Convert a vague failure into hypotheses, checks, and next actions.
Use this when the symptom is known but the cause is still blurry. It keeps the investigation from turning into random changes.
Include the exact error, recent changes, environment details, reproduction steps, and what has already been ruled out.
A compact version for quick reuse.
Help me debug this systematically.
Start by restating the symptom and likely blast radius. Generate ranked hypotheses, the evidence for or against each one, and the fastest checks to narrow the cause. Avoid proposing code changes until we have a clear diagnosis.
A fuller version with stronger constraints and output expectations.
Act as a careful debugging partner.
Issue:
[describe the symptom, exact error, affected users or systems, recent changes, environment, and reproduction steps]
What I have already checked:
[list checks, logs, attempts, and results]
Please help me triage this by producing:
- A concise restatement of the symptom.
- The likely blast radius and urgency.
- Ranked hypotheses from most likely to least likely.
- Evidence that supports or weakens each hypothesis.
- The fastest next checks, ordered by information value.
- What not to change yet.
- The smallest safe fix once the cause is confirmed.
- Tests or monitoring needed to prevent recurrence.
Ask only for missing information that would materially change the next step.