Evaluation and monitoring
LLM as a judge, logging, feedback, dashboards, ingestion pipelines.
7 lessonsquests, about 1.2 h. None is open yet: they open here as they are written. Take them in any order.
Introductory2 lessonsquests
- Offline and online evaluation
- Logging every LLM call
Intermediate5 lessonsquests
- LLM as a judge
- Comparing prompts and models
- Feedback and online judges
- Dashboards and traces for LLM apps
- Ingestion pipelines