Real-World RAG Incidents: Lessons from a Production Rollout
KU
Kiril Urbonas
3 months ago • 2 min read•Updated last week•6 views
More from AI
Explore more articles in this category
MLOps — Model Registry vs MLflow Tracking, And When You Need Both
Tracking experiments and shipping models are different problems. The MLOps tooling assumes one solution; production splits them. The patterns we use.
7 min read
Agentic Ops — When (and When Not) to Use AI Agents for Incident Response
AI agents for incident triage sound great in demos. We've tried it in production. The patterns that earn their keep, the ones that backfire, and where humans still beat agents.
7 min read
LLM Evals That Actually Predict Production Quality
Most LLM eval suites correlate poorly with what real users experience. The eval patterns we run that move with prod metrics — and the ones that lied to us.
7 min read
