←Applied AI Engineering

Chapter 14 of 17 · Level 8 · Evaluation

Evaluating Agents & LLMs

Why there is rarely one right answer, eval harnesses, benchmarks, and LLM-as-judge.

14.1
An Agent You Cannot Measure Is an Agent You Cannot Improve
Measuring agents is the skill that separates a demo from a product. It looked fine when I tried it is not measurement, and this is how you replace that feeling with numbers you can trust.
7 min read
→