Batch: a thousand items at once

Your first line in any agent design is what the agent must not do. Most failures come from unclear scope, sloppy tool contracts and missing failure handling, not from a weak model.

Task: Running the same task over a thousand records one by one is too slow.

[Before you start, do three things]
1. Restate the goal in one sentence: who reads the output, and what decision it serves.
2. If I have not given you the following, ask me. Do not assume:
   - average time and cost per item
   - failure rate
   - where results are stored
   - ordering required
3. Say how you plan to do it (at most 5 steps) and wait for my go-ahead.

[Go through each of these]
- run twenty first, measure failure rate and quality
- design concurrency and throttling
- record per-item state and support resume
- separate failed items so only they are retried

[Process]
1. Write the boundary: what it may do, must never do, and when to hand back to a human
2. Define each tool's inputs, outputs, failure semantics, idempotency
3. Write the flow as a state machine with exit conditions
4. Design failure paths: retry, degrade, abort, escalate
5. Give one testable success criterion

[Output]
Fixed shape: boundary, tool contracts, state machine, failure paths, criteria.

[Do not]
- No general-purpose agent that does everything
- Never let fuzzy prose stand in for a tool contract
- The agent must not decide whether approval is needed
- No 'do your best' instead of an abort condition