All articles
BLOG / TOPIC
Evaluation
You cannot safely change an AI system you cannot measure. These articles cover golden sets, retrieval and generation metrics, calibrated LLM judges and CI gates.
2 articles on this topic
Ordered from foundations to advanced, newest first within each level.
- How to Evaluate AI Agents: Beyond Final-Answer AccuracyHow to evaluate AI agents that take many steps: outcome, trajectory, tool use, policy adherence and cost, with a task-based golden set and regression checks.Advanced 10 min readLast reviewed 2026-10-11
- LLM Evaluation Fundamentals for Production SystemsHow to evaluate a production LLM system: golden sets from real traffic, retrieval and generation metrics, calibrated LLM judges, CI gates and online monitoring.Advanced 12 min readLast reviewed 2026-10-11