Skip to main content
The October 2025 PolyAI Agent Studio release includes live call monitoring and expanded configuration for Webchat and API configuration. Expand the items for details:
Monitor calls as they happen in real time in Conversation Review.live-call-listeningWhat’s new:
  • In-progress calls now appear in the Conversations list with a live duration indicator.
  • Watch turns stream live as they occur, including metadata like timestamps and caller ID.
  • Access is permission-controlled. Users without PII-level access cannot view live transcripts.
  • A new tabbed view for Live, Ended, and All calls in the Conversations list.
You can now write structured logs from inside functions using conv.log, with entries visible in Conversation Review → Diagnosis.What’s new:
  • Write logs directly in functions using conv.log.info, conv.log.warning, and conv.log.error.
  • Logs are displayed inline during conversation review for external monitoring.
  • Mark entries as PII so they appear only for users with the correct permissions.
You can now run Test Sets automatically when publishing to sandbox, promoting to pre-release, or promoting to live.auto-run-test-setsWhat’s new:
  • Test Sets can now be configured to run automatically when publishing and promoting.
  • Runs trigger before deployment to Sandbox, Pre-release, or Live environments.
  • Useful for enforcing regression checks across complex, multi-variant projects.
Webchat now supports configurable disclaimer messages and consent prompts to meet legal and privacy requirements.webchat-disclaimerWhat’s new:
  • Add a custom disclaimer message above the input field.
  • Include clickable Privacy Policy and Terms & Conditions links that open in new tabs.
  • Optional “I consent” button required to start chatting.
  • Configure and edit all messages, links, and toggles from Settings → Webchat.
Smart Analyst gains performance and interpretability improvements, making analysis faster and more transparent.smart-analyst-streamingWhat’s new:
  • Normalized PolyScore for consistent scoring across projects.
  • Streaming reasoning steps: see model reasoning unfold live as it generates answers.
  • Faster processing for large projects.
  • UI enhancements for smoother session handling.
⌘I