Get Agent Loadout
Build agentsIntermediateDocs-checked, not yet hands-on tested

See what your agent is doing

Trace, debug and evaluate an agent in production.

Starter prompt

Add Langfuse tracing to every model call and tool call in this agent. Tag traces with user id and version. Then write an eval script that replays 20 saved traces and reports regressions.

Config

env

LANGFUSE_PUBLIC_KEY=
LANGFUSE_SECRET_KEY=
LANGFUSE_HOST=

Setup steps

  1. Add keys.
  2. Instrument model and tool calls.
  3. Review failing traces weekly.

Why this works

You can't fix what you can't see; traces turn vague bug reports into concrete steps.

Watch out

Don't log personal data you don't need.

Related loadouts