YanpengQi7/ai-reliability-copilot
Turn a production incident into a structured 9-section LLM response (severity, root cause, mitigation, postmortem). Ships with a 5-scenario regression suite + LLM-as-judge eval pipeline.
GitHub repository with 106 stars and 0 forks.
Language: TypeScript
Topics: ai-sdk, deepseek, incident-response, llm, llm-evaluation, mcp, nextjs, pgvector, postgres, prompt-engineering