Build the agent's control loop.

Before you start

Use functions, objects, conditions, and explicit success checks from phase 1.

Each lesson follows the same rhythm: understand three small ideas, edit and run the code, then explain the result. Take one lesson at a time.

In your browser, JavaScript and local tools really execute against inspectable inputs. Model decisions and classroom records are authored examples. The optional SDK project runs separately on your computer with its own setup.

Your lesson sequence

1. 1Learn → build → reflectA tool needs a clear contractDefine a tool's purpose, argument schema, returned fields, and permitted effects.
2. 2Learn → build → reflectDecide → act → observeDispatch an allowed tool request, feed its result back, and finish within a turn limit.
3. 3Learn → build → reflectWhat should the agent remember?Separate current task state, an interaction's history, and deliberately retained memory.
4. 4Learn → build → reflectReturn something another program can useParse and validate a result, preserve its evidence fields, and handle an error without inventing success.

CONNECT THE FOUR LESSONS

Your course checkpoint

Run the loop with a one-turn allowance, then inspect a well-shaped result that names a room absent from the catalog.

• Explain why one completed read may still leave the loop unfinished.
• Point to the observation that prevents a repeated read.
• Show that passing a shape check does not establish factual support.

Use these lessons’ experiment inputs and lab notebooks to record your evidence. This is a self-review prompt; only the lesson questions and code cases contribute to the progress shown above.