Skip to content
AI Practice
Commons
Start small
Early preview Nothing here is released yet. Pages marked Garden are drafts that no person has reviewed. How review works

Commons map

Every record in the commons and the links between them. Concepts and skills are named on the diagram. Hover over or tab to any other shape to see its name, and click a shape to open its page.

Skip the map and read it as a list Check the result (Competency) Check what AI gave you against something real before you trust it or pass it on. Check the result Describe the task (Competency) Give AI the context, examples and constraints it needs to do the job well. Describe the task Frame the outcome (Competency) Decide what result you want, and what it's for, before asking AI for anything. Frame the outcome Make it repeatable (Competency) Turn something that worked once into a routine you, or others, can rely on. Make it repeatable Steer (Competency) Direct the work as it goes. Steer Use responsibly (Competency) Protect private information, know when a person has to decide, and be open about how AI was used. Use responsibly Adoption rituals over mandates (Concept) Teams start using AI through recurring shared habits, such as a weekly AI hour, hack weeks and leaders building things where others can see, more than through orders to use it. Adoption rituals over man… Agents (Concept) AI that works toward a goal over several steps on its own, choosing actions, using tools and checking its progress, rather than giving one reply and waiting. Agents AI writing tells (Concept) The recognisable habits of AI-generated text, such as stock phrases, tidy groups of three, empty enthusiasm and vague claims, that make writing feel generic and erode readers' trust. AI writing tells Allocation economy (Concept) Dan Shipper's forecast that as AI does more of the making, people will be valued less for what they know and more for how well they direct models: a clear goal, saying exactly what is wrong with a re… Allocation economy Artifacts and canvases (Concept) A workspace beside the chat where the AI creates a standalone thing you can see, edit and reuse, such as a document, chart, small web page or interactive tool. Artifacts and canvases Automation (Concept) Setting AI up to handle a repeatable job on its own, triggered by a time or an event like a new form entry, so the work happens without you starting it each time. Automation Centaurs and cyborgs (Concept) Ethan Mollick's names for two ways of working well with AI: centaurs split a job, keeping some tasks and handing others to AI, while cyborgs go back and forth with it inside a single task. Centaurs and cyborgs Clarifying questions (Concept) Asking the AI to question you about the task before it starts, so gaps in your request surface early and you make the decisions the AI would otherwise guess at. Clarifying questions Cognitive offloading (Concept) Handing mental work to a tool. Cognitive offloading Compounding loop (Concept) After each piece of AI work, writing down what you learned where the AI will read it next time, such as a line in its instructions, a saved example or a new check, so you don't catch the same mistake… Compounding loop Context engineering (Concept) Choosing and arranging everything the AI can see, such as instructions, examples, files, past messages and connected data, so it has what it needs for the task and little that distracts it. Context engineering Context window (Concept) The amount of material an AI can hold in view during one conversation. Context window Custom assistants (Concept) A version of an AI tool set up for one purpose, with its own instructions, files and sometimes tools, that you or others can open and use without setting it up again. Custom assistants Custom instructions (Concept) Standing instructions you save once, such as your role, preferred tone or formatting rules, that the AI applies to every conversation so you don't repeat yourself. Custom instructions Deep research (Concept) An AI mode that spends several minutes searching many sources, reading and cross-checking them, and returns a longer cited report on a question. Deep research Delegating to AI (Concept) Deciding whether a task is worth handing to AI, by weighing how long it takes you against how often the AI gets it right and how long asking and checking take, then handing it over with a brief like… Delegating to AI Evals (Concept) A small, reusable set of test tasks with known good answers that you run an AI setup against, so you can tell whether it works and whether a change made it better or worse. Evals Examples in prompts (Concept) Showing the AI one or more samples of what you want, such as a past email or a filled-in table, so it can match the pattern you show it. Examples in prompts Generative AI (Concept) Software that produces new text, images, audio or code in response to a request, by learning patterns from huge amounts of existing material. Generative AI Hallucination (Concept) When AI states something false or invented, such as a statistic, quote, source or policy detail, with the same confidence as something true. Hallucination Human in the loop (Concept) Designing AI work so a person reviews or approves at the points that matter, especially before anything is sent, published, paid or deleted. Human in the loop Jagged frontier (Concept) The uneven line between tasks AI does well and tasks it does badly, which often doesn't match human intuition about what is hard, so you have to test it on your own tasks. Jagged frontier Large language model (Concept) The engine behind AI chat tools: a system trained on vast amounts of text to predict what words should come next, which turns out to be enough to write, summarise, translate and reason in useful ways. Large language model Model Context Protocol (MCP) (Concept) An open standard for connecting AI tools to other software and data, so a connector built once works in every AI product that supports the standard. Model Context Protocol (M… Memory (Concept) A feature that lets an AI carry details about you and your past conversations into new ones, so it can personalise answers without you repeating yourself. Memory Model choice (Concept) Picking which AI model, or which tool, to use for a given job, based on what it is good at, how fast and costly it is, and how much is at stake. Model choice Multimodal AI (Concept) AI that can take in or produce more than text, such as photos, screenshots, PDFs, voice, audio and video, so you can show it the problem as well as describe it. Multimodal AI Onboard AI like a new hire (Concept) Setting up an AI assistant or agent the way you'd bring on a new colleague: a role and ways of working, background on the organisation, its own limited accounts, and more access only as it proves rel… Onboard AI like a new hire Privacy and data (Concept) Knowing what information is safe to share with an AI tool, how that tool stores and uses it, and which settings and account types protect you, your organisation and the people you serve. Privacy and data Productive friction (Concept) Deliberately adding a small amount of effort to working with AI, such as drafting first, predicting before the reveal or asking it to argue back, so you think the problem through before accepting an… Productive friction Projects and knowledge (Concept) A workspace where you keep the files, instructions and chats for one body of work together, so every conversation in it starts with the same background. Projects and knowledge Prompt engineering (Concept) The early practice of finding special wording, templates and tricks to coax better answers from AI. Prompt engineering Prompt injection (Concept) Anything an AI reads while working, such as an email, web page, calendar invite or document, can contain words written to look like orders. Prompt injection Prompting (Concept) Telling an AI what you want in plain words: the task, who it is for, what good looks like and any limits. Prompting Reasoning models (Concept) Models that work through a problem step by step before answering, trading speed for better results on tasks like analysis, planning, maths and multi-step decisions. Reasoning models Scheduled tasks (Concept) Asking an AI to run a prompt or job automatically at a set time or on a repeat, such as a Monday news digest or a daily inbox summary, without you starting it each time. Scheduled tasks Skills (Concept) Packaged instructions, examples and sometimes small tools for one kind of task, which the AI loads only when that task comes up, so a proven way of working can be reused and shared. Skills Smallest useful version (Concept) The simplest thing that solves part of your problem, built first and tried for real before adding anything more. Smallest useful version Solution ladder (Concept) A way to choose how to solve a problem by climbing from the simplest option (paper, a document or sheet, a prompt) toward an agent or an app, and stopping at the lowest rung that works. Solution ladder Steering (Concept) Directing AI work as it happens: setting the goal and limits, approving one step at a time, correcting course early and cutting anything it does beyond what you need. Steering Sycophancy (Concept) The tendency of AI to agree with you, praise your ideas and soften bad news, even when you're wrong, because it was trained partly on what people rate highly. Sycophancy Tools and connectors (Concept) Ways for an AI to do more than write: search the web, read your email or calendar, look in shared drives, or take actions in other apps, using access you grant. Tools and connectors Verification (Concept) Checking what AI gives you against something real, such as the source, the data, an expert or your own knowledge, before you rely on it or pass it on. Verification Vibe coding (Concept) Building working software by describing what you want in plain language and letting AI write the code, while you test, steer and decide what it should do. Vibe coding Build a style guide so AI drafts sound like you (Blueprint) A one-page style guide, built from your own writing, that you paste into an AI tool before it drafts for you, so you spend less time rewriting its drafts into your voice. Build a style guide so AI… Ask AI to find where your draft misleads (Blueprint) A draft you wrote yourself, revised by you after an AI pointed out every place it overstates, misleads or oversimplifies, with a record of which criticisms you accepted and why. Ask AI to find where your… Compare AI tools on a task you actually do (Blueprint) A choice of AI tool for one recurring task, based on a rubric you wrote before seeing any answers rather than habit, rankings or which answer sounded most confident. Compare AI tools on a tas… Write a handover brief before you give an agent a real task (Blueprint) One task handed to an AI agent with a written brief, a decision about whether it was worth handing over, and a check of the result against the "done" line you wrote in advance. Write a handover brief be… Ask AI to play devil's advocate on a team decision (Blueprint) A team decision that has been questioned before you commit to it, with a short table of the assumptions it rests on and one change or check you'll make because of them. Ask AI to play devil's ad… Hire and onboard an AI copilot for one piece of work (Blueprint) An AI project that knows your role, your goals and one live initiative well enough to ask useful questions, push back on a weak plan, and suggest a next step you can judge against your own. Hire and onboard an AI co… Let AI ask before it plans (Blueprint) A plan for a real piece of work that fits your situation on the first or second try, because the details that were in your head made it into the request. Let AI ask before it plans Teach your AI assistant your team's jargon, one confirmed term at a time (Blueprint) A short glossary of your team's internal terms that the AI found in your own notes, guessed at, and saved only after you confirmed or corrected each one, so later answers stop misreading your shortha… Teach your AI assistant y… Turn messy notes into a status draft you can check (Blueprint) A weekly status update that takes less time to write, points to the note behind every claim, and flags what is missing or contradictory instead of smoothing it over. Turn messy notes into a s… Write a one-page build plan before you ask AI to make an app (Blueprint) A one-page plan for a small app, with what it must do, what it leaves out and three milestones, that you can hand to any AI app builder so the first version matches what you meant and is easy to chec… Write a one-page build pl… practice-coach (Skill) A coach for learning to build with AI by improving real work. practice-coach /frame-the-problem (Skill) Turns a vague complaint or big goal into a specific problem, a desired change and a first thing to try. /frame-the-problem /brainstorm (Skill) Shows what's possible for a goal by generating many varied approaches, building on the person's own ideas first. /brainstorm /build-brief (Skill) Plans a small AI build before anything gets built. /build-brief /expert-council (Skill) Vets an idea, plan, draft or decision from three to five relevant perspectives, each saying what it would do and what worries it, and ends with where they agree and disagree. /expert-council /prove-it (Skill) Checks an AI result against something real before you trust it or pass it on, using the source, the actual number, or a rerun with one thing changed, and says what evidence would change the answer. /prove-it /stuck-or-pivot (Skill) For when an AI build, prompt or workflow isn't working. /stuck-or-pivot /make-it-repeatable (Skill) Turns something that worked once into something reusable (a saved prompt, template, checklist or personal skill) plus a short share-out of what was built and learned, and can draft it as a contributi… /make-it-repeatable academy-guide (Skill from the field) When you ask how to do something with Claude, points you to matching Claude Academy courses, tutorials and use cases. academy-guide discernment-nudge (Skill from the field) After a substantive answer you might act on, adds two or three short questions that help you check key facts, probe the reasoning and notice missing context, at most once per conversation. discernment-nudge skill-creator (Skill from the field) Helps you turn a way of working into your own skill, and test whether it does what you meant. skill-creator ChatPRD plugin (Cursor, Codex, ChatGPT) (Skill from the field) Seven skills for writing a requirements doc from notes or code, scoring a doc on strategy, structure, clarity and completeness, turning a doc into an interactive page, and checking that what was buil… ChatPRD plugin (Cursor, C… evals-skills (Skill from the field) For when something you built with AI runs again and again and needs real testing: reviewing failures, writing judge prompts and checking that your checks are trustworthy. evals-skills compound-engineering (plugin) (Skill from the field) About 36 skills for AI coding agents, built around a loop: plan, build, review, then write down what you learned so the next job can read it. compound-engineering (plu… draft-review-kit (Skill from the field) Review skills for a draft you have already written. draft-review-kit ec-public (consulting workflows) (Skill from the field) Four skills for everyday client work: a weekly update from material you supply, a proposal from discovery notes, email in a voice you describe, and a review of how a spreadsheet reads to someone new. ec-public (consulting wor… awesome-pm-skills (Skill from the field) 25 workflows that start from something you already have, such as a pricing page, interview notes or a rough feature idea, and turn it into a spec, a research summary or a test plan. awesome-pm-skills no-ai-slop (Skill from the field) Finds the patterns that make writing sound machine-made and suggests edits that keep your meaning and tone. no-ai-slop human-review (Skill from the field) Opens a page or document your AI made in the browser, where you edit the text directly and leave comments as you would in a shared doc. human-review fuck-cancer (patient and caregiver brief) (Skill from the field) For someone supporting a person through cancer. fuck-cancer (patient and… lenny-skills (Skill from the field) About 76 product and team skills, such as writing a requirements doc, running customer interviews, prioritising a roadmap and giving feedback, each built from methods guests described on Lenny's Podc… lenny-skills Wharton Generative AI Labs prompt library (Skill from the field) Seventeen paste-in prompts that set AI up as a coach or role-play partner that asks one question at a time, including a devil's advocate, a team after-action review, a team charter, a meeting facilit… Wharton Generative AI Lab… How AI assistance impacts the formation of coding skills (Resource) A controlled experiment in which people learned a new programming tool with or without AI help. How AI assistance impacts… AI Capabilities and Limitations (Resource) 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 wh… AI Capabilities and Limit… AI Fluency: Framework & Foundations (Resource) 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… AI Fluency: Framework & F… The AI Fluency Index (Resource) Anthropic studied about ten thousand real Claude conversations to see which good habits people show. The AI Fluency Index AI Fluency for Nonprofits (Resource) Applies the AI Fluency habits to nonprofit work such as fundraising, communications, programs and operations. AI Fluency for Nonprofits Claude 101 (Resource) A guided tour of Claude for people starting to use it at work. Claude 101 Anthropic Education Report: How university students use Claude (Resource) A look at how university students use Claude. Anthropic Education Repor… Introduction to Claude Cowork (Resource) 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. Introduction to Claude Co… Claude Help Center: Introduction to prompt design (Resource) A short help article on writing requests to Claude. Claude Help Center: Intro… Google AI Essentials (Resource) A short certificate course from Google, delivered through Coursera, for people with no AI experience. Google AI Essentials Gemini API prompt design strategies (Resource) Google's guide to designing prompts for Gemini, written for developers but readable by confident nontechnical users. Gemini API prompt design… Introduction to Generative AI (Resource) 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. Introduction to Generativ… Gemini for Workspace prompting guide (PDF) (Resource) A downloadable guide from Google Workspace on writing prompts for Gemini inside everyday office tools. Gemini for Workspace prom… Google Workspace Learning Center (Resource) Google's help hub for Workspace apps, including how-to material on using Gemini in Docs, Gmail and other tools. Google Workspace Learning… Agents Course, Unit 0-1 (what an agent is) (Resource) 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. Agents Course, Unit 0-1 (… HuggingChat (try open models) (Resource) A chat app where you can talk to many open models, either letting it pick one for you or choosing a model yourself. HuggingChat (try open mod… LLM Course, Chapter 1: Transformer models (intro) (Resource) The opening chapter of Hugging Face's free course on large language models, which explains what these models are and what they can do. LLM Course, Chapter 1: Tr… OpenAI Academy: Apply AI at Work track (Resource) A hub page collecting OpenAI Academy courses and events on using AI in everyday work, with separate groups for small businesses, nonprofits and government. OpenAI Academy: Apply AI… OpenAI Academy: AI Foundations (Resource) OpenAI's beginner course for people who use AI at work, which runs inside ChatGPT and ends with a certificate. OpenAI Academy: AI Founda… ChatGPT 101: A Guide to Your AI Super Assistant (recording) (Resource) A recorded introductory session from OpenAI Academy for people new to ChatGPT. ChatGPT 101: A Guide to Y… OpenAI Academy: Nonprofits club (Resource) An OpenAI Academy community space for nonprofit staff, with dated events and sessions. OpenAI Academy: Nonprofit… Prompt engineering best practices for ChatGPT (Resource) OpenAI's help-center article on writing better requests to ChatGPT. Prompt engineering best p… Generative AI without guardrails can harm learning (Resource) A field experiment with about a thousand high-school maths students. Generative AI without gua… Making things hard on yourself, but in a good way: Creating desirable difficulties to enhance learning (Resource) 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. Making things hard on you… Why "Get With the Program" Doesn't Work: Claire Vo on AI That Actually Sticks (Agents of Scale) (Resource) 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, lead… Why "Get With the Program… The AI Agent Glossary (Resource) A community glossary, started from a post by Claire Vo, of agent words such as agent, sandbox, context window, system prompt and MCP. The AI Agent Glossary How to Turn a One-Off AI Chat Session into a Reusable Workflow for Your Team (Resource) Taken from the How I AI episode on Kai, Stripe's internal AI assistant. How to Turn a One-Off AI… Claude Cowork 101: How to automate your workday without touching code (How I AI, with JJ Englert) (Resource) 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 simu… Claude Cowork 101: How to… How I AI (podcast) (Resource) 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. How I AI (podcast) How I AI workflow guides (Resource) 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. How I AI workflow guides How to Write a PRD: A Step-by-Step Guide for Product Managers (Resource) 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… How to Write a PRD: A Ste… How to Improve Interview Feedback Consistency with a Custom GPT (Resource) 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. How to Improve Interview… OpenClaw: The complete guide to building, training, and living with your personal AI agent (Resource) Claire Vo's guest post on setting up OpenClaw, an open-source personal agent you message through apps such as Telegram. OpenClaw: The complete gu… Claude Cowork for PMs: My Self-Improving Productivity System (How I AI, with Daniel Blum) (Resource) 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… Claude Cowork for PMs: My… Tradclaw: a household starter kit for OpenClaw (Resource) 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. Tradclaw: a household sta… The Agent That Saved My Brain (Resource) 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 dozen… The Agent That Saved My B… AI Style Guides: How to Help AI Write Like You (Resource) A step-by-step guide to writing a style guide that an AI reads before it drafts for you. AI Style Guides: How to H… The Knowledge Economy Is Over. Welcome to the Allocation Economy. (Resource) 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. The Knowledge Economy Is… ChatGPT for Knowledge Work (Resource) 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. ChatGPT for Knowledge Work How to Use Claude Code as a Second Brain (Resource) 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 drafti… How to Use Claude Code as… Compound Engineering (Resource) Every's long guide to working with AI agents so that each job leaves the next one easier. Compound Engineering Compound Writing: The Ultimate Guide (Resource) Applies the compound loop to writing: interview, outline, draft, review, finish, then save what you learned so the next piece goes faster. Compound Writing: The Ult… The Eight Levels of AI Adoption (Resource) 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 dire… The Eight Levels of AI Ad… We Gave Every Employee an AI Agent. Here's What Happened. (Resource) Every's COO and head of platform talk through giving each staff member their own agent. We Gave Every Employee an… An Executive's Guide to Implementing AI (Resource) 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,… An Executive's Guide to I… Securing an Always-on AI Employee (Resource) How Every limits the risk of an agent that runs all day with real accounts. Securing an Always-on AI… Your Brain on ChatGPT (Resource) An MIT Media Lab study that measured brain activity while people wrote essays with ChatGPT, a search engine or nothing. Your Brain on ChatGPT The Impact of Generative AI on Critical Thinking (Resource) A survey of 319 knowledge workers about when they think critically while using AI. The Impact of Generative… Not all AI agents are created equal (Resource) 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 too… Not all AI agents are cre… An AI glossary (Resource) 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. An AI glossary A guide to AI prototyping for product managers (Resource) 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 Curso… A guide to AI prototyping… Build your personal AI copilot (Resource) Tal Raviv's free guide to using an AI project as a long-term thinking partner at work. Build your personal AI co… Lenny's Data: free public starter pack (Resource) 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. Lenny's Data: free public… Beyond vibe checks: A PM's complete guide to evals (Resource) Aman Khan of Arize AI explains how to test AI output on purpose rather than by feel. Beyond vibe checks: A PM'… Everyone should be using Claude Code more (Resource) 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, dr… Everyone should be using… This week on How I AI: Claude Cowork tutorial for non-engineers + Build your own Slack inbox (for $0) (Resource) 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 abo… This week on How I AI: Cl… The non-technical PM's guide to building with Cursor (Lenny's Podcast, with Zevi Arnovitz) (Resource) Zevi Arnovitz, a product manager at Meta who doesn't write code, shows how he builds working products with Cursor and Claude. The non-technical PM's gu… How to build your PM second brain with ChatGPT (Resource) 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 (doc… How to build your PM seco… What people are vibe coding (and actually using) (Resource) 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… What people are vibe codi… A Conversation with Dr. Vivienne Ming, author of Robot-Proof (Resource) A short written Q&A from Fidelity's research centre. A Conversation with Dr. V… A top researcher says a new divide is emerging in AI use, and most people are on the losing side (Resource) A news report on Ming's forecasting experiment, in which teams predicted real events with or without AI and were compared against Polymarket. A top researcher says a n… Vivienne Ming on hybrid collective intelligence, building cyborgs, meta-uncertainty, and the unknown infinite (Resource) A long interview on the Humans + AI podcast with a full transcript. Vivienne Ming on hybrid c… In Conversation... with Vivienne Ming (Resource) A 34-minute interview from a law firm's future-of-work series, with a written transcript. In Conversation... with V… Robot-Proof: When Machines Have All the Answers, Build Better People (Resource) Vivienne Ming's 2026 book about people more than machines. Robot-Proof: When Machine… The AI That Asks Better Questions: Dr. Vivienne Ming at SIM 2025 (Resource) A write-up of Ming's 2025 keynote in Porto. The AI That Asks Better Q… 15 Times to use AI, and 5 Not to (Resource) A checklist for deciding whether a task suits AI. 15 Times to use AI, and 5… Against "Brain Damage" (Resource) Mollick pushes back on headlines claiming AI harms our brains and says the danger is thoughtless use. Against "Brain Damage" Giving your AI a Job Interview (Resource) 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 fi… Giving your AI a Job Inte… Assigning AI: Seven Approaches for Students, with Prompts (Resource) 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. Assigning AI: Seven Appro… Centaurs and Cyborgs on the Jagged Frontier (Resource) Mollick's plain-language account of a 2023 experiment with 758 Boston Consulting Group consultants. Centaurs and Cyborgs on t… Choosing to Stay Human (Resource) Ethan Mollick argues that the risk lies in using AI on autopilot, and pulls together studies showing that skipping effort means skipping learning. Choosing to Stay Human Co-Intelligence: Living and Working with AI (Resource) Mollick's 2024 book for general readers on working alongside AI as a coworker, tutor, coach and creative partner. Co-Intelligence: Living a… The Cybernetic Teammate (Resource) Reports a randomised trial with 776 Procter & Gamble professionals working on real product development tasks. The Cybernetic Teammate Wharton Generative AI Labs Prompt Library (Resource) 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. Wharton Generative AI Lab… Getting started with AI: Good enough prompting (Resource) A short starter guide for people who feel they need to learn prompt engineering first. Getting started with AI:… Instructors as Innovators: A future-focused approach to new AI learning opportunities, with prompts (Resource) 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. Instructors as Innovators… Making AI Work: Leadership, Lab, and Crowd (Resource) A plan for bringing AI into an organisation through three groups. Making AI Work: Leadershi… Management as AI superpower (Resource) Argues that working with AI agents mostly uses ordinary management skills: delegating, giving clear instructions and judging the work. Management as AI superpow… An opinionated guide to which AI to use to do stuff (Summer 2026 Edition) (Resource) Mollick's mid-2026 buyer's guide for people who aren't developers. An opinionated guide to w… On Working with Wizards (Resource) 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. On Working with Wizards 12 Rules to Vibe Code Without Frustration (Resource) Peter Yang's tips from more than 50 hours of building apps with AI as someone who doesn't code. 12 Rules to Vibe Code Wit… 20 Tips to Master Claude Code in 35 Minutes (Build a Real App) (Resource) A product manager's tour of Claude Code while building an app. 20 Tips to Master Claude… Introducing My New AI Learning Path and Co-Pilot (Resource) 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. Introducing My New AI Lea… Behind the Craft — Transcripts (Resource) 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. Behind the Craft — Transc… Behind the Craft (YouTube channel) (Resource) Peter Yang's channel of practical AI tutorials and interviews with people who build AI products. Behind the Craft (YouTube… ChatGPT vs Claude vs Gemini: The Best AI Model for Each Use Case in 2025 (Resource) 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. ChatGPT vs Claude vs Gemi… Use My /Human-Review Skill to Edit HTML and Markdown Files Visually (Resource) 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 i… Use My /Human-Review Skil… n8n Tutorial: Build an AI Workflow to Extract Top Insights From All Your Newsletter Emails (Resource) 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. n8n Tutorial: Build an AI… Build Beautiful Slides with Claude Code in 12 Minutes (12 Formats + 3 Templates) (Resource) 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… Build Beautiful Slides wi… How to be more ambitious: A tutorial for humans with models (Resource) A practical essay on asking more of AI. How to be more ambitious:… AI Should Challenge, Not Obey (Resource) Advait Sarkar argues that AI should sometimes act as a provocateur, offering counterarguments, critiques and questions instead of finishing your work for you. AI Should Challenge, Not… Perplexity Academy (Resource) A library of short video lessons, a few minutes each, on using Perplexity's search and its Computer feature for multi-step work. Perplexity Academy Perplexity at Work Guide (Resource) A downloadable guide on using Perplexity in daily work, organised around cutting distractions, extending what you can research and write, and reaching concrete outcomes. Perplexity at Work Guide Evaluating AI for high-stakes work (Resource) A guide for teams in finance, legal and research who must check AI work before it shapes a decision. Evaluating AI for high-st… Search vs Computer (Resource) 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. Search vs Computer Grok Bot use cases (Resource) 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. Grok Bot use cases Welcome to Grok (consumer docs) (Resource) xAI's overview of the Grok assistant and its features. Welcome to Grok (consumer…
How to read the lines
  • Idea links: builds on (arrow), evolved from (arrow), related, parallels (dashed).
  • Practice links: what a skill or project practises or uses, and which skill to try next.
  • Source links: which resources teach or explain what.

The same graph as data: /graph.json. Links shown dashed on concept pages as “not written yet” aren't on the map until someone writes that card.

The map as a list

The same records and connections, readable without the picture.

Concepts (44)
Skills (8)
Blueprints (10)
Competencies (6)
Resources (97)
Skills from the field (14)