Skip to main content
The Conversation Diagnosis menu on the Conversation Review page provides deeper insights into the agent’s behavior and decision-making at each turn. Users can toggle different data layers to inspect how the agent understood the user and responded. diagnosis-menu

​
Available diagnosis views

  • Conversation variables Displays live variable values captured during the call (e.g. booking IDs, customer names, flags).
  • Flows and steps Tracks the agent’s navigation through flows and steps, showing the execution path and decisions made.
  • Function calls View the functions the agent triggered during the call, including call parameters and outcomes. conversations-function
  • LLM Request Shows the underlying large-language-model (LLM) request made by the agent for a given turn, where applicable.
  • Topic citations Highlights the knowledge base topics the agent used to generate each response. conversations-topics
  • Transcript corrections Displays where the automatic transcript was edited for clarity or accuracy.
  • Turn latency Measures how long the agent took to respond at each turn.
  • Interruptions Shows when the caller interrupted the agent or when barge-in was detected.
  • Variants Identifies which variant handled each part of the call.
  • Logs Displays function logs and any structured conv.log entries emitted during runtime.
  • Entities Lists extracted entities captured from the user, like booking numbers, account IDs, or city names. This is especially useful in transactional scenarios where the agent needs to capture structured data from free text.