APromptAura
0

Blameless incident postmortem writer from raw timeline notes

auto-checked, 2 hours old
AauraNovice

The prompt

0 copies
Turn my raw incident notes into a blameless postmortem document. Structure: 1. Summary (3 sentences: what broke, user impact, duration). 2. Timeline (bulleted, timestamped, factual only, no speculation about intent or blame, use 'the deploy introduced X' not 'engineer Y broke X'). 3. Root cause (the actual mechanism, not just 'human error', trace it to the systemic gap: missing test, missing alert, missing review step). 4. Contributing factors, separate from root cause (things that made detection or recovery slower than it should have been). 5. What went well (detection speed, a runbook that worked, etc.) - do not skip this section. 6. Action items as a table: Action, Owner (leave blank if unknown), Priority, Prevents-recurrence-of (link back to which factor it addresses). Every root cause and contributing factor must have at least one action item addressing it. 7. Do not use any person's name in a way that reads as blame; describe actions taken by roles or systems. Raw notes: raw_notes Services involved: services User impact data: impact_data

Run it in your model, then come back and report whether it worked, including the model and version.

Where it has been run

People and our automated sweep are counted separately. Only the People column is someone vouching for this prompt.

ModelVersionPeopleBrokeAutoLast
ClaudeHaiku 4.5001/12 hours ago

Example output

Summary: A configuration change to the payment gateway's timeout value caused 8% of checkout requests to fail for 47 minutes, affecting an estimated 2,300 customers. Root cause: The timeout was lowered as part of an unrelated config cleanup; there was no staging environment that replicated production-scale payment gateway latency, so the regression was invisible until production load. Contributing factor: The alert for elevated checkout error rate has a 15-minute evaluation window, which delayed detection by roughly 12 minutes past when the error rate actually crossed threshold. What went well: On-call correctly identified the recent config deploy as the likely cause within 5 minutes of paging, using the deploy-timeline dashboard. | Action | Owner | Priority | Prevents | |---|---|---|---| | Add production-scale load replay to staging for gateway configs | (unassigned) | P1 | Root cause | | Reduce checkout error-rate alert window to 5 minutes | (unassigned) | P2 | Contributing factor |

0 comments

Sign in to comment or report what this prompt did for you.

Sign in

No comments yet. Run the prompt and report what you got.