Telemetry
For teams asking Claude Code to modify production apps

Claude Code Observability

Give Claude Code a prompt that makes telemetry part of the implementation pass instead of a separate cleanup project.

Reviewed by the Telemetry product team on . Event contract, recommended analysis, and privacy boundaries. Review standards and ownership

Run a sample agent queryCopy the prompt
Why this works
  • Structured logs generated from the same context as the code change.
  • Dashboards and SQL queries that humans can inspect after the agent is done.
  • Redaction-first guidance so prompts, secrets, and raw payloads stay out of event data.
Use-case evidence path

Claude Code Observability: from implementation to decision

A complete claude code observability measurement loop connects one owned workflow, a bounded event contract, a controlled fixture, and a question someone can act on.

  1. 1

    Set the boundary

    Create a Telemetry account and API key.

  2. 2

    Capture the outcome

    Begin with agent_task_started, agent_task_completed, feature_used and document the grain of each event.

  3. 3

    Prove the rows

    Review the resulting tables, charts, and alerts before shipping.

  4. 4

    Make the decision

    Which agent-authored features are actually used after release?

Agent prompt

Paste this into your coding agent

Replace YOUR_API_KEY after signup, then ask the agent to run the product flow and verify the first events.

agent prompt

Claude Code Observability setup prompt

text
Instrument this project with structured logs using /skill.md.

Use this Telemetry API key: YOUR_API_KEY

Please:
1. Find the most important user-facing flows, background jobs, and AI/tooling workflows.
2. Add structured logging with pragmatic snake_case tables and fields.
3. Capture the key signals for each workflow, including status, latency, identifiers, and error context when relevant.
4. Send test events to Telemetry and verify that ingestion works.
5. Create a high-level dashboard with charts and tables that summarize the most important signals in this project.
6. Tell me what you instrumented, which tables you created, and which dashboard views I should review first.

Prefer small, composable events over giant payloads, and optimize for dashboards that humans can scan quickly.

Setup steps

  1. 1Create a Telemetry account and API key.
  2. 2Paste the prompt into Claude Code at the start of a feature or observability pass.
  3. 3Ask Claude Code to run the app flow, send test events, and create a dashboard.
  4. 4Review the resulting tables, charts, and alerts before shipping.

Events to capture

agent_task_startedagent_task_completedfeature_usedapi_request_completedcheckout_completedbackground_job_failed

Questions unlocked

  • Which agent-authored features are actually used after release?
  • Where are Claude Code changes creating support or reliability risk?
  • Which workflows should get alerts before more automation is added?

Event schema starting points

Event contracts for this workflow

Review the row grain, emit boundary, required types, privacy classes, example payload, and validation checklist before adapting a query or snippet to production.

Product lifecycle7 fields

user_signed_up

One accepted signup per user and account.

Inspect contract
Product analytics8 fields

product_milestone_completed

One completed milestone per actor, account, and occurrence.

Inspect contract
AI agent operations10 fields

ai_agent_run_completed

One terminal outcome per logical agent run.

Inspect contract

Related product capability

Continue this workflow in Dashboards

Turn a validated product or revenue query into a focused decision surface.

Explore DashboardsReview customer evidence

Related SQL recipes

Answer the next question with SQL

Run the query against the structured fields from this workflow, inspect the example result, and turn a useful answer into a dashboard or alert.

Browse all recipes
API reliabilityBeginner

Calculate API Error Rate by Route

Which API routes have the highest meaningful 5xx error rate?

Open recipe
Background jobsBeginner

Measure Background Job Retry and Failure Rate

Which background jobs consume the most retries or still fail?

Open recipe
Product analyticsIntermediate

Build a Signup-to-Activation Funnel in SQL

Where do new users leave before reaching first value?

Open recipe
Complete collectionsAPI reliability SQLBackground jobs SQLProduct analytics SQL

Next step

Create the API key your agent will use

The free plan is enough to run the prompt, send test events, and review the first dashboard.

Prompt packRun a sample agent query

Related pages

AI Agent Telemetry and Observability

Instrument AI agent telemetry for runs, tool calls, retries, latency, model cost, failures, and accepted outcomes in SQL-ready event tables.

Open page

Cursor Telemetry Setup

A copyable setup prompt for adding event tables, funnel tracking, and dashboards from inside Cursor.

Open page

Codex Instrumentation Prompt

A focused prompt that asks Codex to instrument the rest of the product, verify events, and summarize coverage gaps.

Open page