Evals, tracing, monitoring and guardrails for LLM apps and agents: how to measure quality, catch failures and watch costs in production.
Set up RAG evaluation with Ragas: build a small test set, match each metric to retrieval or generation, run a first score and compare two versions.
7 min read
Add Langfuse tracing to a Python LLM app, choose cloud or self-hosted, read traces and token costs, and mask personal data before it leaves your app.
7 min read
Set up LLM evaluation with promptfoo: write a YAML test suite with assertions, compare two models side by side and fail a CI build on regressions.
6 min read