Real-World RAG Incidents: Lessons from a Production Rollout
KU
Kiril urbonas
2 months ago • 2 min read•Updated 2 weeks ago•3 views
More from AI
Explore more articles in this category
Self-Hosted LLMs vs OpenAI API: A Cost-vs-Latency Analysis After 6 Months
We ran the same workload on both for half a year. The break-even point isn't where most blog posts say it is — and the latency story has more nuance than throughput-per-dollar charts admit.
7 min read
Embedding Quality in RAG: How We Cut Hallucinations by 60%
Six months running RAG in production taught us that the retrieval step matters far more than the model. Concrete techniques that moved the needle, with before/after numbers.
4 min read
Prompt Engineering Patterns That Actually Work in Production
Battle-tested prompt patterns from running LLM features in production: structured output, chain-of-thought, and graceful failure handling.
3 min read
