Agent Observability

Purpose: Make every LLM call, tool call, and agent decision observable, debuggable, and cost-attributable.

When to Use This Skill

• Standing up an LLM-powered service in any environment beyond local dev
• Investigating regressions, latency spikes, or cost spikes
• Wiring evaluation scores into traces for replay
• Building a feedback loop from production data
• Debugging multi-agent handoffs (see multi-agent-orchestration)

Three Pillars