Skip to content

Learn · Track

Testing and shipping agents

How to tell whether an agent works, and whether it still works after you change a prompt, a model or a tool. You should know what an agent is; some experience with automated tests helps.

Guides in this track

Intermediate4 guides, in reading order

  1. Agent evals

    What an agent eval is: tasks, trials, graders and transcripts, capability vs regression evals, pass@k vs pass^k, and how to write your first 20 cases.

    8 min read

  2. Regression testing agents

    Catch a prompt, model or tool change that breaks your agent before users do: save known-good runs, replay changes against recordings, gate CI.

    8 min read

  3. Testing MCP tools

    Why live MCP calls make agent tests flaky, and what recorded replays, schema-built mocks and breaking-change checks each catch and miss.

    9 min read

  4. Release gates

    A release gate lets a workflow version reach production only after its tests pass on that exact version. How gates, drafts, overrides and rollback work.

    9 min read

Before and after this track

  • CI for AI agents

    The step-by-step docs guide: run recorded tests in your pipeline and fail the build on a regression.

This website (not the L2M product) uses Google Analytics, only after you accept cookies. Cookie settings