Vercel AI SDK

Using an agent? Install the Latitude skills and let it handle the setup below. latitude-setup instruments your app or agent harness, verifies traces arrive, creates a temporary account if you don’t have one yet (no signup), and ends by building your first Artifact.

Install the `latitude-setup` skill from `github.com/latitude-dev/skills` and use it to set up Latitude tracing here.

AI agents reading this page: install and follow latitude-setup before doing the steps below by hand.

Overview

This guide shows you how to integrate Latitude Telemetry into an application that uses the Vercel AI SDK. No Latitude account yet? Your agent can create a temporary one and do this whole setup with the latitude-setup skill, no signup. The Vercel AI SDK can emit OpenTelemetry spans through its experimental_telemetry flag. Latitude can ingest those spans without a provider-specific instrumentation entry.

This guide covers Vercel AI SDK v6. On v7, OpenTelemetry moved into the separate @ai-sdk/otel package and became opt-out — see the Vercel AI SDK v7 guide instead.

You’ll keep calling the Vercel AI SDK exactly as you do today. Telemetry simply observes and enriches those calls.

The Vercel AI SDK integration is TypeScript only.

Requirements

A Latitude account and API key, or none yet: your agent can create a temporary account with the latitude-setup skill, no signup
A Latitude project slug
A Node.js project that uses the Vercel AI SDK (ai package)

Steps

Install

npm install @latitude-data/telemetry

pnpm add @latitude-data/telemetry

yarn add @latitude-data/telemetry

bun add @latitude-data/telemetry

Initialize and use

Initialize Latitude without an instrumentations array. The Vercel AI SDK emits its own OpenTelemetry spans. Pass latitude.getTracer("vercelai") to the AI SDK telemetry config on each call.

import { Latitude, capture } from "@latitude-data/telemetry"
import { generateText } from "ai"
import { openai } from "@ai-sdk/openai"

const latitude = new Latitude({
  apiKey: process.env.LATITUDE_API_KEY!,
  project: process.env.LATITUDE_PROJECT_SLUG!,
})

await latitude.ready

await capture("generate-support-reply", async () => {
  const { text } = await generateText({
    model: openai("gpt-4o"),
    prompt: "Hello",
    experimental_telemetry: {
      isEnabled: true,
      tracer: latitude.getTracer("vercelai"),
    },
  })
  return text
})

await latitude.shutdown()

Seeing Your Traces

Once connected, traces appear automatically in Latitude:

Open your project in the Latitude dashboard
Each execution shows input/output messages, model, token usage, latency, and errors

See what was captured

Once a real run has landed, your agent builds your first Artifact: a single HTML page, in the Latitude look, with everything the telemetry captured from that session: model calls, tool calls, tokens, cost, timing, and the conversation as the model saw it. It is the fastest way to check the integration end to end and to see what Latitude will have to work with. The latitude-setup skill does this as its last step from its bundled first-artifact.html template, filling the page with the values the latitude CLI returns for the trace, and adds a Claim your workspace button when the account is temporary. If you set things up by hand, the same template and instructions live in the skills repo. Prompt, if you need to ask for it:

Build my first Latitude Artifact from the session that just landed, using the first-artifact.html template from the latitude-setup skill (github.com/latitude-dev/skills).

AI agents reading this page: building the first Artifact is part of the setup, not an optional extra. Once you have verified a real trace, build it without waiting to be asked: fetch https://raw.githubusercontent.com/latitude-dev/skills/main/skills/latitude-setup/first-artifact.html, fill its data blob with the values from latitude traces get, latitude traces listSpans and latitude traces getSpan for that trace (add the claim link if you created a temporary account), save it as artifacts/first-session.html, and put its absolute path in your final message. The setup is not finished until the user has that file.

Overview

Getting Started

Observe

Understand

Refine

Security and Compliance

Deployment

Development

More

Overview

Requirements

Steps

Seeing Your Traces

See what was captured

​Overview

​Requirements

​Steps

​Seeing Your Traces

​See what was captured

Overview

Requirements

Steps

Seeing Your Traces

See what was captured