Overview
This guide shows you how to send traces from an agent built with Eve to Latitude. No Latitude account yet? Your agent can create a temporary one and do this whole setup with thelatitude-setup skill, no signup.
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.
You’ll keep building with Eve exactly as you do today. The exporter simply
sends your traces to Latitude alongside any other observability backend.
The Eve integration is TypeScript only.
Requirements
- A Latitude account and API key, or none yet: your agent can create a temporary account with the
latitude-setupskill, no signup - A Latitude project slug
- An Eve project (with an
agent/instrumentation.tsfile)
Steps
1
Install
2
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.Eve records full message history and model outputs on spans by default
(
recordInputs / recordOutputs). Set them to false for sensitive or
regulated data.3
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:Seeing Your Traces
Once connected, traces appear automatically in Latitude:- Open your project in the Latitude dashboard
- Each turn shows input/output messages, model, token usage, latency, and errors
- Eve turns, model calls, and tool executions appear as nested spans, grouped by session
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. Thelatitude-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:
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.