE.md", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Free copy: https://github.com/LennysNewsletter/lennys-newsletterpodcastdata/blob/main/newsletters/a-guide-to-ai-prototyping-for-product-managers.md. Tool names date from January 2025. Follow-up post 'How to get your entire team prototyping with AI' (2025-06-10) is paid and not in the starter pack.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Standard reference for AI prototyping; its unsticking tactics apply to any nontechnical builder." }, "page": "/catalogue/#res-other-lenny-ai-prototyping-guide" }, { "id": "res-other-lenny-build-your-personal-ai-copilot", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Build your personal AI copilot", "url": "https://www.lennysnewsletter.com/p/build-your-personal-ai-copilot", "provider": "other-lenny", "authors": [ "Tal Raviv" ], "type": "article", "summary": "Tal Raviv's free guide to using an AI project as a long-term thinking partner at work. You \"hire\" it by writing how it should work with you (including when to push back), onboard it with background on your role, team and goals, kick off one initiative, then keep feeding it updates so its advice gets better. It includes starter prompts and an appendix for tools without a projects feature.\n", "teaches": [ "cmp-describe-the-task", "cmp-frame-the-outcome", "cmp-steering" ], "concepts": [ "con-projects-and-knowledge", "con-custom-instructions", "con-context-engineering", "con-memory", "con-sycophancy", "con-onboard-ai-like-a-new-hire" ], "audience": "nontechnical", "language": "en", "effort": "30 to 45 minutes to read; about 30 minutes to set up", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2025-07-22", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "feed", "signal": "Substack post API (audience: everyone on 2026-10-16)", "bot_checkable": true }, "notes": "Source for prj-onboard-an-ai-copilot. Tal Raviv also publishes free video tutorials on AI agents at work (linked from the post).", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Free, step-by-step and written for knowledge workers; the clearest 'treat it like a new colleague' guide in Lenny's archive." }, "page": "/catalogue/#res-other-lenny-build-your-personal-ai-copilot" }, { "id": "res-other-lenny-data-starter-pack", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Lenny's Data: free public starter pack", "url": "https://github.com/LennysNewsletter/lennys-newsletterpodcastdata", "provider": "other-lenny", "authors": [ "Lenny Rachitsky" ], "type": "dataset", "summary": "A free sample of Lenny's archive as plain Markdown: 10 newsletter posts and 50 podcast transcripts, with an index of titles, dates and guests. It includes several posts that are otherwise paid, among them the AI prototyping, evals, AI glossary and second-brain guides. Use it to read those posts, or to practise asking your own AI questions over a folder of documents.\n", "teaches": [ "cmp-describe-the-task" ], "concepts": [ "con-projects-and-knowledge", "con-context-engineering", "con-mcp" ], "audience": "mixed", "language": "en", "access": { "cost": "free starter pack; full archive (373 posts, 321 transcripts, MCP access) for paid subscribers", "login": "none", "checked": "2026-10-16" }, "accessibility": "Plain Markdown files", "source_updated": "2026-10-11", "rights": { "licence": "Lenny's Data starter-pack terms: personal, non-commercial use; no redistribution of raw files; © Lenny Rachitsky, all rights reserved", "evidence": "https://github.com/LennysNewsletter/lennys-newsletterpodcastdata/blob/main/LICENSE.md", "use": "link-and-summarise" }, "freshness": { "method": "manual", "signal": "index.json generated_at (2026-10-11T16:03Z) and GitHub last push", "bot_checkable": true }, "notes": "669 stars on 2026-10-16. Some post_url values in index.json return 404 (3 of 3 tested); use canonical Substack URLs. A separate unofficial archive, ChatPRD/lennys-podcast-transcripts (269 transcripts, 1,369 stars, no licence, \"personal and educational use\"), also exists; link only.\n", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Official, agent-readable source; makes several paid AI guides freely readable for learners." }, "page": "/catalogue/#res-other-lenny-data-starter-pack" }, { "id": "res-other-lenny-evals-guide", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Beyond vibe checks: A PM's complete guide to evals", "url": "https://www.lennysnewsletter.com/p/beyond-vibe-checks-a-pms-complete", "provider": "other-lenny", "authors": [ "Aman Khan" ], "type": "article", "summary": "Aman Khan of Arize AI explains how to test AI output on purpose rather than by feel. He covers what to measure (made-up facts, relevance, tone), a four-part recipe for a prompt that asks one AI to grade another's answer (a role, the text to grade, the goal, and exact definitions of each label), and a cycle of collecting examples, grading them, fixing the prompt and monitoring. The recipe works for anyone who reuses a prompt, not only product teams.\n", "teaches": [ "cmp-check-the-result", "cmp-make-it-repeatable" ], "concepts": [ "con-evals", "con-verification", "con-hallucination" ], "audience": "mixed", "language": "en", "access": { "cost": "paid on lennysnewsletter.com; full text free in Lenny's public data starter pack (personal, non-commercial use)", "login": "required", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2025-04-08", "rights": { "licence": "all rights reserved (Lenny Rachitsky)", "evidence": "https://github.com/LennysNewsletter/lennys-newsletterpodcastdata/blob/main/LICENSE.md", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Free copy: https://github.com/LennysNewsletter/lennys-newsletterpodcastdata/blob/main/newsletters/beyond-vibe-checks-a-pms-complete-guide-to-evals.md. The starter pack index URL for this post returns 404; the URL above is canonical.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Most practical evals primer in the archive; its grading-prompt recipe can feed the prove-it skill." }, "page": "/catalogue/#res-other-lenny-evals-guide" }, { "id": "res-other-lenny-everyone-claude-code", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Everyone should be using Claude Code more", "url": "https://www.lennysnewsletter.com/p/everyone-should-be-using-claude-code", "provider": "other-lenny", "authors": [ "Lenny Rachitsky" ], "type": "article", "summary": "Lenny walks through installing Claude Code and then collects 50 ways people outside engineering use it: cleaning up messy invoice files, organising folders, synthesising customer-call transcripts, drafting a job description, building slides. Read it for ideas once chat feels comfortable and you want an AI that works on the files on your own computer.\n", "teaches": [ "cmp-frame-the-outcome" ], "concepts": [ "con-agents", "con-vibe-coding", "con-tools-and-connectors" ], "audience": "mixed", "language": "en", "prerequisites": "Comfort opening a terminal, or a willingness to try with the install steps in the post", "access": { "cost": "paid on lennysnewsletter.com; full text free in Lenny's public data starter pack (personal, non-commercial use)", "login": "required", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2025-10-14", "rights": { "licence": "all rights reserved (Lenny Rachitsky)", "evidence": "https://github.com/LennysNewsletter/lennys-newsletterpodcastdata/blob/main/LICENSE.md", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Free copy: https://github.com/LennysNewsletter/lennys-newsletterpodcastdata/blob/main/newsletters/everyone-should-be-using-claude-code-more.md. Example 9 (organising scattered thoughts) comes from Helen Lee Kupp of WDAI; a reviewer other than Helen should judge this entry.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Large set of real, nontechnical use cases for a local agent; good idea bank for first builds." }, "page": "/catalogue/#res-other-lenny-everyone-claude-code" }, { "id": "res-other-lenny-how-i-ai-cowork-roundup", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "This week on How I AI: Claude Cowork tutorial for non-engineers + Build your own Slack inbox (for $0)", "url": "https://www.lennysnewsletter.com/p/this-week-on-how-i-ai-claude-cowork", "provider": "other-lenny", "authors": [ "Lenny Rachitsky" ], "type": "newsletter roundup", "summary": "A free weekly roundup of two How I AI episodes: JJ Englert's Claude Cowork tutorial for people who don't code, and Yash Tekriwal's custom Slack digest, which cut 100 to 150 daily notifications to about 30 that need attention. Each comes with links to step-by-step workflow write-ups. A quick way to decide whether either episode is worth an hour.\n", "teaches": [ "cmp-make-it-repeatable" ], "concepts": [ "con-automation", "con-skills", "con-scheduled-tasks" ], "audience": "nontechnical", "language": "en", "effort": "5 minutes", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-04-13", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "feed", "signal": "Weekly How I AI roundups on Lenny's Newsletter", "bot_checkable": true }, "notes": "See also res-other-claire-vo-cowork-daily-operating-system for the episode itself.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Pipeline-linked; the free weekly roundups are the easiest way into How I AI from Lenny's side." }, "page": "/catalogue/#res-other-lenny-how-i-ai-cowork-roundup" }, { "id": "res-other-lenny-nontechnical-pm-cursor", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "The non-technical PM's guide to building with Cursor (Lenny's Podcast, with Zevi Arnovitz)", "url": "https://www.youtube.com/watch?v=1em64iUFt3U", "provider": "other-lenny", "authors": [ "Lenny Rachitsky", "Zevi Arnovitz" ], "type": "podcast episode", "summary": "Zevi Arnovitz, a product manager at Meta who doesn't write code, shows how he builds working products with Cursor and Claude. Saved commands take him from capturing an idea as an issue, to exploring the problem, writing a plan, building, and asking several different AI models to review the result. He suggests starting in a simple chat project and moving to heavier tools only when you outgrow them.\n", "teaches": [ "cmp-steering", "cmp-check-the-result", "cmp-make-it-repeatable" ], "concepts": [ "con-vibe-coding", "con-steering", "con-skills", "con-solution-ladder", "con-verification" ], "audience": "mixed", "language": "en", "access": { "cost": "free to watch; the tools shown have their own plans", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown; a transcript is in Lenny's free data starter pack (podcasts/zevi-arnovitz.md)", "source_updated": "2026-01-18", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "The episode says the prompts and commands can be downloaded from the show notes; not checked.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Best worked example in the archive of a non-coder steering an AI builder through plan, build and review." }, "page": "/catalogue/#res-other-lenny-nontechnical-pm-cursor" }, { "id": "res-other-lenny-pm-second-brain", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "How to build your PM second brain with ChatGPT", "url": "https://www.lennysnewsletter.com/p/how-to-build-your-pm-second-brain", "provider": "other-lenny", "authors": [ "Amir Klein" ], "type": "article", "summary": "Amir Klein, a product manager at monday.com, shows how he set up a ChatGPT Project as a second brain for a new initiative: write instructions that make it challenge him, upload everything he had (docs, decks, exported Slack threads) as files, then ask it to pull together plans and gaps. An appendix covers Claude and Gemini. It is aimed at product managers, but the steps fit anyone juggling scattered context.\n", "teaches": [ "cmp-describe-the-task", "cmp-steering" ], "concepts": [ "con-projects-and-knowledge", "con-custom-instructions", "con-context-engineering", "con-sycophancy", "con-onboard-ai-like-a-new-hire" ], "audience": "mixed", "language": "en", "access": { "cost": "paid on lennysnewsletter.com; full text free in Lenny's public data starter pack (personal, non-commercial use)", "login": "required", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2025-12-16", "rights": { "licence": "all rights reserved (Lenny Rachitsky)", "evidence": "https://github.com/LennysNewsletter/lennys-newsletterpodcastdata/blob/main/LICENSE.md", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Free copy: https://github.com/LennysNewsletter/lennys-newsletterpodcastdata/blob/main/newsletters/how-to-build-your-pm-second-brain-with-chatgpt.md. Before uploading work files, check your organisation's rules; this review did not check how the post handles that.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Concrete projects-as-context walkthrough across three assistants; pairs with Tal Raviv's copilot guide." }, "page": "/catalogue/#res-other-lenny-pm-second-brain" }, { "id": "res-other-lenny-what-people-vibe-code", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "What people are vibe coding (and actually using)", "url": "https://www.lennysnewsletter.com/p/what-people-are-vibe-coding-and-actually", "provider": "other-lenny", "authors": [ "Lenny Rachitsky" ], "type": "article", "summary": "More than 50 small tools that readers built with Replit, Lovable, Bolt, Cursor and similar and still use: a carb counter, a chore app for kids, a bill splitter, meeting-prep automation, a tracker of wins at work. Each entry names the builder and the tool. Useful for choosing a first build that is small, personal and likely to get used.\n", "teaches": [ "cmp-frame-the-outcome" ], "concepts": [ "con-vibe-coding", "con-smallest-useful-version", "con-artifacts" ], "audience": "nontechnical", "language": "en", "access": { "cost": "paid on lennysnewsletter.com; full text free in Lenny's public data starter pack (personal, non-commercial use)", "login": "required", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2025-07-08", "rights": { "licence": "all rights reserved (Lenny Rachitsky)", "evidence": "https://github.com/LennysNewsletter/lennys-newsletterpodcastdata/blob/main/LICENSE.md", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Free copy: https://github.com/LennysNewsletter/lennys-newsletterpodcastdata/blob/main/newsletters/what-people-are-vibe-coding-and-actually-using.md. The post_url in the starter pack index (…-and-actually-using) returns 404; the URL above is the canonical one from the Substack API.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Shows nontechnical people what 'small and useful' looks like, which is the hardest part of picking a first build." }, "page": "/catalogue/#res-other-lenny-what-people-vibe-code" }, { "id": "res-other-ming-fcat-interview", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "A Conversation with Dr. Vivienne Ming, author of Robot-Proof", "url": "https://www.fcatalyst.com/trends-and-signals/a-conversation-with-dr-vivienne-ming-author-of-robot-proof", "provider": "other-ming", "authors": [ "Vivienne Ming", "John Dalton" ], "type": "interview", "summary": "A short written Q&A from Fidelity's research centre. Ming explains her split between well-posed problems that language models handle well and open problems where people do better, and why the combination beats either alone. Her advice for individuals: map the known part with AI, do your own reasoning on the uncertain part, and question its answers. For leaders: develop curious, humble, adaptable people, since she finds those traits predict who works well with AI.\n", "teaches": [ "cmp-frame-the-outcome", "cmp-steering", "cmp-use-responsibly" ], "concepts": [ "con-productive-friction", "con-cognitive-offloading", "con-human-in-the-loop", "con-centaurs-and-cyborgs" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "about 10 minutes", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-08-05", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Fetched 2026-10-16. Mentions an oil-price prediction contest in which human-AI 'cyborgs' beat humans alone; publication status not stated (treat as reported, unpublished).", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "The quickest free summary of Robot-Proof's argument, in her words." }, "page": "/catalogue/#res-other-ming-fcat-interview" }, { "id": "res-other-ming-forecasting-cyborgs-report", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "A top researcher says a new divide is emerging in AI use, and most people are on the losing side", "url": "https://www.aol.com/articles/top-researcher-says-divide-emerging-143334376.html", "provider": "other-ming", "authors": [ "Thibault Spirlet" ], "type": "article", "summary": "A news report on Ming's forecasting experiment, in which teams predicted real events with or without AI and were compared against Polymarket. She reports that most people either let AI produce the answer or used it to confirm what they already believed. A small minority, roughly 5-10%, argued with it and asked it to explain why they were wrong, and those people did best. The finding is reported in an interview and has not been published as research.\n", "teaches": [ "cmp-check-the-result", "cmp-steering" ], "concepts": [ "con-productive-friction", "con-sycophancy", "con-cognitive-offloading", "con-centaurs-and-cyborgs" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "about 5 minutes", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-03-30", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Reported, unpublished: no paper or preprint was found. AOL syndication of a Business Insider story (2026-03-30), fetched 2026-10-16; the Business Insider original blocks bots and wasn't checked. Reported sample: 39 UC Berkeley students and 33 other Bay Area participants, late summer to fall 2025. No accuracy figures are given. Other coverage describes the hybrid teams as the only group to rival the prediction market; that wasn't verified here.\n", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "The one public account of Ming's 'tell me why I'm wrong' finding; kept as a clearly labelled report, not evidence." }, "page": "/catalogue/#res-other-ming-forecasting-cyborgs-report" }, { "id": "res-other-ming-humans-plus-ai-ep13", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Vivienne Ming on hybrid collective intelligence, building cyborgs, meta-uncertainty, and the unknown infinite", "url": "https://humansplus.ai/podcast/vivienne-ming-hybrid-collective-intelligence-building-cyborgs-meta-uncertainty-unknown-infinite-ac-ep13/", "provider": "other-ming", "authors": [ "Vivienne Ming", "Ross Dawson" ], "type": "podcast", "summary": "A long interview on the Humans + AI podcast with a full transcript. Ming's test for any tool is whether it leaves you more capable once you switch it off. She suggests pausing to judge your own uncertainty before accepting an answer, using AI to critique your thinking, and treating it like a research assistant you challenge and correct. She also explains why diverse teams produce more novel ideas and why AI tends to make people's ideas more alike.\n", "teaches": [ "cmp-use-responsibly", "cmp-check-the-result", "cmp-steering" ], "concepts": [ "con-productive-friction", "con-cognitive-offloading", "con-verification", "con-sycophancy", "con-centaurs-and-cyborgs" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "unknown", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "full transcript on the page; also on YouTube", "source_updated": "2025-08-06", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Fetched 2026-10-16. Research she describes from her own work (a model that predicted student outcomes from week-one discussion posts; an analysis of lockdown-era collaborations) is reported in conversation; no published papers were checked. Label those claims \"reported, unpublished\" if quoted.\n", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Ming's most complete free conversation on hybrid intelligence, with a transcript." }, "page": "/catalogue/#res-other-ming-humans-plus-ai-ep13" }, { "id": "res-other-ming-lewis-silkin-conversation", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "In Conversation... with Vivienne Ming", "url": "https://www.lewissilkin.com/en/our-thinking/future-of-work-hub/insights/2024/10/02/in-conversation-with-vivienne-ming", "provider": "other-ming", "authors": [ "Vivienne Ming", "Lucy Lewis" ], "type": "podcast", "summary": "A 34-minute interview from a law firm's future-of-work series, with a written transcript. Ming describes three ways people use AI: self-automators who hand over the thinking, centaurs who split the work, and cyborgs who actively direct and argue with it. She says only the third makes people better at their jobs. Her practical advice: ask AI to critique your draft and then fix it yourself, and protect the routine tasks junior staff learn from.\n", "teaches": [ "cmp-steering", "cmp-use-responsibly", "cmp-check-the-result" ], "concepts": [ "con-productive-friction", "con-cognitive-offloading", "con-human-in-the-loop", "con-centaurs-and-cyborgs" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "34 minutes (audio) or about 20 minutes to read the transcript", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "written transcript on the page", "source_updated": "2024-10-02", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Fetched 2026-10-16. Her three-style split parallels Mollick's centaurs and cyborgs (res-other-mollick-centaurs-and-cyborgs) and adds the self-automator.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Ming's clearest free explanation of productive friction, with a transcript for readers who prefer text." }, "page": "/catalogue/#res-other-ming-lewis-silkin-conversation" }, { "id": "res-other-ming-robot-proof", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Robot-Proof: When Machines Have All the Answers, Build Better People", "url": "https://www.wiley.com/en-us/Robot-Proof%3A+When+Machines+Have+All+the+Answers%2C+Build+Better+People-p-9781394397808", "provider": "other-ming", "authors": [ "Vivienne Ming" ], "type": "book", "summary": "Vivienne Ming's 2026 book about people more than machines. She argues that AI handles questions with known answers well, so human value lies in open, ill-posed problems, and in traits such as curiosity, humility and perspective-taking that can be developed. It covers what predicts long-term outcomes for children, what makes teams smart, and why using AI to skip thinking may cost us. For readers who want the case for building people alongside tools.\n", "teaches": [ "cmp-use-responsibly", "cmp-frame-the-outcome" ], "concepts": [ "con-cognitive-offloading", "con-productive-friction", "con-human-in-the-loop" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "288 pages", "access": { "cost": "paid: hardcover $30.00, ebook $18.00 (Wiley list prices)", "login": "none", "checked": "2026-10-16" }, "accessibility": "audiobook edition exists (narrated by Kristen Kallen-Keck, per retailer listings)", "source_updated": "2026-03", "rights": { "licence": "all rights reserved (commercial book)", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Wiley product page fetched 2026-10-16 (ISBN 978-1-394-39780-8, March 2026). The book itself wasn't read; the summary draws on the publisher description and Ming's interviews (res-other-ming-fcat-interview, res-other-ming-humans-plus-ai-ep13). The publisher blurb names an \"Informational-Exploration Paradox\" without defining it. Research she reports from her own work (e.g. forecasting teams, student-discussion predictions) is described in talks and interviews; no peer-reviewed papers were found for it.\n", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "The fullest statement of Ming's argument that AI should make people more capable, not less." }, "page": "/catalogue/#res-other-ming-robot-proof" }, { "id": "res-other-ming-sim-2025-keynote", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "The AI That Asks Better Questions: Dr. Vivienne Ming at SIM 2025", "url": "https://citynomads.com/the-ai-that-asks-better-questions-dr-vivienne-ming-at-sim-2025/", "provider": "other-ming", "authors": [ "City Nomads" ], "type": "article", "summary": "A write-up of Ming's 2025 keynote in Porto. Her line is that AI should make your life harder in ways that make you better. She describes giving her book manuscript to a language model and asking it to find every place she lied, misled or oversimplified, and she says the best AI tutors hold back answers and ask questions. A quick introduction to her case for AI as a critic.\n", "teaches": [ "cmp-check-the-result", "cmp-use-responsibly" ], "concepts": [ "con-productive-friction", "con-verification", "con-cognitive-offloading" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "about 5 minutes", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2025-05-14", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Secondary source: a magazine's account of the talk, not Ming's own text. Fetched 2026-10-16. Source for prj-ask-ai-where-your-draft-misleads.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Records the manuscript-critique practice Ming describes, which the commons turns into a project card." }, "page": "/catalogue/#res-other-ming-sim-2025-keynote" }, { "id": "res-other-mollick-15-times-to-use-ai", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "15 Times to use AI, and 5 Not to", "url": "https://www.oneusefulthing.org/p/15-times-to-use-ai-and-5-not-to", "provider": "other-mollick", "authors": [ "Ethan Mollick" ], "type": "essay", "summary": "A checklist for deciding whether a task suits AI. Good fits include generating many ideas, work in your own field that you can judge quickly, low-stakes summaries and getting unstuck on a small problem. Poor fits include learning something you need to understand yourself, work that needs very high accuracy, and tasks where the struggle is how you reach the insight.\n", "teaches": [ "cmp-frame-the-outcome", "cmp-use-responsibly" ], "concepts": [ "con-jagged-frontier", "con-cognitive-offloading", "con-productive-friction", "con-sycophancy" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "about 15 minutes", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2024-12-09", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "feed", "signal": "https://www.oneusefulthing.org/feed", "bot_checkable": true }, "notes": "Fetched 2026-10-16; full text free.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "A usable when-to-use and when-not-to list; the 'not to' half gives the cognitive-offloading concept a practical form." }, "page": "/catalogue/#res-other-mollick-15-times-to-use-ai" }, { "id": "res-other-mollick-against-brain-damage", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Against \"Brain Damage\"", "url": "https://www.oneusefulthing.org/p/against-brain-damage", "provider": "other-mollick", "authors": [ "Ethan Mollick" ], "type": "essay", "summary": "Mollick pushes back on headlines claiming AI harms our brains and says the danger is thoughtless use. His practical advice is to come up with your own ideas and drafts first, then bring in AI as a reader, editor or devil's advocate, partly because ideas generated with AI tend to look alike.\n", "teaches": [ "cmp-frame-the-outcome", "cmp-steering" ], "concepts": [ "con-cognitive-offloading", "con-productive-friction", "con-ai-writing-tells" ], "audience": "nontechnical", "language": "en", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2025-07", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "unknown" }, "notes": "Mentions a tutor prompt under a Creative Commons licence (version unspecified); not covered by this record. A reviewer could confirm the RSS feed as the freshness signal.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Thinking-with-AI reading list: the clearest source for 'think first, then use AI'." }, "page": "/catalogue/#res-other-mollick-against-brain-damage" }, { "id": "res-other-mollick-ai-job-interview", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Giving your AI a Job Interview", "url": "https://www.oneusefulthing.org/p/giving-your-ai-a-job-interview", "provider": "other-mollick", "authors": [ "Ethan Mollick" ], "type": "essay", "summary": "Explains why public benchmark scores tell you little about whether a model suits your work, and suggests testing models the way you'd interview a job candidate: give them realistic tasks from your field, grade the answers blind and repeat on judgment calls. In one test he asked several models to rate a dubious business idea ten times each; each model was consistent, but their scores differed by 3 to 4 points out of 10.\n", "teaches": [ "cmp-check-the-result", "cmp-frame-the-outcome" ], "concepts": [ "con-evals", "con-model-choice", "con-jagged-frontier" ], "audience": "mixed", "language": "en", "prerequisites": "none", "effort": "about 15 minutes", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2025-11-12", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "feed", "signal": "https://www.oneusefulthing.org/feed", "bot_checkable": true }, "notes": "Fetched 2026-10-16; full text free. Parts of the method (expert-built multi-hour tasks) suit organisations more than individuals; the repeat-the-question test works for anyone.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "The reasoning behind prj-compare-models-on-a-real-task, explained for knowledge workers." }, "page": "/catalogue/#res-other-mollick-ai-job-interview" }, { "id": "res-other-mollick-assigning-ai", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Assigning AI: Seven Approaches for Students, with Prompts", "url": "https://arxiv.org/abs/2306.10052", "provider": "other-mollick", "authors": [ "Ethan Mollick", "Lilach Mollick" ], "type": "paper", "summary": "Describes seven roles you can give an AI, such as mentor, tutor, coach, teammate, student, simulator and tool, each with example prompts and the risks to watch for. Written for classrooms, but the roles work for anyone deciding how AI should help.\n", "teaches": [ "cmp-frame-the-outcome", "cmp-describe-the-task" ], "concepts": [ "con-prompting", "con-custom-instructions", "con-human-in-the-loop" ], "audience": "mixed", "language": "en", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2023", "rights": { "licence": "CC BY-NC-SA 4.0", "evidence": "https://arxiv.org/abs/2306.10052", "use": "link-and-summarise", "attribution": "Ethan Mollick and Lilach Mollick, Assigning AI: Seven Approaches for Students, with Prompts, arXiv:2306.10052" }, "freshness": { "method": "unknown" }, "notes": "Licence from the arXiv abstract page (checked 2026-10-16): CC BY-NC-SA 4.0, so link and summarise only, never adapt. URL moved from SSRN (blocks bots, papers.ssrn.com abstract 4475995) to the free arXiv version, submitted 2023-06-13.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Thinking-with-AI reading list: practical menu of roles for AI as a thinking partner." }, "page": "/catalogue/#res-other-mollick-assigning-ai" }, { "id": "res-other-mollick-centaurs-and-cyborgs", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Centaurs and Cyborgs on the Jagged Frontier", "url": "https://www.oneusefulthing.org/p/centaurs-and-cyborgs-on-the-jagged", "provider": "other-mollick", "authors": [ "Ethan Mollick" ], "type": "essay", "summary": "Mollick's plain-language account of a 2023 experiment with 758 Boston Consulting Group consultants. With GPT-4, they finished more tasks, faster and to a higher standard, but on one task the AI got wrong they did worse than colleagues working alone. The post names two ways of working well with AI: centaurs split tasks between person and AI, and cyborgs weave the two together.\n", "teaches": [ "cmp-check-the-result", "cmp-frame-the-outcome" ], "concepts": [ "con-jagged-frontier", "con-human-in-the-loop", "con-verification", "con-centaurs-and-cyborgs" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "about 15 minutes", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2023-09-16", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "feed", "signal": "https://www.oneusefulthing.org/feed", "bot_checkable": true }, "notes": "Fetched 2026-10-16; full text free. Reported figures: 12.2% more tasks, 25.1% faster, about 40% higher quality; on the task outside the frontier, 84% correct without AI vs 60-70% with it. Underlying working paper (Dell'Acqua et al., not peer-reviewed at the time): https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4573321 (SSRN, not fetched). Feed URL is the standard Substack feed and wasn't fetched.\n", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "The origin of the jagged-frontier idea already in the concept map, plus the centaur/cyborg distinction, from the person who coined both." }, "page": "/catalogue/#res-other-mollick-centaurs-and-cyborgs" }, { "id": "res-other-mollick-choosing-to-stay-human", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Choosing to Stay Human", "url": "https://www.oneusefulthing.org/p/choosing-to-stay-human", "provider": "other-mollick", "authors": [ "Ethan Mollick" ], "type": "essay", "summary": "Ethan Mollick argues that the risk lies in using AI on autopilot, and pulls together studies showing that skipping effort means skipping learning. He points readers to the tutoring modes now built into chat tools and asks everyone to keep deciding what to hand over and what to keep for themselves.\n", "teaches": [ "cmp-frame-the-outcome", "cmp-use-responsibly" ], "concepts": [ "con-cognitive-offloading", "con-productive-friction", "con-jagged-frontier" ], "audience": "nontechnical", "language": "en", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-05-26", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "unknown" }, "notes": "Substack newsletter; a reviewer could confirm its RSS feed as the freshness signal.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Thinking-with-AI reading list: accessible synthesis of the evidence on offloading." }, "page": "/catalogue/#res-other-mollick-choosing-to-stay-human" }, { "id": "res-other-mollick-co-intelligence", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Co-Intelligence: Living and Working with AI", "url": "https://www.penguinrandomhouse.com/books/741805/co-intelligence-by-ethan-mollick/", "provider": "other-mollick", "authors": [ "Ethan Mollick" ], "type": "book", "summary": "Mollick's 2024 book for general readers on working alongside AI as a coworker, tutor, coach and creative partner. It is best known for four rules, roughly: always invite AI to the table, be the human in the loop, treat AI like a person but tell it what kind of person it is, and assume this is the worst AI you will ever use. A good single read for someone who wants the big picture before practising.\n", "teaches": [ "cmp-frame-the-outcome", "cmp-steering", "cmp-use-responsibly" ], "concepts": [ "con-jagged-frontier", "con-human-in-the-loop", "con-custom-instructions", "con-generative-ai", "con-centaurs-and-cyborgs" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "256 pages; audiobook 4 hours 39 minutes", "access": { "cost": "paid: hardcover $30.00 list; ebook and audiobook available", "login": "none", "checked": "2026-10-16" }, "accessibility": "audiobook edition available", "source_updated": "2024-04-02", "rights": { "licence": "all rights reserved (commercial book)", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Publisher page fetched 2026-10-16 (Portfolio, ISBN 9780593716717). Rule wording above comes from reviews and summaries, not the book itself; check exact phrasing before quoting. Mollick announced a follow-up book, Co-Existence, due 2026-10-20 (https://www.oneusefulthing.org/p/co-existence-and-the-end-of-co-intelligence); not catalogued yet because it isn't out.\n", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Paid, but the standard general-audience book on working with AI; its four rules are widely taught." }, "page": "/catalogue/#res-other-mollick-co-intelligence" }, { "id": "res-other-mollick-cybernetic-teammate", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "The Cybernetic Teammate", "url": "https://www.oneusefulthing.org/p/the-cybernetic-teammate", "provider": "other-mollick", "authors": [ "Ethan Mollick" ], "type": "essay", "summary": "Reports a randomised trial with 776 Procter & Gamble professionals working on real product development tasks. One person working with AI did about as well as a two-person team without it, and teams with AI were the most likely to produce top-ranked ideas. AI users also finished 12-16% faster and reported feeling more positive. Useful for team leads deciding how AI should fit into group work.\n", "teaches": [ "cmp-frame-the-outcome", "cmp-make-it-repeatable" ], "concepts": [ "con-human-in-the-loop", "con-jagged-frontier" ], "audience": "mixed", "language": "en", "prerequisites": "none", "effort": "about 15 minutes", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2025-03-22", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "feed", "signal": "https://www.oneusefulthing.org/feed", "bot_checkable": true }, "notes": "Fetched 2026-10-16; full text free. Pre-registered trial using GPT-4/GPT-4o in one-day workshops. Paper: \"The Cybernetic Teammate: A Field Experiment on Generative AI Reshaping Teamwork and Expertise\", https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5188231 (SSRN, not fetched; access unknown).\n", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "The strongest field evidence on AI in teams rather than individuals; supports the adoption lane." }, "page": "/catalogue/#res-other-mollick-cybernetic-teammate" }, { "id": "res-other-mollick-gail-prompt-library", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Wharton Generative AI Labs Prompt Library", "url": "https://gail.wharton.upenn.edu/prompt-library/", "provider": "other-mollick", "authors": [ "Ethan Mollick", "Lilach Mollick", "Wharton Generative AI Labs" ], "type": "prompt-library", "summary": "Seventeen tested prompts you paste into a chat tool, each of which sets the AI up as a coach, tutor or role-play partner that asks one question at a time. Examples include a devil's advocate for a team decision, a team after-action review, a team charter, a meeting midpoint facilitator, a problem-reframing prompt and builders that help you make your own tutor or simulation. Most were written for teaching, but about half are tagged for professional use.\n", "teaches": [ "cmp-describe-the-task", "cmp-steering", "cmp-make-it-repeatable" ], "concepts": [ "con-prompting", "con-custom-instructions", "con-productive-friction", "con-clarifying-questions", "con-custom-assistants" ], "audience": "mixed", "language": "en", "prerequisites": "none", "effort": "5-30 minutes per prompt", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "CC-BY-4.0", "evidence": "https://gail.wharton.upenn.edu/prompt-library/", "use": "adapt", "attribution": "Prompts by Ethan Mollick and Lilach Mollick, Wharton Generative AI Labs, licensed CC BY 4.0" }, "freshness": { "method": "manual", "signal": "https://gail.wharton.upenn.edu/prompt-library/", "bot_checkable": false }, "notes": "Fetched 2026-10-16. The licence covers the prompts only: the page says \"Prompts on this page (but no other content on the site)\" are CC BY 4.0, and each prompt page in the library (a public Notion database, https://hd3ns092ns.notion.site/1b3dc3333315802a9e99cafedb321048) repeats that notice. Site text, images and guidance are not covered, so link and summarise those. The tested-model list includes ChatGPT 5.1, so the library was updated in late 2025 or later; individual prompt dates are blank.\n", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "The only openly licensed (CC BY 4.0) prompt set from these sources; its coach-style prompts can be adapted into commons skills with credit." }, "page": "/catalogue/#res-other-mollick-gail-prompt-library" }, { "id": "res-other-mollick-good-enough-prompting", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Getting started with AI: Good enough prompting", "url": "https://www.oneusefulthing.org/p/getting-started-with-ai-good-enough", "provider": "other-mollick", "authors": [ "Ethan Mollick" ], "type": "essay", "summary": "A short starter guide for people who feel they need to learn prompt engineering first. Mollick says to treat the AI like a capable new coworker who forgets everything between chats: give context, say who the work is for, ask for many options and keep talking. His main instruction is to spend about ten hours using it on real tasks in your own field, where you can spot its mistakes.\n", "teaches": [ "cmp-describe-the-task", "cmp-steering" ], "concepts": [ "con-prompting", "con-prompt-engineering", "con-context-engineering", "con-hallucination" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "about 10 minutes to read; the advice asks for about 10 hours of practice", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2024-11-24", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "feed", "signal": "https://www.oneusefulthing.org/feed", "bot_checkable": true }, "notes": "Fetched 2026-10-16; full text free. Page footer shows © Ethan Mollick and no open licence.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Gives beginners permission to start without technique and a concrete practice target (ten hours on real work)." }, "page": "/catalogue/#res-other-mollick-good-enough-prompting" }, { "id": "res-other-mollick-instructors-as-innovators", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Instructors as Innovators: A future-focused approach to new AI learning opportunities, with prompts", "url": "https://arxiv.org/abs/2407.05181", "provider": "other-mollick", "authors": [ "Ethan Mollick", "Lilach Mollick" ], "type": "paper", "summary": "A 76-page guide with ready-to-use prompts for AI exercises: simulations, mentoring, coaching and co-creation, each with notes on how to run it, how to assess it and what can go wrong. It also includes \"blueprint\" prompts that interview you and then write a custom prompt for your own topic. Written for teachers, but useful to anyone who trains or coaches colleagues.\n", "teaches": [ "cmp-describe-the-task", "cmp-make-it-repeatable", "cmp-use-responsibly" ], "concepts": [ "con-prompting", "con-custom-instructions", "con-custom-assistants", "con-productive-friction" ], "audience": "mixed", "language": "en", "prerequisites": "none", "effort": "76 pages; prompts in Appendices A and B", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2024-04-23", "rights": { "licence": "CC-BY-4.0", "evidence": "https://arxiv.org/abs/2407.05181", "use": "adapt", "attribution": "Ethan Mollick and Lilach Mollick, Instructors as Innovators (arXiv:2407.05181), CC BY 4.0" }, "freshness": { "method": "manual" }, "notes": "arXiv abstract page fetched 2026-10-16; it links the CC BY 4.0 licence. Also on SSRN (abstract 4802463), whose licence wasn't checked; adapt only from the arXiv version. Prompts were written for 2024 models.\n", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Openly licensed source of tested coaching and blueprint prompts; a direct input for practice-coach and make-it-repeatable." }, "page": "/catalogue/#res-other-mollick-instructors-as-innovators" }, { "id": "res-other-mollick-leadership-lab-crowd", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Making AI Work: Leadership, Lab, and Crowd", "url": "https://www.oneusefulthing.org/p/making-ai-work-leadership-lab-and", "provider": "other-mollick", "authors": [ "Ethan Mollick" ], "type": "essay", "summary": "A plan for bringing AI into an organisation through three groups. Leaders describe what an AI-enabled workplace will look like and promise that sharing productivity gains won't cost people their jobs. Employees experiment in their own work and share what works. A small lab team turns the best of it into tools and tests. He points out that many workers use AI without telling anyone, and the organisation can't learn from use it doesn't know about.\n", "teaches": [ "cmp-make-it-repeatable", "cmp-use-responsibly" ], "concepts": [ "con-automation", "con-evals", "con-custom-assistants", "con-adoption-rituals" ], "audience": "mixed", "language": "en", "prerequisites": "none", "effort": "about 20 minutes", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2025-05-22", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "feed", "signal": "https://www.oneusefulthing.org/feed", "bot_checkable": true }, "notes": "Fetched 2026-10-16; full text free. Much of the productivity evidence he cites is self-reported, which he acknowledges. For team leads and people running AI programmes.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "The clearest short adoption model for teams: who leads, who experiments, who scales." }, "page": "/catalogue/#res-other-mollick-leadership-lab-crowd" }, { "id": "res-other-mollick-management-as-ai-superpower", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Management as AI superpower", "url": "https://www.oneusefulthing.org/p/management-as-ai-superpower", "provider": "other-mollick", "authors": [ "Ethan Mollick" ], "type": "essay", "summary": "Argues that working with AI agents mostly uses ordinary management skills: delegating, giving clear instructions and judging the work. Mollick offers a quick test for whether to delegate (how long the task takes you, how often the AI gets it right, how long asking and checking take) and lists what a good handover covers: the goal and why, limits on authority, what done looks like, checkpoints and a self-check. Includes a class where executive MBA students, most of whom had never coded, built working startup prototypes in four days.\n", "teaches": [ "cmp-describe-the-task", "cmp-steering", "cmp-check-the-result" ], "concepts": [ "con-agents", "con-steering", "con-human-in-the-loop", "con-vibe-coding", "con-verification", "con-allocation-economy", "con-delegating-to-ai" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "about 20 minutes", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-01-27", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "feed", "signal": "https://www.oneusefulthing.org/feed", "bot_checkable": true }, "notes": "Fetched 2026-10-16; full text free. The delegation estimate uses OpenAI's GDPval figures (about 7 hours of expert work, about 1 hour to check, roughly 72% tie-or-win rate); treat the \"about 3 hours saved\" figure as his worked example. Source for prj-delegation-brief-for-an-agent.\n", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Turns delegating to an agent into a skill managers already have, with a concrete brief checklist." }, "page": "/catalogue/#res-other-mollick-management-as-ai-superpower" }, { "id": "res-other-mollick-which-ai-summer-2026", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "An opinionated guide to which AI to use to do stuff (Summer 2026 Edition)", "url": "https://www.oneusefulthing.org/p/an-opinionated-guide-to-which-ai-b22", "provider": "other-mollick", "authors": [ "Ethan Mollick" ], "type": "guide", "summary": "Mollick's mid-2026 buyer's guide for people who aren't developers. He matches tools to jobs: free chatbots for low-stakes questions, the strongest paid models for second opinions, cloud agents such as ChatGPT Work and Claude Cowork for delegated tasks, and local agents such as Codex and Claude Code for large projects. He also says how to start safely: connect only apps you're comfortable with, and keep approvals on for anything that sends, spends or deletes.\n", "teaches": [ "cmp-frame-the-outcome", "cmp-use-responsibly", "cmp-steering" ], "concepts": [ "con-model-choice", "con-agents", "con-tools-and-connectors", "con-human-in-the-loop", "con-privacy-and-data" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "about 20 minutes", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-07-23", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "feed", "signal": "https://www.oneusefulthing.org/feed", "bot_checkable": true }, "notes": "Fetched 2026-10-16. Mollick rewrites this guide every few months under a new URL (earlier editions: 2025-10-19 an-opinionated-guide-to-using-ai, 2026-02-18 a-guide-to-which-ai-to-use-in-the). A reviewer should swap the URL when the next edition appears and mark this one stale. Product names will date fast.\n", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "The most widely read plain-language 'which tool for which job' guide; pairs with con-model-choice and prj-compare-models-on-a-real-task." }, "page": "/catalogue/#res-other-mollick-which-ai-summer-2026" }, { "id": "res-other-mollick-working-with-wizards", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "On Working with Wizards", "url": "https://www.oneusefulthing.org/p/on-working-with-wizards", "provider": "other-mollick", "authors": [ "Ethan Mollick" ], "type": "essay", "summary": "As AI produces larger pieces of finished work, you can see less of how it got there, and checking every detail can take as long as doing the job. Mollick suggests deciding when to use AI as a partner you talk with versus a \"wizard\" you hand a whole task to, judging the result, and asking whether it is good enough for this purpose. He also warns that leaning on AI can wear away the expertise you need to check it.\n", "teaches": [ "cmp-check-the-result", "cmp-steering", "cmp-use-responsibly" ], "concepts": [ "con-verification", "con-human-in-the-loop", "con-cognitive-offloading", "con-agents", "con-delegating-to-ai" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "about 15 minutes", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2025-09-11", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "feed", "signal": "https://www.oneusefulthing.org/feed", "bot_checkable": true }, "notes": "Fetched 2026-10-16; full text free.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Names the verification problem that grows as people move from chat to agents; useful framing for prove-it." }, "page": "/catalogue/#res-other-mollick-working-with-wizards" }, { "id": "res-other-peter-yang-12-rules-vibe-coding", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "12 Rules to Vibe Code Without Frustration", "url": "https://creatoreconomy.so/p/12-rules-to-vibe-code-without-frustration", "provider": "other-peter-yang", "authors": [ "Peter Yang" ], "type": "essay", "summary": "Peter Yang's tips from more than 50 hours of building apps with AI as someone who doesn't code. The rules start before any code: have the AI write a short readme with requirements and a few milestones, ask for a plan and the simplest options first, then build in small steps, test after each change and roll back when something breaks. A good checklist for a first app build.\n", "teaches": [ "cmp-frame-the-outcome", "cmp-describe-the-task", "cmp-check-the-result" ], "concepts": [ "con-vibe-coding", "con-smallest-useful-version", "con-context-engineering", "con-verification", "con-multimodal" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "about 10 minutes", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2025-03-19", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Fetched 2026-10-16; full text visible. Some tool names will date quickly; the planning rules hold up. Basis for project card prj-write-a-build-readme-before-you-vibe-code.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Free, concrete rules for non-engineers building with AI, led by planning before code." }, "page": "/catalogue/#res-other-peter-yang-12-rules-vibe-coding" }, { "id": "res-other-peter-yang-20-claude-code-tips", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "20 Tips to Master Claude Code in 35 Minutes (Build a Real App)", "url": "https://creatoreconomy.so/p/20-tips-to-master-claude-code-in-35-min-build-an-app", "provider": "other-peter-yang", "authors": [ "Peter Yang" ], "type": "video tutorial", "summary": "A product manager's tour of Claude Code while building an app. The free part covers planning before code, asking for the simplest option first, going from spec to to-do list to code, and setting up a project memory file with your preferences. Later tips on debugging and version control are paid.\n", "teaches": [ "cmp-describe-the-task", "cmp-steering" ], "concepts": [ "con-vibe-coding", "con-custom-instructions", "con-memory", "con-agents" ], "audience": "mixed", "language": "en", "prerequisites": "Claude Code installed; some familiarity with web app terms helps.", "effort": "about 35 minutes", "access": { "cost": "partly paid: first six tips free, rest needs a paid subscription (price not checked)", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2025-09-24", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "PARTLY PAYWALLED. Fetched 2026-10-16; only the intro and tips 1-6 visible.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "A step up from the 12 rules for people moving into Claude Code." }, "page": "/catalogue/#res-other-peter-yang-20-claude-code-tips" }, { "id": "res-other-peter-yang-ai-learning-path", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Introducing My New AI Learning Path and Co-Pilot", "url": "https://creatoreconomy.so/p/introducing-my-new-ai-learning-path-and-co-pilot", "provider": "other-peter-yang", "authors": [ "Peter Yang" ], "type": "reading list", "summary": "A starting map to Peter Yang's tutorials, sorted into six tracks: a personal AI assistant, career, saving time at work, prototypes and apps, workflows and agents, and building AI products. Each entry is marked if it is a video interview or a paid post. Useful for picking a first tutorial by goal rather than by date.\n", "teaches": [ "cmp-frame-the-outcome" ], "concepts": [ "con-custom-assistants", "con-vibe-coding", "con-automation", "con-agents" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "the list itself takes 5 minutes; each linked post about 5 minutes", "access": { "cost": "free post; about half the linked posts and the AI co-pilot need a paid subscription (price not checked)", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2025-08-27", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Fetched 2026-10-16. The post links a fuller collection at creatoreconomy.so/s/ai-track, which returned 404 when checked.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Learning and upskilling: a goal-sorted entry point to his tutorials." }, "page": "/catalogue/#res-other-peter-yang-ai-learning-path" }, { "id": "res-other-peter-yang-behind-the-craft-transcripts", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Behind the Craft — Transcripts", "url": "https://github.com/petergyang/behind-the-craft-transcripts", "provider": "other-peter-yang", "authors": [ "Peter Yang" ], "type": "transcript archive", "summary": "Full transcripts of Peter Yang's YouTube tutorials and interviews (181 episodes when checked), each tagged with title, guest, date and topics, plus a topic index. You can load the folder into an AI tool and ask questions across all of it. Also a tidy example of publishing your own work in a form AI tools can read.\n", "teaches": [ "cmp-describe-the-task" ], "concepts": [ "con-projects-and-knowledge", "con-context-engineering", "con-deep-research" ], "audience": "mixed", "language": "en", "prerequisites": "Basic GitHub use (download or clone) to load the files into an AI tool.", "effort": "unknown", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "Text transcripts of video content.", "source_updated": "2026-10-16", "rights": { "licence": "none stated", "evidence": "https://github.com/petergyang/behind-the-craft-transcripts", "use": "link-and-summarise" }, "freshness": { "method": "feed", "signal": "https://api.github.com/repos/petergyang/behind-the-craft-transcripts/commits", "bot_checkable": true }, "notes": "Checked with gh api 2026-10-16: 34 stars, last push 2026-10-16, no licence file. Link only; do not copy transcripts.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Turns his whole tutorial back catalogue into something a learner's agent can search." }, "page": "/catalogue/#res-other-peter-yang-behind-the-craft-transcripts" }, { "id": "res-other-peter-yang-behind-the-craft-youtube", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Behind the Craft (YouTube channel)", "url": "https://www.youtube.com/@PeterYangYT", "provider": "other-peter-yang", "authors": [ "Peter Yang" ], "type": "video channel", "summary": "Peter Yang's channel of practical AI tutorials and interviews with people who build AI products. Many tutorials show a full build on screen in under 30 minutes, such as a slide deck, a research agent or a small app, which makes them easy to follow along with.\n", "teaches": [ "cmp-describe-the-task", "cmp-make-it-repeatable" ], "concepts": [ "con-vibe-coding", "con-agents", "con-skills", "con-automation" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "most videos 10-40 minutes", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "Transcripts published separately: res-other-peter-yang-behind-the-craft-transcripts.", "source_updated": "unknown", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Channel URL confirmed reachable 2026-10-16 and linked from the transcripts repo; individual videos not reviewed.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Hub for his follow-along tutorials." }, "page": "/catalogue/#res-other-peter-yang-behind-the-craft-youtube" }, { "id": "res-other-peter-yang-chatgpt-claude-gemini-use-cases", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "ChatGPT vs Claude vs Gemini: The Best AI Model for Each Use Case in 2025", "url": "https://creatoreconomy.so/p/chatgpt-vs-claude-vs-gemini-the-best-ai-model-for-each-use-case-2025", "provider": "other-peter-yang", "authors": [ "Peter Yang" ], "type": "essay", "summary": "Peter Yang gives the same tasks to three AI assistants, such as editing his own draft from his writing samples and researching a market, and says which one he would use for each kind of work. The verdicts are from mid-2025 and will age, but the method is worth copying: one real task, the same prompt to each, and a judgement you write down.\n", "teaches": [ "cmp-check-the-result", "cmp-describe-the-task" ], "concepts": [ "con-model-choice", "con-deep-research", "con-jagged-frontier" ], "audience": "nontechnical", "language": "en", "prerequisites": "none", "effort": "about 15 minutes", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2025-06-04", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Fetched 2026-10-16; full text visible. Informal single-trial tests, not benchmarks; product verdicts are dated. Pairs with prj-compare-models-on-a-real-task.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "A worked example of comparing models on your own tasks, which the commons already teaches." }, "page": "/catalogue/#res-other-peter-yang-chatgpt-claude-gemini-use-cases" }, { "id": "res-other-peter-yang-human-review-skill", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Use My /Human-Review Skill to Edit HTML and Markdown Files Visually", "url": "https://creatoreconomy.so/p/use-my-human-review-skill-to-edit-html-markdown-visually", "provider": "other-peter-yang", "authors": [ "Peter Yang" ], "type": "tool tutorial", "summary": "Introduces a free skill that opens a document or web page your AI made in the browser, where you edit text directly and leave comments as you would in a shared doc, then send all of it to the agent in one batch. It replaces long chat messages like \"in the third paragraph, change X\". For anyone reviewing AI-made plans, pages or copy.\n", "teaches": [ "cmp-check-the-result", "cmp-steering" ], "concepts": [ "con-human-in-the-loop", "con-artifacts", "con-skills", "con-steering" ], "audience": "nontechnical", "language": "en", "prerequisites": "An AI coding agent such as Claude Code or Codex to install the skill.", "effort": "about 10 minutes", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-08-05", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Fetched 2026-10-16. The post states no licence; the tool repo petergyang/human-review is MIT (proposed field skill fld-peter-yang-human-review).", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Makes human review of AI output faster and more precise, which the commons wants learners to do every time." }, "page": "/catalogue/#res-other-peter-yang-human-review-skill" }, { "id": "res-other-peter-yang-n8n-newsletter-digest", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "n8n Tutorial: Build an AI Workflow to Extract Top Insights From All Your Newsletter Emails", "url": "https://creatoreconomy.so/p/n8n-tutorial-build-an-ai-workflow-to-get-a-weekly-digest-newsletter-emails", "provider": "other-peter-yang", "authors": [ "Peter Yang" ], "type": "tutorial", "summary": "Builds a weekly automation in n8n that collects every email you have labelled as a newsletter, passes them to an AI model with a summary prompt and emails you one digest on Sunday morning. A concrete first automation for anyone drowning in subscriptions, with each node's settings spelled out.\n", "teaches": [ "cmp-make-it-repeatable", "cmp-describe-the-task" ], "concepts": [ "con-automation", "con-scheduled-tasks", "con-tools-and-connectors", "con-context-window" ], "audience": "nontechnical", "language": "en", "prerequisites": "A Gmail account and an n8n account (14-day free trial at time of writing).", "effort": "unknown", "access": { "cost": "paid post: setup steps 1-4 visible free, the prompt and final step need a paid subscription (price not checked)", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2025-07-30", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "PARTLY PAYWALLED. Fetched 2026-10-16. The digest prompt is behind the paywall. The tutorial connects your inbox to a third-party service; check what your workplace allows.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "A reproducible first scheduled automation with settings shown node by node." }, "page": "/catalogue/#res-other-peter-yang-n8n-newsletter-digest" }, { "id": "res-other-peter-yang-slides-claude-code", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Build Beautiful Slides with Claude Code in 12 Minutes (12 Formats + 3 Templates)", "url": "https://creatoreconomy.so/p/build-beautiful-slides-with-claude-code-in-12-min", "provider": "other-peter-yang", "authors": [ "Peter Yang" ], "type": "video tutorial", "summary": "Shows a slide-making skill that takes a rough outline, asks you questions about the content, looks up gaps, builds the deck as a single web page and then screenshots each slide to fix its own layout problems. The habit worth taking away is the last step: have the AI look at what it made and fix it before you see it.\n", "teaches": [ "cmp-make-it-repeatable", "cmp-check-the-result" ], "concepts": [ "con-skills", "con-clarifying-questions", "con-artifacts", "con-verification" ], "audience": "nontechnical", "language": "en", "prerequisites": "Claude Code installed.", "effort": "about 12 minutes", "access": { "cost": "free to read; the /slides skill needs a paid Behind the Craft membership (price not checked)", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-05-27", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "manual" }, "notes": "Fetched 2026-10-16; article visible, skill gated, no public repo.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Clear example of a skill with a built-in self-check loop." }, "page": "/catalogue/#res-other-peter-yang-slides-claude-code" }, { "id": "res-other-rieseberg-be-ambitious", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "How to be more ambitious: A tutorial for humans with models", "url": "https://felixrieseberg.com/how-to-be-more-ambitious-a-tutorial-for-humans-with-models/", "provider": "other-felix-rieseberg", "authors": [ "Felix Rieseberg" ], "type": "essay", "summary": "A practical essay on asking more of AI. It describes kinds of ambition, such as aiming at the goal behind your goal, asking for a deeper version of a task rather than a bigger one, and having the AI play the real roles of a team. It also advises against letting a model judge its own work.\n", "teaches": [ "cmp-frame-the-outcome", "cmp-describe-the-task", "cmp-check-the-result" ], "concepts": [ "con-prompting", "con-evals", "con-verification", "con-jagged-frontier" ], "audience": "nontechnical", "language": "en", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2026-10-13", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "unknown" }, "notes": "Page states no licence. URL found by the seed agent via search; the research notes gave no link.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Thinking-with-AI reading list: concrete moves for raising ambition and using outside checks." }, "page": "/catalogue/#res-other-rieseberg-be-ambitious" }, { "id": "res-other-sarkar-challenge-not-obey", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "AI Should Challenge, Not Obey", "url": "https://arxiv.org/abs/2411.02263", "provider": "other-acm", "authors": [ "Advait Sarkar" ], "type": "essay", "summary": "Advait Sarkar argues that AI should sometimes act as a provocateur, offering counterarguments, critiques and questions instead of finishing your work for you. He also warns that constant criticism gets tiresome, so the challenge has to fit the moment. Short and readable for anyone curious about AI as a tool for thinking.\n", "teaches": [ "cmp-steering", "cmp-check-the-result" ], "concepts": [ "con-productive-friction", "con-sycophancy", "con-cognitive-offloading" ], "audience": "mixed", "language": "en", "access": { "cost": "free", "login": "none", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "2024-10", "rights": { "licence": "unknown", "use": "link-and-summarise" }, "freshness": { "method": "unknown" }, "notes": "Published in Communications of the ACM, October 2024; linked here via the free arXiv copy. Check the arXiv licence.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Thinking-with-AI reading list: the core argument for AI that argues against you." }, "page": "/catalogue/#res-other-sarkar-challenge-not-obey" }, { "id": "res-perplexity-academy", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Perplexity Academy", "url": "https://www.perplexity.ai/hub/academy", "provider": "perplexity", "authors": [ "Perplexity" ], "type": "video lessons", "summary": "A library of short video lessons, a few minutes each, on using Perplexity's search and its Computer feature for multi-step work. Most lessons are product how-tos rather than general skills.\n", "teaches": [ "cmp-describe-the-task" ], "concepts": [ "con-deep-research", "con-agents" ], "audience": "nontechnical", "language": "en", "effort": "2-4 minutes per lesson", "access": { "cost": "free to watch; Computer features need a paid or Enterprise plan (UNVERIFIED)", "login": "unknown", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "all rights reserved", "use": "link-and-summarise" }, "freshness": { "method": "manual", "signal": "no dates on page; FAQ says lessons are added about weekly", "bot_checkable": false }, "notes": "Terms bar copying and scrapers: link only. Paid plan for Computer UNVERIFIED.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Perplexity's own entry point; covers research and agent-style work." }, "page": "/catalogue/#res-perplexity-academy" }, { "id": "res-perplexity-at-work", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Perplexity at Work Guide", "url": "https://www.perplexity.ai/hub/guides/perplexity-at-work", "provider": "perplexity", "authors": [ "Perplexity" ], "type": "guide", "summary": "A downloadable guide on using Perplexity in daily work, organised around cutting distractions, extending what you can research and write, and reaching concrete outcomes. It reads as product marketing, so use it for ideas rather than method.\n", "teaches": [ "cmp-frame-the-outcome" ], "concepts": [ "con-deep-research", "con-automation" ], "audience": "nontechnical", "language": "en", "access": { "cost": "free; may be gated by a form (UNVERIFIED)", "login": "unknown", "checked": "unknown" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "all rights reserved", "use": "link-and-summarise" }, "freshness": { "method": "unknown", "bot_checkable": false }, "notes": "Vendor-marketing tone; summarise, don't quote. Check whether the download asks for contact details.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Workplace use cases for research-led AI tools." }, "page": "/catalogue/#res-perplexity-at-work" }, { "id": "res-perplexity-evaluating-ai-high-stakes", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Evaluating AI for high-stakes work", "url": "https://www.perplexity.ai/hub/guides/evaluating-ai-for-high-stakes-work", "provider": "perplexity", "authors": [ "Perplexity" ], "type": "guide", "summary": "A guide for teams in finance, legal and research who must check AI work before it shapes a decision. It reviews output for accuracy, transparency and human oversight, and helps you spot risky workflows and choose what to automate first.\n", "teaches": [ "cmp-check-the-result", "cmp-use-responsibly" ], "concepts": [ "con-verification", "con-human-in-the-loop", "con-hallucination", "con-evals" ], "audience": "mixed", "language": "en", "access": { "cost": "free (gating UNVERIFIED)", "login": "unknown", "checked": "unknown" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "all rights reserved", "use": "link-and-summarise" }, "freshness": { "method": "unknown", "bot_checkable": false }, "notes": "Aimed at business decision-makers. Check whether the download is gated by a form.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Rare provider guide focused on checking output when stakes are high." }, "page": "/catalogue/#res-perplexity-evaluating-ai-high-stakes" }, { "id": "res-perplexity-search-vs-computer", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Search vs Computer", "url": "https://www.perplexity.ai/hub/academy/search-vs-computer", "provider": "perplexity", "authors": [ "Perplexity" ], "type": "video lesson", "summary": "A short lesson on when a quick cited answer is enough and when to hand over a multi-step job that pulls from several tools, builds a report and can run on a schedule. It ends with a simple checklist for choosing between the two.\n", "teaches": [ "cmp-frame-the-outcome" ], "concepts": [ "con-model-choice", "con-deep-research", "con-agents", "con-scheduled-tasks" ], "audience": "nontechnical", "language": "en", "effort": "about 4 minutes", "access": { "cost": "free to watch", "login": "unknown", "checked": "unknown" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "all rights reserved", "use": "link-and-summarise" }, "freshness": { "method": "unknown", "bot_checkable": false }, "notes": "Product-specific framing, but the choose-the-right-tool idea is general.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Teaches picking the right kind of AI help for the job." }, "page": "/catalogue/#res-perplexity-search-vs-computer" }, { "id": "res-xai-grok-bot-use-cases", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Grok Bot use cases", "url": "https://docs.x.ai/grok-bot/use-cases", "provider": "xai", "authors": [ "xAI" ], "type": "use-case page", "summary": "A page of example roles for xAI's Grok Bot, which gathers and prepares work across connected tools and hands it back for review, with outside actions held for your approval. Examples include sales outreach, recruiting, expenses and a chief-of-staff assistant. Use it for project ideas; it does not teach skills.\n", "teaches": [ "cmp-make-it-repeatable", "cmp-steering" ], "concepts": [ "con-agents", "con-tools-and-connectors", "con-human-in-the-loop", "con-scheduled-tasks" ], "audience": "nontechnical", "language": "en", "access": { "cost": "unknown; the product is likely paid (UNVERIFIED)", "login": "unknown", "checked": "unknown" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "all rights reserved", "use": "link-and-summarise" }, "freshness": { "method": "llms-txt", "signal": "docs.x.ai llms.txt", "bot_checkable": false }, "notes": "Plan and price not stated on the page; verify. Use as inspiration-card source.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Concrete agent use cases with an approval step, useful for inspiration cards." }, "page": "/catalogue/#res-xai-grok-bot-use-cases" }, { "id": "res-xai-grok-overview", "schema": "resource/1", "layer": "garden", "status": "candidate", "title": "Welcome to Grok (consumer docs)", "url": "https://docs.x.ai/grok/overview", "provider": "xai", "authors": [ "xAI" ], "type": "product docs", "summary": "xAI's overview of the Grok assistant and its features. It describes the product rather than teaching skills, so it is mainly useful when you want to try the same task in Grok as in other assistants.\n", "teaches": [], "concepts": [ "con-model-choice" ], "audience": "nontechnical", "language": "en", "access": { "cost": "free tier; SuperGrok is paid", "login": "required", "checked": "2026-10-16" }, "accessibility": "unknown", "source_updated": "unknown", "rights": { "licence": "all rights reserved", "use": "link-and-summarise" }, "freshness": { "method": "llms-txt", "signal": "docs.x.ai llms.txt", "bot_checkable": false }, "notes": "Feature overview only, no teaching content. xAI terms page not fetchable; confirm terms.", "origin": { "kind": "ai-proposed", "by": "seed agent 2026-10-16", "rationale": "Covers the sixth provider so learners can compare assistants." }, "page": "/catalogue/#res-xai-grok-overview" } ] }