Aulafy
ESEN
Courses
Courses/Production agents with LangGraph and n8n/Observability for local agents
Lesson

Observability for local agents

If you can't reconstruct what it thought, which tool it called, and why it failed, you don't have an agent—you have a black box with permissions. Observability turns a demo into a maintainable system.

  • Define useful traces for agents with tools and RAG.
  • Separate technical logs, decisions, and evidence.
  • Detect loops, latency, repeated errors, and lack of grounding.
TerminalCode
trace:
  request_id: "support-1042"
  user_id: "u_123"
  model: "local-qwen"
  route: "local"
  steps:
    - tool: "search_qdrant"
      latency_ms: 182
      chunks: 5
    - tool: "draft_reply"
      latency_ms: 4210
  guardrails:
    repeated_tool_calls: 0
    human_approval_required: true
  outcome: "draft_created"

What to always log

  • Model, runtime, and chosen route.
  • Tools called, arguments, and summarized result.
  • RAG chunks used and source.
  • Repeated errors and strategy changes.
  • Whether there was human approval or automatic cutoff.

Official sources

  • Langfuse observability overview
  • Langfuse tracing
  • OpenTelemetry traces
Evals, logs, and observabilityProject: inbox agent for SMBs