Telemetry
Copy-paste instrumentation template

AI Agent Observability Template

Track agent runs, tool calls, retries, model latency, errors, and accepted outcomes with structured SQL-ready events.

Questions this unlocks
  • Which tools fail most often?
  • Which agent workflows are slow or expensive?
  • Which outputs are accepted, retried, copied, or discarded?

Template

Paste this into your coding agent

Replace YOUR_API_KEY, run the flow locally, then verify the generated events and dashboards.

ai-agent-observability

AI Agent Observability Template

text
Add Telemetry to this AI agent workflow.

Use /skill.md and this Telemetry API key: YOUR_API_KEY

Log:
1. agent_run_started with agent_name, route, user_id, team_id, model, provider, and input_category.
2. agent_tool_called with tool_name, status, latency_ms, retry_count, and error_type.
3. agent_run_completed with status, duration_ms, total_tokens, estimated_cost_usd, output_category, and accepted when available.
4. agent_run_failed with error_type, failed_step, retry_count, and duration_ms.

Create SQL queries for run volume, failure rate by tool, p95 duration, model cost by feature, and accepted-output rate.

Do not log raw prompts, completions, secrets, auth headers, or personal data unless explicitly approved.

Events to capture

agent_run_startedagent_tool_calledagent_run_completedagent_run_failedai_output_accepted

More templates