Observability, tracing and monitoring
Comes up in: AI engineering, AI system design
This concept is being written. It gets the full five steps — explanation, predict, interview angle, practice with tests, and review cards. Here is exactly what it will cover, so you can study it elsewhere in the meantime.
What it covers
- tracing LLM calls and tool steps (OpenTelemetry GenAI conventions
- tools like Langfuse/LangSmith/Braintrust/Phoenix at awareness level)
- latency/cost dashboards
- online evals and user feedback
- drift and model updates
Words you will know
What you will practise
- add tracing to the agent from AGT.07