Get Started

Detectors evaluate your traces and surface problems the moment they happen. This guide walks through creating your first detector, watching the LLM-as-a-judge flag a problem, and reading the AI agent’s root cause analysis.

​

Prerequisites

You need a project with at least one incoming trace. See Tracing if you don’t have that yet.

​

Create a detector

Open your project in TraceRoot Cloud, select Detectors from the left nav, then click + New Detector.

​

Pick a starting point

The create sheet offers a handful of templates covering common failure modes — things like tool errors, hallucinations, logic mistakes, incomplete tasks, and safety issues — plus a blank slate if none of them fit. Pick whichever maps to a problem you’ve seen in production. The template fills in a prompt you can edit; save, and the detector starts running on the next incoming trace.

​

How it works

The pipeline that runs on every trace:

1. Ingest. A trace lands in the project.
2. Match. TraceRoot decides which detectors apply (default: all enabled detectors in the project).
3. Evaluate. The LLM-as-a-judge (Claude Haiku by default) reads the trace and returns identified plus a short summary.
4. Diagnose. When identified is true, the trace becomes a finding and the TraceRoot AI agent investigates: it downloads the trace, reads your production source code at the failure point, checks recent commits and PRs touching that file, and produces a root cause analysis.
5. Alert. The combined finding plus RCA is sent to your configured channels (email, Slack).

​

View findings

Open the detector to see its findings table. Each row links back to the trace that produced it; clicking the trace opens the trace viewer with a red Alert badge in the header. The Alert badge in the trace viewer opens a chat panel pre-loaded with the AI agent’s RCA session. From there you can ask follow-up questions in the same session — you’re talking to the same agent that wrote the analysis.

​

Bring Your Own Key (BYOK)

Both stages of the pipeline — the LLM-as-a-judge and the AI agent — run on a model you choose. Either can use a TraceRoot-provided system model or your own API key, configured independently per stage.

​

Next steps