Applied AI · 4 min read
Evaluate retrieval before generation: measuring a RAG system
Most RAG errors start in retrieval, not in the model. How to build an evaluation set and measure recall, MRR and faithfulness in CI.
Applied AI
Putting language models and generative AI into production: RAG, evaluation, agents and integration with real systems.
- Applied AI · 3 min read
Safe AI agents: tools, permissions and human approval
An AI agent is only as safe as the tools it can call. How to scope tools, propagate user permissions and require approval before real-world effects.