{
 "id": "https://redfinchadvisory.com/lexicon/observability",
 "slug": "observability",
 "prefLabel": "Observability",
 "altLabel": [
  "Tracing",
  "AI observability",
  "LLM monitoring",
  "Agent tracing",
  "AgentOps"
 ],
 "hiddenLabel": [],
 "definition": "The tracking and recording of what an AI system does on each run: inputs, outputs, steps, tool calls, cost and errors.",
 "scopeNote": "Some tools also record a model's visible reasoning. That is often a summary, and it does not always show what drove the answer.",
 "tier": "explain",
 "group": "Connections and systems",
 "broader": [
  "https://redfinchadvisory.com/lexicon/ai-operations"
 ],
 "narrower": [],
 "related": [
  {
   "id": "https://redfinchadvisory.com/lexicon/explainability",
   "type": "confused"
  },
  {
   "id": "https://redfinchadvisory.com/lexicon/eval",
   "type": "related"
  },
  {
   "id": "https://redfinchadvisory.com/lexicon/production-monitoring",
   "type": "confused"
  },
  {
   "id": "https://redfinchadvisory.com/lexicon/stack",
   "type": "related"
  }
 ],
 "links": [
  {
   "id": "https://redfinchadvisory.com/lexicon/llm-gateway",
   "label": "logs from",
   "direction": "out"
  },
  {
   "id": "https://redfinchadvisory.com/lexicon/agent-manager",
   "label": "watches agents through",
   "direction": "in"
  }
 ],
 "modified": "2026-10-21",
 "markdown": "https://redfinchadvisory.com/lexicon/observability.md",
 "inScheme": {
  "id": "https://redfinchadvisory.com/lexicon",
  "version": "1.0",
  "currentAsOf": "2026-10-21"
 }
}