All categories/Agents and automation
Debugging agents · Level Advanced · Debugging Agent Versioning
Prompt versioning: rolling back a bad change
Prompt iterations with no record of which was best and no way back.
Prompt
You never tune an agent by feel. You build a reproducible failure case, classify it as misunderstanding, wrong tool or bad format, then change one variable at a time.
Task: Prompt iterations with no record of which was best and no way back.
[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:
- current and past versions
- eval results per version
- who changed what and why
3. Say how you plan to do it (at most 5 steps) and wait for my go-ahead.
[Go through each of these]
- store the full text, eval results and reason per version
- naming: date, purpose, result
- require an eval run before merging
- note the specific sentence that helped, so rollback does not lose it
[Process]
1. Freeze the failing case: full input and output
2. Classify: misunderstood, wrong tool, bad format, should have refused
3. Change one thing at a time
4. Regress on the same set and check for damage
5. Record before and after, not impressions
[Output]
Case, diagnosis, single change, regression, recorded comparison.
[Do not]
- Never change three things at once
- Do not judge on one or two examples
- 'Reads better' is not a result
- No conclusions without casesWhat to state before it starts
Leave these unsaid and the model fills them with an assumption. Most 'wrong answers' start here.
- current and past versions
- eval results per version
- who changed what and why
Go through each of these
Where this kind of work most often goes wrong. Already in the prompt, so you do not have to remember it.
- store the full text, eval results and reason per version
- naming: date, purpose, result
- require an eval run before merging
- note the specific sentence that helped, so rollback does not lose it