Vercel AI SDK Telemetry

Snippet

Start with one structured event

Add this shape where the workflow completes, fails, or retries. Then build the dashboard from real fields.

vercel-ai-sdk

Vercel AI SDK Telemetry event

javascript

await telemetry.log("llm_request_completed", {
  provider: "openai",
  model: "gpt-4.1-mini",
  feature: "draft_reply",
  input_tokens: 924,
  output_tokens: 218,
  latency_ms: 1380,
  status: "success",
});

Templates to pair with this integration

AI Agent Observability Template

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

Open template

Background Job Failure Monitor

Capture queue, cron, import, billing sync, and webhook job health from the first run through retries and failures.

Open template

API Error And Latency Monitor

Watch request volume, status codes, route latency, failed endpoints, and customer-impacting API incidents.

Open template

More integrations

OpenAI Agent Telemetry

Log OpenAI agent runs, tool calls, model usage, latency, cost, and final outcomes with structured events.

Open guide

Inngest And Trigger.dev Job Telemetry

Instrument async workers, scheduled jobs, retries, failures, and dead-letter events with SQL-ready logs.

Open guide

Stripe Webhook Telemetry

Debug payment, subscription, invoice, retry, and downstream billing sync behavior without storing webhook bodies.

Open guide