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

# Failure Mode Clustering

> Composo groups your failing traces into named failure modes you can triage and track week to week.

<iframe className="w-full aspect-video rounded-xl" src="https://www.youtube-nocookie.com/embed/Ii0G5rmL1xA" title="Composo failure mode clustering demo" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowfullscreen />

Once your traces are failing criteria, the question stops being *which trace* and becomes *which problem*. Composo clusters failing traces by similarity and names each cluster, so you triage a handful of recurring failure modes instead of scrolling a list.

**What's in the video**

* The failure map - every failing trace placed by similarity, grouped into named modes
* How each mode is trending against the previous week, and which modes are new
* Opening a mode to read the traces behind it
* Promoting a mode into an evaluator, so the failure you just found is measured from now on

Clustering runs on the traces you already send. See [Agent Tracing](/documentation/monitoring/tracing) to start sending them, and [Tags](/documentation/monitoring/tags) to slice modes by agent, customer, or release.