Blog
Writing about AI engineering, software quality and real-world experience.
Testing RAG Applications: A Practical Guide
A retrieval-augmented generation system has two places to fail — retrieval and generation. A layered test strategy that isolates each, from unit tests to end-to-end evaluation.
2 min readTesting · LLM Evaluation
2 min read
Testing · LLM Evaluation
Evaluating LLM Applications in Production
Offline test sets tell you whether a change is safe to ship; production signals tell you whether it keeps working. How to combine both into an evaluation practice for LLM features.
2 min readLLM Evaluation
2 min read
LLM Evaluation
Building Reliable AI Applications
Reliability in LLM-based software is an engineering property, not a model property. A practical look at the boundaries, contracts, and feedback loops that make AI features dependable.
2 min readAI Engineering · Architecture
2 min read
AI Engineering · Architecture