Skip to main content

Review calls and runs

Trace a conversation from runtime inputs to the final outcome and downstream delivery.
2 min read

Start with one run#

Open the agent's run history and select a call by time, destination, or run ID. Confirm the workflow, definition ID, call mode, and direction before investigating the transcript. A run from an editor test may use different context and a different definition from a production call.

Inspect the evidence#

SurfaceWhat to check
TranscriptWhat the caller actually said and what the agent promised
RecordingRecognition mistakes, interruptions, silence, and audio quality when a recording exists
Node transitionsWhether the conversation followed the intended pathways
ToolsSelected function, arguments, response, failure handling, and external outcome
initial_contextValues supplied before the conversation
gathered_contextExtracted outputs and call disposition
QA annotationsResults produced by configured QA analysis
Usage and costComponents reported for this run and any unavailable data

Separate call state from business outcome#

A completed call can still fail its business purpose. Compare call_status, raw call_disposition, and mapped_call_disposition with the transcript and external system. See call dispositions for the data contract.

Share artifacts carefully#

Recording and transcript download links can carry access through a signed token. Share them only with the people who need the content. Availability depends on the run, storage, and deployment configuration; a missing artifact is not evidence that a call never happened.

Turn findings into a tested edit#

Classify the failure: prompt, pathway, context, tool, model, telephony, or infrastructure. Fix the smallest responsible part, replay a relevant scenario, run a Web Call if speech changed, and publish after review.