Skip to main content

​
Overview

Trace Search lets you query across all traced calls in your organization — both simulated and uploaded conversations — from a single page. Instead of inspecting traces one call at a time, you can search by span name, provider, status, duration, attributes, or plain English to find patterns across your entire call history. Open Trace Search in the sidebar. Type a plain English query into the search bar and Trace Search will interpret it into structured filters automatically. For example:
  • "slowest 10 LLM calls in the last 24 hours"
  • "errors from NormalAgentName agent in the last two weeks"
  • "TTS calls longer than 2 seconds"
The NL search supports sort keywords (slowest, fastest, newest, oldest), result limits (top 10, five slowest), and time expressions.

​
Structured Filters

You can also build precise queries using the structured filter controls: Multiple attribute filters stack with AND logic. Autocomplete suggestions are drawn from your organization’s actual trace data.

​
Results

Search results show as cards with:
  • Conversation source (Simulated or Uploaded) and timestamp
  • Overall span status with color coding
  • Total span count and root span duration
  • Provider and service metadata
  • Direct link to the full trace viewer for each result
An aggregate stats bar at the top shows the total number of matching calls and the error rate across results.

​
Transition Hotspots

The Transition Hotspots tab shows a failure matrix computed across your filtered search results. This is the same heatmap visualization available on individual runs (see Transition Hotspots), but applied across all calls matching your current search filters. Use this to identify systemic failure patterns across runs and uploaded conversations — for example, a specific state transition that consistently fails across your production traffic.