
LangChain · Course
Introduction to Agent Observability & Evaluations
Introduction to Agent Observability and Evaluations teaches the essentials of observability, evaluation and prompt engineering with LangSmith, so you can keep improving your agents.
Who it suits
- Developers who need visibility into how their agents behave.
- Teams that want to test changes with datasets and experiments instead of guessing.
What it covers
- Tracing: basics, types of runs, alternative ways to trace and conversational threads.
- Testing and evaluation: datasets, evaluators, experiments and analysing results, with optional pairwise and summary evaluators.
- Prompt engineering: the playground, Prompt Hub and the prompt engineering lifecycle.
- Collecting human feedback with user feedback and annotation queues.
- Production observability: filtering, online evaluation, automations, monitoring and custom dashboards.
Watch here
From LangChain’s own channel, so you can start without leaving Infrato. Nothing loads from YouTube until you press play.
LangChain · 2024
LangChain Academy New Course: Introduction to LangSmith
Common questions about Introduction to Agent Observability & Evaluations
- Is it free?
- LangChain Academy labels the course Free.
- How long is Introduction to Agent Observability and Evaluations?
- The course page lists its modules and lessons; check it for the length.
- Who runs it?
- LangChain Academy, run by the company behind LangChain, LangGraph and LangSmith.
More like this
Keep learning on Infrato
- Path: AI for software developers
- More from LangChain: all LangChain listings in the directory
- Explore all AI courses
Where this comes from
Written from LangChain’s own pages, read on 2026-10-13. Content, prices and availability change, so the provider’s page is the source. We are not affiliated with LangChain and this is not an endorsement.