Skip to main content
The August 2025 PolyAI Agent Studio release focuses on performance improvements, voice configuration flexibility, and more powerful call review tools, as well as introducing OpenAI’s new model GPT-5 as an option for agents. Expand the items for details:
The Agent Studio homepage now loads faster and presents key metrics more cleanly. The displayed metrics can be customized to meet the needs of a particular project, so what you see will be unique to your deployment.homepage-optimisationWhat’s new:
  • Reduced page load time
  • Improved widget layout for better readability
  • More consistent alignment across metric cards and charts
Agent Studio now displays an AI-generated summary at the top of the Conversation Review screen.ai-call-summaryWhat’s new:
  • New AI Summary module in the Conversation Review screen
  • Generated post‑call using GPT summarization logic
This will only appear by default for projects that have signed the current DPA and support Azure AI..
Projects can now have up to 10 active voices, updated from the previous limit of 5 voices.multi-voice-limitVoice limits apply per project and can be managed from the settings page.
It is now much easier to filter calls in Conversation Review by delivery status, channel, and other metadata.enhanced-filtersWhat’s new:
  • Faster filter response time
  • Filter combinations can be applied without resetting the view
Use saved filters to make these configurations instantly reusable.
Conversation Review now displays additional call attributes and improved channel labels for quicker scanning.channel-metadataWhat’s new:
  • Clearer channel tags for Inbound, Outbound, and Agent Chat
  • Additional metadata columns available for custom table views
  • Streamlined column naming for consistency across the platform
We’ve added GPT‑5 options to Agent Studio for evaluation and feedback.gpt5-modelsWhat’s available:
  • GPT‑5 nano and GPT‑5 mini: Recommended for most Agent Studio use cases (best balance of quality/latency)
  • GPT‑5 (large): Included for testing; note it’s currently slow at 3–4 seconds or more.
  • GPT‑5 chat (router): Routes dynamically across the above models so you can experiment quickly.
Switch models from function settings or your project’s model configuration panel.
You can now test calls using a selected variant directly in the Test panel.calling-variantsWhat’s new:
  • Variant dropdown + search in Test ▸ Call
  • Calls launched with the chosen variant’s config
  • Transcripts tagged with variant_id for review and filtering
Use this to test prompts, policies, or routing logic before upgrading your deployment to production.
It’s now easier to jump from answers to exact conversations. New and more complex SQL data enquires have also been added to the Analyst.smart-analyst-updatesWhat’s new:
  • Clickable Call IDs: Any Call ID in a Smart Analyst answer opens that call’s Conversation Review in a new tab.
  • Expanded SQL range: Queries can include additional tables, such as PolyScore and Custom Metrics.
If a Start or End function has an error that prevents execution, Agent Studio now shows a warning and guidance to fix it.function-warnings
Agent Analysis now supports multiple analysis tasks per project.agent-analysis-multitaskWhat’s new:
  • Configure up to 10 analysis tasks per project. Each task can have its own prompt, categories, and color-coding.
  • A redesigned chart creation flow with filters, random call selection, and manual call selection.
  • A dedicated Batch UI Page where you can see task results, call breakdowns, filters, and categories in one view.
  • The ability to click into a call to open Conversation Review, with categorizations still editable at the call level
Use multiple tasks to mimic QA workflows, track quality across different call types, and monitor continuous improvement.