Skip to main content
CodingDebuggingadvancedFeatured

Production Incident Post-Mortem & Root-Cause Synthesizer

Optimized for Claude, Chatgpt, Gemini • Verified Prompt Template

Convert messy incident Slack logs and alerts into a blameless, rigorous post-mortem with corrective action items.

Compatibility & Specs

Compatible AI Models
ClaudeChatGPTGemini
Last UpdatedApr 1, 2026
Customizable Variables3 parameters

How to Use This Prompt

Follow this 3-step workflow to extract high-signal responses from any compatible AI model.

01

1. Tailor the Parameters

Use the interactive customizer above to substitute the bracketed placeholders with your exact context, requirements, and constraints.

02

2. Send to AI Model

Copy the prompt and paste it into Claude, ChatGPT, Gemini, or Copilot. These models follow structured multi-step constraints reliably.

03

3. Review and Iterate

Review the output against the verified benchmark below. Follow up in the conversation to stress-test edge cases or refine tone.

Prompt Variables & Parameters

Reference breakdown of every dynamic variable embedded in this prompt template.

PlaceholderParameter NameTypeStatusDescription & Guidance
[incident_severity]Incident Severity & Affected ServicetextRequiredSeverity level and impacted serviceDefault: SEV-1: Customer Payment Processing Outage
[downtime_duration]Downtime / Degradation DurationtextRequiredTotal elapsed time from first error to full resolutionDefault: 34 minutes full checkout outage; 14 minutes elevated error rates
[raw_incident_notes]Raw Incident Notes & Slack LogstextareaRequiredPaste unformatted incident notes, alerts, and chat snippetsDefault: 14:12 UTC - Automated Datadog alert: Stripe webhook consumer backlog exceeds 10,000. 14:16 UTC - On-call engineer notices Redis connection pool saturated (100% capacity). 14:22 UTC - Deploy pipeline locked by an unrelated PR merge. 14:29 UTC - Redis maxclients reached because worker pods auto-scaled from 6 to 48 without connection limits. 14:38 UTC - Hard restart of worker pods with lowered pool sizes restores processing. 14:46 UTC - Backlog cleared, error rate returns to 0.01%.

Example Output & Parameters Breakdown

Inspect verified benchmark AI responses and review how parameters, system constraints, and input variables calibrate generation.

Parameters & Variable Breakdown

3 Inputs
[incident_severity]
SEV-1: Customer Payment Processing Outage
[downtime_duration]
34 minutes full checkout outage; 14 minutes elevated error rates
[raw_incident_notes]
14:12 UTC - Automated Datadog alert: Stripe webhook consumer backlog exceeds 10,000. 14:16 UTC - On-call engineer notices Redis connection pool saturated (100% capacity). 14:22 UTC - Deploy pipeline locked by an unrelated PR merge. 14:29 UTC - Redis maxclients reached because worker pods auto-scaled from 6 to 48 without connection limits. 14:38 UTC - Hard restart of worker pods with lowered pool sizes restores processing. 14:46 UTC - Backlog cleared, error rate returns to 0.01%.

Verified AI Benchmark Response

Grounded Output
### 1. Executive Summary On October 12, 2026, from 14:12 UTC to 14:46 UTC (34 minutes full outage, 14 minutes degraded recovery), our payment processing service experienced a complete inability to ingest customer checkout webhooks. Approximately 1,420 transactions were delayed, with zero corrupted financial data. The root cause was an un-capped database connection pooling configuration that exhausted Redis maxclients when background worker pods auto-scaled eightfold during a traffic surge. ### 3. Root Cause Analysis (The 5 Whys) 1. **Why did checkout fail?** The payment worker pods threw timeout exceptions trying to acquire Redis lock connections. 2. **Why were connections unavailable?** Redis reached its hard ceiling of 10,000 concurrent client sockets. 3. **Why were there 10,000 sockets?** Horizontal Pod Autoscaler scaled workers from 6 to 48 pods, and each pod initialized a static pool of 200 persistent connections (48 x 200 = 9,600 + system connections). 4. **Why did each pod initialize 200 connections?** Connection pool sizing was hard-coded in 2024 when the cluster ran only 4 fixed pods. 5. **Why was this not caught in staging?** Staging traffic never reaches thresholds required to trigger pod autoscaling beyond the minimum replica count (Systemic flaw: lack of load-test scale parity). ### 5. Corrective Action Items - **[P0]** Implement Redis client connection pooling limits tied dynamically to pod replica counts (Owner: SRE | Due: Oct 15). - **[P1]** Add Datadog threshold alert when Redis client count exceeds 70% of maxclients (Owner: Infra | Due: Oct 16).

Best Use Cases

Scenarios and roles where this prompt produces maximum leverage.

Engineering teams drafting formal post-mortems after production service outages
SREs standardizing incident management and corrective action tracking across squads
Tech leads presenting outage post-mortems to non-technical executive stakeholders

Tips for Best Results

Techniques to elevate response fidelity

  • •Provide rich background context rather than one-sentence inputs to receive deep, non-generic responses.
  • •Engage in multi-turn conversation: use the initial output as a baseline, then ask the AI to sharpen specific sections.
  • •Prompt the model to highlight any hidden assumptions or missing trade-offs in its recommendations.

Common Mistakes to Avoid

Frequent failure modes and anti-patterns

  • •Giving minimal context and expecting nuanced, expert-level strategic output.
  • •Not validating factual references, citations, or statistical claims with verified primary sources.
  • •Skipping the customization step and pasting raw bracketed template variables into the AI chat.

Frequently Asked Questions About This Prompt

Technical guidance on model compatibility, parameter substitution, iteration techniques, and commercial usage.

Q1.Which AI models work best with the "Production Incident Post-Mortem & Root-Cause Synthesizer" prompt?

This prompt is thoroughly tested and compatible with Claude, Chatgpt, Gemini. For multi-step reasoning, architectural planning, and code refactoring, Claude 3.7/3.5 Sonnet and ChatGPT-4o provide the highest constraint adherence. For large-document synthesis, Google Gemini 2.5 Pro is also recommended.

Q2.How do I customize the parameters in this prompt template?

This template features 3 customizable parameter(s): [incident_severity], [downtime_duration], [raw_incident_notes]. Replace each bracketed placeholder with your project's specific details, constraints, or code before submitting to your AI model. You can also use our interactive workbench on this page to populate and copy the completed prompt in one click.

Q3.Can I use this prompt and its outputs for commercial projects?

Yes. All prompts published on Beautiful AI Prompt are 100% free for both personal and commercial use. You hold full ownership of all code, copy, strategies, or imagery generated by your selected AI model when running this prompt.

Q4.How does this prompt prevent AI hallucinations and ensure output accuracy?

This template enforces explicit negative constraints, few-shot parameter boundaries, and schema requirements (such as tabular comparisons or step-by-step logic). This suppresses speculative drift and forces the AI model to ground its response in your provided inputs.

Part of Curated Collections

This prompt is sequenced as part of these goal-oriented workflows

View all collections

Related AI Prompts

Complementary workflows in Coding

View all Coding prompts
Codingadvanced

Principal Code Reviewer & Architecture Auditor

Conduct rigorous architectural code reviews identifying memory leaks, race conditions, and typing holes.

[Copy & Paste Template]4 parameters

›You are a Principal Software Architect conducting an uncompromising production code review. Programming Language & Stack: [language_stack] Primary Objective: [primary_objective] Target Strictness: [strictness_level] Code to review: ``` [code_to_review] ``` Deliver your review in this structured format: 1. Executive Summary: 2-sentence verdict on production-readiness. 2. Critical Vulnerabilities & Bugs: Race conditions, unhandled exceptions, memory leaks, security flaws (OWASP), or type unsafety. 3. Architecture & Separation of Concerns: Assess coupling, cohesion, testability, and state management. 4. Complete Before & After Refactoring: Rewrite the code adhering to clean architecture, full typing, and explicit error handling. 5. Performance & Complexity Analysis: Big-O time and space delta between original and refactored versions.

claudechatgptcopilot
#code-review#clean-code#architecture
Job Interviewadvanced

Behavioral Failure & Workplace Conflict Answer Architect

Structure answers for difficult behavioral questions about interpersonal conflict, failed projects, and bad decisions.

[Copy & Paste Template]4 parameters

›You are a Veteran Executive Interview Bar-Raiser and Behavioral Assessment Director. I need to formulate a compelling, authentic, and completely de-risked answer to a high-stakes behavioral interview question. The Specific Question I am Answering: [interview_question] The Real Situation / Raw Incident: [raw_incident_details] My Role & What Went Wrong: [what_went_wrong] The Resolution & Concrete Institutional Lessons Learned: [resolution_and_learnings] Engineer an airtight STAR narrative: 1. Trap Analysis: Explain why hiring managers ask this specific question, what disqualifying red flags they are screening for (e.g. defensiveness, blaming teammates, lack of agency), and what genuine green flags look like. 2. Structured 2-Minute STAR Script: Write a word-for-word conversational answer using Situation, Task, Action, and Result with 60% of runtime dedicated to the constructive Action and permanent Result. 3. The Takeaway Pivot: A concluding sentence demonstrating how this painful failure directly altered your engineering or leadership standards permanently. 4. Follow-up Pressure Tests: Anticipate 2 aggressive probe questions an interviewer might ask to test your authenticity.

claudechatgptgemini
#behavioral-questions#conflict-resolution#failure-story
Codingintermediate

Exhaustive Edge-Case Unit & Integration Test Generator

Analyze production functions to discover subtle concurrency, boundary, and null pointer edge cases and write unit tests.

[Copy & Paste Template]3 parameters

›You are an Elite QA Architect and Test Automation Specialist. I need an exhaustive, production-grade test suite covering both the happy paths and obscure edge cases for the following code. Testing Framework / Language: [test_framework] Target Function or Service Code: [source_code] Known business requirements or constraints: [business_constraints] Deliver a comprehensive test suite: 1. Edge-Case Matrix: A table listing every identified edge condition categorized by: (A) Boundary Values (off-by-one, 0, MAX_INT), (B) Temporal/Timezone traps, (C) Null/Undefined/Type Coercion, (D) Concurrency / Idempotent retries. 2. Complete Test Suite Code: Self-contained, runnable test suite using idiomatic [test_framework] conventions with clear arrange-act-assert structure. 3. Descriptive Test Names: Follow the `describe('method') -> it('should [expected behavior] when [specific condition]')` standard. 4. Mocking & Isolation Strategy: Minimal, clean mocks for external network/database dependencies without over-mocking internal logic.

claudechatgptgemini
#unit-testing#integration-testing#edge-cases

Related Engineering Guides

Deep-dive playbooks and system prompt methodologies for Coding

View all guides