System prompt: a role it can execute

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: Writing a support agent's system prompt and afraid of over-promising.

[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:
   - the scope of issues
   - what it must never promise
   - tools available
   - escalation conditions
3. Say how you plan to do it (at most 5 steps) and wait for my go-ahead.

[Go through each of these]
- start with 'you are / you are not', in checkable sentences
- list prohibitions with a counter-example each
- state preconditions and effects of tool calls
- fix the output format and the fallback line for uncertainty

[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