Skip to main content

How do I build my own agent?

What an agent actually is, harnesses vs frameworks, tools via MCP, and the context and verification that keep it honest.

Check yourself.

One question per step. Take it cold to find where to start, or after reading to see what stuck. Nobody's grading you.

  1. In the now-settled definition, what makes a system an agent rather than a workflow?

  2. When does an agent framework beat a plain provider SDK plus a loop?

  3. How does MCP relate to the function calling that model APIs already provide?

  4. Why is "give the agent as much context as possible" bad advice?

  5. You wire your test suite into an agent's loop. Why must the tests be protected from the implementer?

  6. You're splitting a feature across parallel agents. Which work actually parallelizes well?