Topic
Agent Observability & Tracing
12 posts on agent observability & tracing — part of ai agents & automation on the n4n AI blog.
Why agent logs alone aren't enough for observability
Logs capture what happened, but agent logs vs observability shows why multi-step LLM agents fail. Use tracing, metrics, and structured events.
Token-level tracing: seeing inside agent decisions
A practical guide to token-level tracing AI agents: capture per-token usage, attribute decisions, and rebuild agent reasoning paths with real code.
Setting up alerts for AI agent failures in production
Learn how to build production alerts for AI agent failures with Prometheus, OpenTelemetry, and Slack. A hands-on tutorial for engineers running LLM agents.
OpenTelemetry for LLM agents: a practical guide
Practical OpenTelemetry LLM agents guide: trace agent runs, tool calls, token metrics, context propagation, and dodge common observability pitfalls.
Latency, cost, and errors: pillars of agent monitoring
A practical guide to agent monitoring latency cost errors: instrument traces, track spend, handle failures, and tradeoffs for production LLM systems.
How to trace tool calls across a multi-step agent run
Learn how to trace tool calls AI agent runs end to end with structured logging, correlation IDs, and OpenAI-compatible gateways for debuggability.
How to debug a failing AI agent with trace logs
Learn how to debug AI agent trace logs with practical steps: instrument spans, capture tool calls, and pinpoint failures in multi-step agent runs.
Five signals to monitor in production AI agents
Five operational signals to monitor production AI agents effectively: token latency per route, tool failure loops, context window use, cost per task, and semantic drift.
What is AI agent observability and why it matters
AI agent observability definition explained: tracing LLM prompts, tool calls, and decisions to debug and operate autonomous agents in production.
LangSmith vs Langfuse: comparing agent tracing tools
A pragmatic engineering comparison of LangSmith vs Langfuse for agent tracing: capabilities, cost, latency, ergonomics, ecosystem, and limits.
How to trace multi-agent workflows step by step
A practical guide to trace multi-agent workflows with OpenTelemetry and structured logging, from instrumenting agents to debugging cross-agent latency.
How to build an observability stack for LLM agents
A practical step-by-step guide to building an observability stack for LLM agents: trace calls, capture token usage, and monitor failures.
More topics in ai agents & automation
- Function Calling Fundamentals27
- Autonomous Coding Agents: Claude Code, Devin, Cursor15
- Model Context Protocol (MCP) Deep Dives15
- Multi-Agent Orchestration Patterns15
- Agentic RAG14
- AI Agent Cost & Latency Optimization14
- AI Agent Framework Comparison14
- AI Agent Security & Prompt Injection Defense14
- AI Agent Tool Use Design Patterns14
- AI Agents in Customer Support14
- LangGraph for Agent Workflows14
- LLM Workflow Automation: n8n, Zapier, Make14