Agents
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.
Also called: AI agents · agent mode · agentic AI · computer use · Cowork · operator
Connections
Understand first
Ideas this one builds on.
Leads on to
Ideas that build on this one.
Related
Often used together or easily confused.
Blueprints that practise it
Resources that teach it
- Introduction to Claude Cowork (garden)
- Agents Course, Unit 0-1 (what an agent is) (garden)
- The AI Agent Glossary (garden)
- How I AI (podcast) (garden)
- How I AI workflow guides (garden)
- OpenClaw: The complete guide to building, training, and living with your personal AI agent (garden)
- Tradclaw: a household starter kit for OpenClaw (garden)
- The Agent That Saved My Brain (garden)
- ChatGPT for Knowledge Work (garden)
- How to Use Claude Code as a Second Brain (garden)
- Compound Engineering (garden)
- Compound Writing: The Ultimate Guide (garden)
- The Eight Levels of AI Adoption (garden)
- We Gave Every Employee an AI Agent. Here's What Happened. (garden)
- Securing an Always-on AI Employee (garden)
- Not all AI agents are created equal (garden)
- An AI glossary (garden)
- Everyone should be using Claude Code more (garden)
- Management as AI superpower (garden)
- An opinionated guide to which AI to use to do stuff (Summer 2026 Edition) (garden)
- On Working with Wizards (garden)
- 20 Tips to Master Claude Code in 35 Minutes (Build a Real App) (garden)
- Introducing My New AI Learning Path and Co-Pilot (garden)
- Behind the Craft (YouTube channel) (garden)
- Perplexity Academy (garden)
- Search vs Computer (garden)
- Grok Bot use cases (garden)
Competency
Find agents on the commons map ↗
You may know it from
- administration an executive assistant acting on your behalf You set the goal and the limits; they handle the steps and check in on anything unusual.
- construction a general contractor
In products
The same idea, under different names in different tools.
| Provider | What they call it |
|---|---|
| Anthropic | Claude Cowork; Claude Code |
| OpenAI | ChatGPT agent |
| Gemini Agent | |
| Perplexity | Perplexity Computer; Comet browser |
In plain words
A chat assistant gives one answer and waits for you. An agent keeps working toward the goal. Given a goal like “collect the prices from these five vendor sites into a comparison table”, it plans steps, opens pages, reads, fills in the table, notices a missing number and goes back for it, and then reports. It uses tools and connectors to act, and a reasoning model to decide what to do next.
With an agent, you spend less time doing the work yourself and more time directing it: stating the goal clearly, setting limits on what it may touch, approving risky steps, and checking the result. Agents can save hours on tedious multi-step work. They can also go confidently in the wrong direction for a long time, or do more than you asked.
Start with low-stakes, easy-to-check tasks, keep permissions narrow, and watch the first few runs.
Example
An office manager asks an agent to read twelve supplier invoices in a folder, list each amount and due date in a spreadsheet, and flag any over budget. She spot-checks three against the PDFs before trusting the rest.
How it connects
- Built from tools and connectors plus reasoning models.
- Working with one well is mostly steering, with a human in the loop for key decisions.
- Agents that run on a timer become automation or scheduled tasks.
Try it
Pick a boring multi-step task. Before handing it over, write the goal, one thing the agent must not do, and how you’ll check the result. Then try it in your tool’s agent mode.
Read this card as plain Markdown: /concepts/con-agents.md. Know a parallel from your own field, or a product that implements this? Add it.