Evaluation and Testing

Evals replace unit tests. Golden datasets, code graders vs LLM-as-judge, regression gates, hallucination scoring. Table-stakes.

1. 1Why evals replace unit tests3 q
2. 2Building a golden dataset3 q
3. 3Code-based graders3 q
4. 4LLM-as-judge and its calibration3 q
5. 5Groundedness and hallucination scoring3 q
6. 6pass@k and statistical literacy3 q
7. 7Regression gates in CI3 q
8. 8Tracing and observability3 q