Learn

1. 1
   What an agent actually isUsing agents · Level 1 · 6 min
2. 2
   Install your first server without guessingMCP servers · Level 1 · 6 min
3. 3
   What a skill is, and what it is notSkills and prompts · Level 1 · 6 min
4. 4
   Choosing an assistant without reading a benchmarkUsing agents · Level 1 · 7 min
5. 5
   What MCP is, and why it existsMCP servers · Level 1 · 8 min
6. 6
   When not to use an agentUsing agents · Level 2 · 6 min

What these tools actually are, how to brief them, and when to stop using one.

• What an agent actually isLevel 1 · 6 min · The difference between a chatbot, a tool, and an agent — and why the distinction decides what you can delegate.
• Prompts that survive contact with realityLevel 2 · 7 min · Why constraint beats encouragement, with the four-part structure behind every prompt in our library.
• Choosing an assistant without reading a benchmarkLevel 1 · 7 min · The three properties that decide which one you open daily, and why every leaderboard is the wrong input.
• Giving an agent context, in the right orderLevel 2 · 8 min · Files, docs, tools, and history — what to hand over, what to withhold, and why more context can make output worse.
• When not to use an agentLevel 2 · 6 min · The delegation test in full: reversible, verifiable, and describable. Fail any of the three and you want a script or a human.

5 of 5 lessons published.

From installing your first server to writing one, including the security model nobody explains.

• What MCP is, and why it existsLevel 1 · 8 min · The problem the protocol solves, in terms of the alternative you were probably using: custom integrations per client.
• Install your first server without guessingLevel 1 · 6 min · The config file, the three values that actually matter, and how to know it worked.
• Debugging a server that will not startLevel 2 · 7 min · A five-step order that eliminates transport, credentials, arguments, and context before you blame the model.
• Judging a server before you install itLevel 2 · 8 min · Five checks that take ten minutes and predict most of the pain: maintenance, transport, permissions, blast radius, and install path.
• Writing your first MCP serverLevel 3 · 10 min · The smallest useful server is about forty lines: two tools, a schema, and a decision about what not to expose.

5 of 5 lessons published.

Writing instructions that change behavior instead of setting a tone.

• What a skill is, and what it is notLevel 1 · 6 min · A folder with a SKILL.md the agent loads on demand — closer to a training manual than a plugin.
• Writing a skill that changes behaviorLevel 2 · 9 min · The four sections every working skill has, why the fourth one is skipped, and how to test a skill before you ship it.
• Turning a prompt you reuse into a skillLevel 2 · 7 min · The upgrade path from a copied prompt to a shared practice, and the point where a skill is the wrong tool.
• Reviewing a skill before you install itLevel 2 · 7 min · Five minutes of reading that predicts whether a skill will change behaviour or just consume context.

4 of 4 lessons published.

Cost, context, evaluation, and the guardrails that keep an agent from doing damage.

• Context and cost, measured instead of guessedLevel 2 · 8 min · Where the tokens actually go, why tool definitions are charged on every request, and the three levers that change the bill.
• How to know your agent got worseLevel 3 · 10 min · A minimal eval harness: twenty cases, a deterministic check where possible, and a rule for when to re-run it.
• Guardrails: permissions, approval, and auditLevel 3 · 9 min · What to hand an agent, what to keep behind a human, and how to reconstruct what it did afterwards.
• The last hour before launchLevel 3 · 8 min · Eight checks that catch the failures which only appear once real people and crawlers arrive.

4 of 4 lessons published.

Eight books and ongoing resources, each with the chapter where you should stop.