AI Support Triage Assistant
Problem
RAG-based support triage tool that helps a tier-2 support engineer diagnose tickets across four shared-infrastructure applications
Outcome
Reduced time-to-resolution from 2 hours of investigation to minutes for reviewing troubleshooting steps
- Created technical design document (problem statement, phased roadmap with exit criteria, success metrics, and risk register), then implemented hybrid semantic + keyword retrieval, confidence scoring, and a human-in-the-loop accept/reject/modify feedback loop
- Prioritized build-vs-buy and considered data-residency decisions (vanilla Python; 100% on-device inference), with Phoenix observability and SQLite audit trail for accuracy tracking
Technologies
Flask Phoenix Ollama ChromaDB