Skip to main content
CodingDebuggingadvanced

Production Bug Forensic Root-Cause Analysis & 5-Whys

Optimized for Claude, Chatgpt, Gemini • Verified Prompt Template

Conduct a blameless post-mortem, trace crash telemetry, and execute a 5-Whys root cause investigation.

Compatibility & Specs

Compatible AI Models
ClaudeChatGPTGemini
Last UpdatedOct 3, 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_timeline]Incident Timeline & ImpacttextareaRequiredWhen it happened, what broke, customer impactDefault: 10:14 AM: Marketing sent email campaign to 500k users. 10:18 AM: Web dashboard latency spiked from 150ms to 24,000ms. 10:22 AM: PostgreSQL database CPU hit 100% and connection pool exhausted. 10:40 AM: Database restarted, traffic throttled.
[error_telemetry]Stack Trace & TelemetrytextareaRequiredError messages, Datadog alerts, or SQL slow query logsDefault: Postgres log: `LOG: duration: 8412.314 ms statement: SELECT * FROM user_notifications WHERE user_id = $1 ORDER BY created_at DESC;` Node.js error: `TimeoutError: ResourceRequest timed out after 10000ms at Pool.acquire`
[system_code]System Code / QuerytextareaRequiredThe code or query involved in the incidentDefault: The notification dropdown component in the web navigation bar triggers `GET /api/notifications` on every page navigation, executing `SELECT * FROM user_notifications WHERE user_id = $1 ORDER BY created_at DESC LIMIT 10`.

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_timeline]
10:14 AM: Marketing sent email campaign to 500k users. 10:18 AM: Web dashboard latency spiked from 150ms to 24,000ms. 10:22 AM: PostgreSQL database CPU hit 100% and connection pool exhausted. 10:40 AM: Database restarted, traffic throttled.
[error_telemetry]
Postgres log: `LOG: duration: 8412.314 ms statement: SELECT * FROM user_notifications WHERE user_id = $1 ORDER BY created_at DESC;` Node.js error: `TimeoutError: ResourceRequest timed out after 10000ms at Pool.acquire`
[system_code]
The notification dropdown component in the web navigation bar triggers `GET /api/notifications` on every page navigation, executing `SELECT * FROM user_notifications WHERE user_id = $1 ORDER BY created_at DESC LIMIT 10`.

Verified AI Benchmark Response

Grounded Output
### Forensic Root-Cause Analysis (RCA) #### 1. The 5-Whys Investigation 1. **Why did the API return 504 Timeouts?** Node.js backend exhausted its database connection pool waiting for queries to complete. 2. **Why was the connection pool blocked?** Each connection was tied up for 8.4 seconds executing `SELECT * FROM user_notifications`. 3. **Why did that query take 8.4 seconds?** The database performed a Sequential Table Scan across 42 million notification rows. 4. **Why was there a sequential scan?** The index on `user_notifications` only indexed `(user_id)`, forcing an in-memory Sort of hundreds of notifications per user before applying `LIMIT 10`. 5. **Why was this index gap not caught in staging?** Staging had only 1,000 rows where in-memory sorting executed in 1ms, masking the O(N log N) scaling cliff. #### 2. The Permanent Fix 1. **Database:** Add compound index `CREATE INDEX CONCURRENTLY idx_user_notifications_composite ON user_notifications (user_id, created_at DESC);` 2. **Application:** Cache user unread notification counts in Redis with a 60-second TTL instead of querying Postgres on every client page load.

Best Use Cases

Scenarios and roles where this prompt produces maximum leverage.

SREs and tech leads conducting blameless post-mortem reviews after production outages
Developers diagnosing complex performance degradations under heavy traffic spikes
Engineering managers preparing transparent root-cause reports for 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 Bug Forensic Root-Cause Analysis & 5-Whys" 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_timeline], [error_telemetry], [system_code]. 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

Pragmatic REST & GraphQL API Contract Architect

Design robust, backwards-compatible API contracts with clean error schemas, pagination, and idempotency keys.

[Copy & Paste Template]4 parameters

›You are a Principal API Architect and API Governance Director. I need to design a clean, backwards-compatible, and enterprise-grade API contract for [entity_domain] operations. API Paradigm: [api_paradigm] Primary Client Consumers: [client_consumers] Key Use Cases & Capabilities Needed: [api_use_cases] Deliver a complete production API contract specification: 1. Resource Schema / Type Definitions: Full TypeScript / GraphQL interface definitions with strict field nullability, scalar types, and descriptive field comments. 2. Endpoint / Mutation Design: Complete HTTP routes (verbs, paths, query parameters) or GraphQL queries/mutations following idiomatic naming conventions. 3. Idempotency & Concurrency Control: Exact headers (e.g. `Idempotency-Key`, `If-Match` ETag) and mechanics for safe payment/mutation retries. 4. Standardized Error Response Envelope: RFC 7807 Problem Details JSON format specifying machine-readable error codes, human messages, and field-level validation error arrays. 5. Cursor Pagination & Filtering: Efficient cursor-based pagination schema for large datasets.

claudechatgptgemini
#api-design#rest-api#graphql
Codingadvanced

Relational & NoSQL Database Schema & Indexing Audit

Audit database tables, composite indexes, foreign keys, partition strategies, and N+1 query vulnerability points.

[Copy & Paste Template]3 parameters

›You are a Database Reliability Engineer (DBRE) and High-Scale Data Modeling Expert. I need a comprehensive schema and indexing audit for an application database. Database Engine & Version: [database_engine] Proposed Schema (DDL / Prisma / Models): [schema_definition] Primary Query Access Patterns & Expected Table Growth: [access_patterns] Conduct an exhaustive Database Schema Audit: 1. Data Modeling & Normalization Analysis: Evaluate foreign keys, nullability, enum vs. lookup table usage, and column data types (e.g. `TIMESTAMPTZ` vs `TIMESTAMP`, `BIGINT` vs `INT` for primary keys). 2. Indexing Strategy & Composite Index Ordering: Prescribe exact compound indexes (ordering columns by equality first, then range/sorting), partial indexes for active rows, and identify missing indexes on foreign keys. 3. Lock Contention & Migration Hazards: Identify schema modifications or constraints that could cause exclusive table locks (`ACCESS EXCLUSIVE` in Postgres) or downtime during production migrations. 4. Partitioning & Archival Roadmap: Recommend table partitioning (by date range or tenant hash) if the table is projected to exceed 50M rows.

claudechatgptgemini
#database-schema#sql-optimization#indexing
Codingadvanced

End-to-End & Integration Test Boundary Specification

Architect integration test boundaries with ephemeral test containers, database seed strategies, and external API stubs.

[Copy & Paste Template]3 parameters

›You are a Principal Test Automation Architect and Quality Lead. I need to design a reliable, non-flaky Integration and End-to-End Test Plan for a multi-service workflow. Workflow / System Under Test: [system_workflow] External Services Involved (Database, Third-Party APIs, Queues): [services_involved] Test Execution Constraints (CI Speed, Flakiness Prevention, Database Isolation): [test_constraints] Deliver an Integration Test Strategy: 1. Test Boundary Matrix: Define what is tested with real containers (e.g. real Postgres via Testcontainers), what is mocked at the HTTP transport layer (e.g. WireMock/MSW), and what is tested in end-to-end browser tests. 2. Deterministic Database Fixture & Seeding Strategy: Protocol for seeding clean tenant data and isolating parallel test runs without database race conditions. 3. The 4 Critical Test Scenarios: Fully specified integration test cases covering Happy Path, Downstream Service Timeout, Partial Network Partition, and Webhook Retry Idempotency. 4. Flakiness Defense Protocol: Strict rules for eliminating timing-dependent sleeps (`sleep(5000)`), replacing them with deterministic polling assertions.

claudechatgptgemini
#integration-testing#e2e#testcontainers

Related Engineering Guides

Deep-dive playbooks and system prompt methodologies for Coding

View all guides