- Testing AI agents before release: trajectory assertions, recorded tool replays and pass-rate gates in CIAI & GenAI · 9 Nov 2026
- RAG keeps answering from outdated documents: metadata filters, time decay and supersessionAI & GenAI · 7 Nov 2026
- Measure RAG retrieval properly: recall@k, MRR and a golden set that catches regressionsAI & GenAI · 6 Nov 2026
- RAG citations point to the wrong document or page: fix chunk IDs, metadata and citation checkingAI & GenAI · 3 Nov 2026
- Advanced RAG retrieval: query rewriting, multi-query, HyDE and question decomposition, measuredAI & GenAI · 29 Oct 2026
- Same prompt, different answer at temperature 0: where LLM non-determinism comes from and how to live with itAI & GenAI · 28 Oct 2026
- Advisory: an evaluation strategy for GenAI applications - offline test sets, online signals and human reviewAI & GenAI · 25 Oct 2026
- Advisory: choosing an LLM for a use case - hosted or open-weight, model size, and selecting by evaluationAI & GenAI · 25 Oct 2026
- Optimization: model routing and cascades - send each request to the smallest model that does it wellAI & GenAI · 25 Oct 2026
- Optimization: running LLM evaluations without a huge bill - tiered suites, smaller judges, caching and batchAI & GenAI · 25 Oct 2026
- Sev1: RAG answers got much worse after a re-index. Finding what changed and rolling backAI & GenAI · 25 Oct 2026
- Transformation: extending an existing MLOps platform to support LLM applicationsAI & GenAI · 25 Oct 2026
- Evaluating LLM answers with LLM-as-a-judge: a practical setupAI & GenAI · 22 Oct 2026
- LLMOps foundation: prompt versioning, evaluation gates and safe releasesAI & GenAI · 22 Oct 2026
- RAG answers are incomplete or off-topic: tune chunk size and overlapAI & GenAI · 22 Oct 2026
- Your support chatbot is making things up: diagnosing and reducing hallucinationsAI & GenAI · 22 Oct 2026
- Running a RAG pipeline in production: an operations checklistAI & GenAI · 10 Oct 2026