Two ways to send LLM data
Atatus collects LLM traces from two kinds of producer. They work side by side, so you can use both in the same account and both feed the same LLM pages.
Most teams start with APM agents, because that is where their product’s model calls happen. To trace
the model calls your own application makes, start with Node.js or
Python. If you also want visibility into how your developers use
AI coding tools, add Coding agents.
What a trace contains
Whichever producer sends it, a trace is a tree of spans, and every span has a kind:
For the full reference, see Span kinds. For how spend is calculated,
see Cost and tokens.
Where your data goes
Both producers send traces tohttps://otel-rx.atatus.com over OTLP/HTTP, authenticated with your
Atatus license key. There is no separate collector to run.
On-premise installations use their own endpoint instead of the hosted one. Check with your Atatus
administrator for the correct address.
How projects appear in the UI
Projects are typed, and the type decides where a project shows up:- An APM service with LLM monitoring enabled appears in both the APM and LLM pages, because it has ordinary request traces as well as LLM spans.
- A coding-agent project appears on the LLM page only. It never appears under APM, because it has no web transactions to show there.
If you installed a coding agent and cannot find it, look on the LLM page rather than APM. This is
the most common reason people think the install did not work.
Next steps
Pick the path that matches what you want to monitor:- Getting started takes you from nothing to your first LLM trace.
- Node.js and Python cover tracing your own application.
- Coding agents overview covers the ten supported tools.
- Span kinds explains how to read a trace.
- Evaluators score your traces with an LLM-as-a-judge, once traces are arriving.