Intern

You are not expected to memorize the monorepo. Your first job is to build a dependable map and make one outcome measurably better.

Four things to remember

Name	Meaning
Experience	What the work means and what robots have done
Worlds	Where behavior is generated and evaluated before physical deployment
Autonomy	How governed experience becomes an ability to act
Fleet	How exact applications run on robots under supervision

The task contract connects all four. Tests, receipts, and evidence tell you whether a change is real.

Your first-PR golden path

Write the outcome in one sentence

Good: “A missing task digest produces a clear refusal.” Avoid starting with “edit file X.”

Ask an agent for a map

Have it read the root and member guidance, then cite the entry point, canonical types, effect, and focused tests. Ask it not to edit yet.

Read the small path yourself

Open the cited files. Explain what goes in, what comes out, and what can fail before changing anything.

Make one complete change

Update the implementation, test, example, and documentation that describe the same behavior. Do not add a second representation or compatibility shim.

Prove it

Run the focused test, read the failure output, then run the broadest relevant repository gate.

Hand off clearly

Lead with the outcome. List the evidence, remaining risk, and the next safe step.

Copy this prompt

Help me understand and implement <issue>. Read CLAUDE.md, docs/DESIGN-POLICY.md,
and the affected member guidance. First explain the real request-to-effect path with file
citations and the focused test. Then make the smallest complete change, preserving safety,
lineage, and typed failures. Run focused checks and show me how the evidence proves the outcome.
Do not touch unrelated changes.

Stop and ask when

an action could delete or rewrite raw robot data;
a test would train on or relax held-out evaluation data;
a change affects physical motion, safe-stop, control authority, or deployment promotion;
the requested fix needs a new public contract or changes persisted wire values;
the repository and the issue disagree about what should be true.

A strong intern contribution is small enough to explain, complete enough to trust, and backed by evidence another engineer can reproduce.