> ## Documentation Index
> Fetch the complete documentation index at: https://docs.latitude.so/llms.txt
> Use this file to discover all available pages before exploring further.

# Eve

> Connect your Eve-powered agent to Latitude for observability.

## Overview

This guide shows you how to send traces from an agent built with **[Eve](https://eve.dev)** to Latitude.

Eve is built on the **Vercel AI SDK** and exports standard OpenTelemetry spans (`ai.streamText`, `ai.toolCall`, …) through whatever exporter you register in `agent/instrumentation.ts`. Because Latitude already understands Vercel AI SDK spans, you can point Eve's OTel exporter straight at Latitude's OTLP endpoint — no Latitude SDK required.

<Check>
  You'll keep building with Eve exactly as you do today. The exporter simply
  sends your traces to Latitude alongside any other observability backend.
</Check>

<Note>
  The Eve integration is **TypeScript only**.
</Note>

***

## Requirements

* A **Latitude account** and **API key**
* A **Latitude project slug**
* An **Eve** project (with an `agent/instrumentation.ts` file)

***

## Steps

<Steps>
  <Step title="Install">
    <CodeGroup>
      ```bash npm theme={"theme":{"light":"github-light","dark":"github-dark"}}
      npm install @vercel/otel @opentelemetry/exporter-trace-otlp-http
      ```

      ```bash pnpm theme={"theme":{"light":"github-light","dark":"github-dark"}}
      pnpm add @vercel/otel @opentelemetry/exporter-trace-otlp-http
      ```

      ```bash yarn theme={"theme":{"light":"github-light","dark":"github-dark"}}
      yarn add @vercel/otel @opentelemetry/exporter-trace-otlp-http
      ```

      ```bash bun theme={"theme":{"light":"github-light","dark":"github-dark"}}
      bun add @vercel/otel @opentelemetry/exporter-trace-otlp-http
      ```
    </CodeGroup>
  </Step>

  <Step title="Point the exporter at Latitude">
    In `agent/instrumentation.ts`, register an OTLP exporter that targets Latitude's ingestion endpoint. Eve auto-discovers this file and runs it at startup, which implicitly enables telemetry.

    ```ts theme={"theme":{"light":"github-light","dark":"github-dark"}}
    import { defineInstrumentation } from "eve/instrumentation"
    import { registerOTel } from "@vercel/otel"
    import { OTLPTraceExporter } from "@opentelemetry/exporter-trace-otlp-http"

    export default defineInstrumentation({
      setup: ({ agentName }) =>
        registerOTel({
          serviceName: agentName,
          traceExporter: new OTLPTraceExporter({
            url: "https://ingest.latitude.so/v1/traces",
            headers: {
              Authorization: `Bearer ${process.env.LATITUDE_API_KEY!}`,
              "X-Latitude-Project": process.env.LATITUDE_PROJECT_SLUG!,
            },
          }),
        }),
    })
    ```

    <Note>
      Eve records full message history and model outputs on spans by default
      (`recordInputs` / `recordOutputs`). Set them to `false` for sensitive or
      regulated data.
    </Note>
  </Step>

  <Step title="Group turns into sessions (optional)">
    Eve tags every turn with `eve.session.id`, which Latitude reads automatically to group related traces into a session — no extra work needed.

    To also associate traces with an end user, return a `user.id` attribute from the `step.started` event so it lands on the spans:

    ```ts theme={"theme":{"light":"github-light","dark":"github-dark"}}
    export default defineInstrumentation({
      setup: ({ agentName }) => registerOTel({ /* … */ }),
      events: {
        "step.started"(input) {
          return {
            runtimeContext: {
              "user.id": input.channel.metadata.triggeringUserId ?? "",
            },
          }
        },
      },
    })
    ```
  </Step>
</Steps>

***

## Seeing Your Traces

Once connected, traces appear automatically in Latitude:

1. Open your **project** in the Latitude dashboard
2. Each turn shows input/output messages, model, token usage, latency, and errors
3. Eve turns, model calls, and tool executions appear as nested spans, grouped by session