> ## Documentation Index
> Fetch the complete documentation index at: https://polyai-mintlify-41fdf97b.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# Release notes overview
> Monthly summaries of PolyAI Agent Studio releases, from the latest PolyScore and Guardrails updates back through historical platform changes.
PolyAI releases monthly Studio updates.
Explore the update cards for release summaries:
Click the **bolded** titles for a breakdown of what's new, or go to the [notes tab](./notes/26.08) for full details.
* **[New PolyScore](./notes/26.08#new-polyscore)**: Released 5 August. PolyScore moved from a 0–10 scale to a **1–5 scale**, backed by a rubric that natively scores voice, messaging, and email (inbound and outbound). Two dimensions — **Agent quality** and **Task success** — combine into the overall score, with explicit rules for handoffs, self-service paths, and design-driven declines. See [PolyScore](/analytics/polyscore).
Click the **bolded** titles for a breakdown of what's new, or go to the [notes tab](./notes/26.07) for full details.
* **[PolyAI ADK](./notes/26.07#adk)**: A local, Git-like workflow for Agent Studio projects — pull, edit with standard tooling, validate, and push. Install with `pip install polyai-adk` and see the [ADK docs](/adk).
* **[Builder MCP](./notes/26.07#builder-mcp)**: Point an MCP client — Claude Code, Cursor, Claude Desktop, or Codex — at PolyAI's authenticated MCP server to build, test, and deploy agents from your IDE. See the [MCP overview](/mcp/overview).
**New Agent Studio layout.** On 24 June we're rolling out a cleaner Studio sidebar that consolidates 25+ pages into 15 grouped sections. No functionality changes — agents behave exactly as before.
See **[Meet the new Agent Studio](/get-started/whats-new)** for the full migration guide, including a section-by-section "was → now" map and a list of features that have moved.
Highlights:
* **Wren** is the new homepage — our prompt-based tool for building agents in natural language.
* **Analytics** consolidates KPIs, custom metrics, dashboards, Conversations, PolyScore, and CSAT. The standalone **Agent Analysis** page is sunset; per-call diagnosis lives under [Conversations > Diagnosis](/analytics/conversations/diagnosis).
* **Behavior** merges Agent settings and general configuration into one section with **General**, **Language**, **Guardrails**, and **Models** subsections.
* **Knowledge** renames Managed topics → **FAQs**, Connected knowledge → **Sources**, and pulls Variants in as a tab.
* **Testing** replaces Test suite (which is being sunset). See [Testing](/testing/simulation-tests).
* **Real-time config** combines the real-time config and the configuration builder.
* **Voice** consolidates Settings, Numbers, Handoffs, Audio library, and speech/response-control tuning onto one page, with deeper options under **Advanced**.
* **Messaging** follows the same pattern for chat and SMS.
* **Integrations** becomes its own section (App, API, MCP).
* **Widgets** moves out of Messaging into a standalone section for managing widgets across channels.
The new navigation is **on by default** for all users from 24 June — a temporary **revert toggle** in your profile menu lets you switch back while you adjust.
Click the **bolded** titles for a breakdown of what's new, or go to the [notes tab](./notes/26.06) for full details.
* **[Platform Guardrails](./notes/26.06#guardrails)**: Five pre-built safety protections – jailbreak defence, scope and hallucination control, AI identity, emergency escalation, and tool call integrity – are now applied automatically to every conversation, observable in transcripts, and toggleable per project in [Behavior](/behavior/guardrails/introduction).
* **[A/B testing (Beta)](./notes/26.06#ab-testing)**: Promote a second version to Live alongside the current one with a configurable traffic split, compare real-traffic metrics in your dashboards, and pick a winner – available behind a feature flag on US and UK enterprise clusters. See [A/B testing](/testing/ab-testing).
* **[Agent Builder writes simulation tests](./notes/26.06#agent-builder-test-suite)**: [Agent Builder](/wren/introduction) can now author, run, and maintain [simulation test cases](/testing/simulation-tests) alongside the agent it's building, keeping coverage in step with your changes.
* **[Agent Builder builds chat agents](./notes/26.06#agent-builder-chat)**: Agent Builder now tailors plans and prompts to the project's channel — chat-specific guidance for chat agents, voice for voice agents.
* **[Leaner Agent Builder runtime](./notes/26.06#agent-builder-perf)**: Per-step overhead reductions keep long sessions and large projects responsive.
Click the **bolded** titles for a breakdown of what's new, or go to the [notes tab](./notes/26.05) for full details.
* **[Conversations workspace revamp](./notes/26.05#conversations-revamp)**: Voice and Web chat are now separate scopes with their own saved views, column layouts, and an integrated review side panel that opens without leaving the table.
* **[Diagnosis toggle group](./notes/26.05#diagnosis-toggle-group)**: Debugging layers (tool calls, flows, variables, latency, logs, sources) are now independent toggles that persist as you move between conversations.
* **[Tripleseat integration](./notes/26.05#tripleseat-integration)**: Connect PolyAI to Tripleseat to capture large-party and event leads from voice, webchat, and SMS – no custom code required.
Click the **bolded** titles for a breakdown of what's new, or go to the [notes tab](./notes/26.04) for full details.
* **[Multi-language support](./notes/26.04#multilingual)**: Configure a single agent to handle [multiple languages](/behavior/language/multilingual) from the UI – add languages, assign per-language voices with automatic switching, use conditional content tags, and test in any language from Agent Chat.
* **[Translations](./notes/26.04#translations)**: A new [Translations](/behavior/language/translations) page under [Advanced voice settings](/voice-channel/advanced/call-settings) lets you manage auto-translated content and manually override specific phrases.
* **[MCP integrations](./notes/26.04#mcp-integrations)**: Connect [external tool servers](/mcp/agent-studio-integrations) to your agent from **Integrations > MCP**.
Click the **bolded** titles for a breakdown of what's new, or go to the [notes tab](./notes/26.03) for full details.
* **[Sources in Conversation Review](./notes/26.03#source-hub-file-preview)**: Each turn now shows which Connected Knowledge files the agent retrieved. Click a source name to preview the document content inline, without leaving Conversation Review.
* **[Smart Analyst deep sampling](./notes/26.03#deep-sampling)**: Analyze up to 500 conversations (10× the previous limit) with random or metric-based sampling to uncover patterns and get directional insights at scale.
Click the **bolded** titles for a breakdown of what's new, or go to the [notes tab](./notes/26.02) for full details.
* **[Channels and navigation reorganization](./notes/26.02#channels-navigation-reorg)**: Agent Studio now includes a dedicated **Channels** section for Voice, Chat, and Widget configuration, alongside broader navigation updates across Build, Configure, and Deployments.
* **[Voice library](./notes/26.02#voice-library)**: Browse, preview, and select voices more easily with a redesigned voice page and expanded provider support.
* **[Latency visualization](./notes/26.02#latency-visualization)**: View detailed latency breakdowns, including LLM request and function timing, to understand and improve response performance.
* **[CSAT by voice](./notes/26.02#csat-by-voice)**: Configure in-call voice CSAT surveys with a dedicated UI and dashboard support for voice interactions.
* **[Webchat enhancements](./notes/26.02#webchat-markdown)**: Chat/Webchat is easier to configure, with a dedicated Chat configuration page, separate Widget setup, and markdown rendering in Test Agent Chat and Conversation Review.
* **[Easy telephony integrations](./notes/26.02#ccaas-integrations)**: Set up **Dialpad**, **Twilio**, and **Five9** directly from the Integrations page, then continue routing setup in Handoffs.
* **[User permissions](./notes/26.02#user-permissions)**: Assign mixed access per area (None/Read/Edit) – for example, let users edit Knowledge while keeping Functions read-only – aligned to the new navigation structure.
* **[Security and usability updates](./notes/26.02#security-usability-updates)**: Expanded sample questions, simplified conversation filtering, improved secret handling, updated permissions, and GPT-5-powered PolyScore and call summaries.
Click the **bolded** titles for a breakdown of what's new, or go to the [notes tab](./notes/25.12) for full details.
* **[No-code flows](./notes/25.12#no-code-flows)**: For projects that have opted in, flows can be built using drag-and-drop nodes, conditions, and entity collection – reducing reliance on custom functions for common logic.
* **[Multi-draft (Branches)](./notes/25.12#multi-draft-branches)**: Work in parallel using branches and resolve conflicts visually.
* **[API integrations in Agent Studio](./notes/25.12#api-integrations-in-agent-studio)**: Configure and manage external APIs directly in the UI using environment-specific authentication and reusable operations.
* **[Variant info in Test Cases](./notes/25.12#variant-info-in-test-cases)**: See which variant each test case was saved against.
* **[Conversation review & PolyScore enhancements](./notes/25.12#conversation-review-and-polyscore-enhancements)**: Clearer call summaries and PolyScore breakdowns in the table and Conversation Review.
* **[Smart Analyst live reasoning steps](./notes/25.12#smart-analyst-live-reasoning)**: Analysis steps now stream live as Smart Analyst runs.
Click the **bolded** titles for a breakdown of what's new, or go to the [notes tab](./notes/25.11) for full details.
* **[Connected Knowledge](./notes/25.11#knowledge-source-hub)**: Add, group, and refresh multiple knowledge sources in the Knowledge area – files, URLs, and third-party integrations – with environment/variant scoping and per-chunk citations in Conversation Review.
* **[Integrations overview page](./notes/25.11#integrations-overview-page)**: Browse a searchable, filterable catalog of supported telephony, chat, CRM, vertical, and KB integrations directly inside Agent Studio.
* **[Multi-channel dashboard](./notes/25.11#multi-channel-dashboard)**: New Voice/Chat homepage tabs with channel-specific KPIs and charts, plus automatic currency selection.
* **[SMS messaging-service IDs](./notes/25.11#sms-messaging-service-ids)**: Use Twilio Messaging Service IDs (`MGxxxx`) in SMS fields, replacing the old phone-number-only restriction.
Click the **bolded** titles for a breakdown of what's new, or go to the [notes tab](./notes/25.10) for full details.
* **[Live call listening](./notes/25.10#live-call-listening)**: Watch calls stream live on the Conversations page – turns appear in real time with clear "in progress" indicators and duration tracking.
* **[Advanced Webchat customization](./notes/25.10#advanced-webchat-customization)**: Configure disclaimer messages, consent buttons, and clickable Privacy Policy or T\&C links for GDPR-compliant chat widgets.
* **[Auto-run Test Sets](./notes/25.10#auto-run-test-sets)**: Test Sets can now run automatically when publishing or promoting to Pre-release or Live.
* **[Function logging (conv.log)](./notes/25.10#function-logging-conv-log)**: Add structured logs directly inside functions for easier debugging, visible in Conversation Review → Diagnosis.
* **[Smart Analyst templates](./notes/25.10#smart-analyst-templates)**: New pre-built analysis templates to help build out a quick, categorized set of insights.
* **[Agent Analysis – scheduled batches](./notes/25.10#agent-analysis-scheduled-batches)**: Automate daily or weekly analytics runs with trend charts and filters to track changes over time.
Click the **bolded** titles for a breakdown of what's new, or go to the [notes tab](./notes/25.09) for full details.
* **[Webchat configuration](./notes/25.09#webchat-config)**: Customize the webchat agent's name, button text, and widget colors; live preview in-browser and deploy quickly with an embed or script tag.
* **[Test cases](./notes/25.09#test-cases)**: Define and run individual scenarios, then bundle them into reusable Test Sets for regression testing and workflow coverage.
* **[Home page updates](./notes/25.09#home-page-v2)**: Average PolyScore summary, evolution charts for Containment and PolyScore, and clearer distribution labeling.
* **[Smart Analyst: chat history + structured answers](./notes/25.09#smart-analyst-history)**: Resume past analyses, rename or delete conversations, and view answers with sources and steps.
* **[Numbers tab](./notes/25.09#phone-numbers-variants)**: Buy and manage numbers quickly and assign them to variants for multi-site deployments.
* **[Conversations API: tool calls](./notes/25.09#conversations-api-tool-calls)**: Programmatic access to function/tool execution events; environment-scoped endpoints.
Click the **bolded** titles for a breakdown of what's new, or go to the [notes tab](./notes/25.08) for full details.
* **[Home page improvements](./notes/25.08#home-page-updates)**: Faster load times and a cleaner layout on the Agent Studio homepage dashboard.
* **[AI call summaries](./notes/25.08#ai-call-summaries)**: GPT-based summaries now surface at the top of Conversation Review and as tooltips in Conversations.
* **[Multi-voice limit increase](./notes/25.08#multi-voice-limit-increase)**: Configure up to **10 voices** per project for multi-lingual or multi-persona agents.
* **[Enhanced call review filters](./notes/25.08#new-call-review-filters)**: New options for delivery status, channel, and other metadata–plus snappier filtering.
* **[Updated channel and metadata display](./notes/25.08#updated-channel-and-metadata-display)**: Clearer *Inbound/Outbound/Agent Chat* tags and more column options.
* **[GPT-5 models in Agent Studio (experimental)](./notes/25.08#gpt-5-models-in-agent-studio-experimental)**: Try **GPT-5 nano** and **GPT-5 mini** (recommended), plus **GPT-5 large** and **GPT-5 chat (router)** for experimentation. Not yet ready for production traffic; quota available on request.
* **[In-app calling with variants](./notes/25.08#in-app-calling-with-variants)**: You can run voice test calls against specific [variants](/knowledge/variants/introduction), with transcripts tagged by `variant_id`.
* **[Smart Analyst improvements](./notes/25.08#smart-analyst-improvements)**: Clickable call IDs added to [Smart Analyst](/wren/analyze) to link directly to Conversation Review, SQL query range expanded, and improved search performance.
* **[Start and End function error warnings](./notes/25.08#start-end-function-error-warnings)**: Clear UI alerts when Start or End functions contain errors that prevent execution.
* **[Agent Analysis – Multi-task](./notes/25.08#agent-analysis-multi-task)**: Configure up to **10 analysis tasks** per project with their own prompts, categories, and charts.
Click the **bolded** titles for a breakdown of what's new, or go to the [notes tab](./notes/25.07) for full details.
* **[Smart Analyst enhancements](./notes/25.07#smart-analyst-enhancements)**: Keyword filtering, SQL-style aggregation, and integrated charts now make LLM-powered QA review faster and more insightful.
* **[New homepage](./notes/25.07#new-homepage)**: A redesigned dashboard shows key agent metrics, best/worst recent calls, and quick links to support tools.
* **[Rich text refactor](./notes/25.07#rich-text-refactor)**: Input fields now support slash-command **rich text**, allowing inline references to flows, functions, and more.
* **[Add Amazon Polly voices](./notes/25.07#add-amazon-polly-voices)**: Add new voices with language/accent tags with the improved Amazon Polly integration.
* **[Adjust voice speed](./notes/25.07#adjust-voice-speed)**: Control TTS speed between 0.5× and 1.5× with a precision slider for pacing and accessibility.
* **[Claude integration for Agent Studio functions](./notes/25.07#claude-integration-for-agent-studio-functions)**: Use Claude to generate summaries, text, or structured outputs inside functions.
* **[Channel filter and call metadata improvements](./notes/25.07#channel-filter-and-call-metadata-improvements)**: Conversation Review now shows clearer call direction tags (*Inbound*, *Outbound*, *Agent chat*) and improved filtering.
* **[Outbound call delivery tracking](./notes/25.07#outbound-call-delivery-tracking)**: Delivery outcomes like *Busy*, *Invalid Number*, and *Declined* are now visible in Conversation Review filters and columns for outbound calls.
Click the **bolded** titles for a breakdown of what's new, or go to the [notes tab](./notes/25.06) for full details.
* **[Agent configuration](./notes/25.06#agent-configuration)**: You can now define settings like opening hours or routing rules in a JSON config form, without editing flows.
* **[Version comparison enhancements](./notes/25.06#version-comparison-v2)**: The diff version structure introduced in the **25.02** release is now supported across functions and flows.
* **[Action name search and autofill](./notes/25.06#action-name-search-and-autofill)**: Type `/name` in any rich text field to trigger action insertion.
* **[Cached disclaimer messages](./notes/25.06#cached-disclaimer-messages)**: Disclaimer messages are now stored in the Cache under [audio management](/voice-channel/audio-library), reducing latency and improving reliability across multiple flows.
* **[Smart analyst (Beta)](./notes/25.06#smart-analyst-beta)**: This LLM-powered QA tool can rate calls, summarize agent behavior, and flag weak containment. Contact your PolyAI rep to participate in the Smart Analyst **beta**.
* **[Agent memory](./notes/25.06#agent-memory)**: Retrieve persistent values from previous conversations with the `conv.memory` object.
* **[Test suite](./notes/25.06#test-suite)**: Save real conversations as [test cases](/testing/simulation-tests) and re-run them against draft or sandbox versions to check for changes in behavior.
* **[PolyScore](./notes/25.06#polyscore)**: New automatic scoring for conversation quality using defined behavioral metrics.
Click the **bolded** titles for a breakdown of what's new, or go to the [notes tab](./notes/25.05) for full details.
* **[DTMF support](./notes/25.05#dtmf-support)**: Configure tone-based input (DTMF) during specific steps to collect keypad responses from callers with support for timeouts, digit length, and early listening.
* **[Chat with variants](./notes/25.05#chat-with-variants)**: You can now test how different variants respond in the chat panel–choose any draft, sandbox, or variant on demand.
* **[Duplicate and set default variants](./notes/25.05#duplicate-and-set-default-variants)**: From the ellipsis menu on the variant page, duplicate an existing variant or assign a new default with a simple toggle.
* **[Build KBs with URL and PDF upload](./notes/25.05#build-kbs-with-url-and-pdf-upload)**: Create Knowledge topics directly from a website or uploaded PDF. Real-time crawl status and error reporting help troubleshoot issues when importing.
* **[Chat-to-review shortcut](./notes/25.05#chat-to-review-shortcut)**: Quickly jump from a chat session to the conversation review page with one click, streamlining your debugging process.
* **[Handoff reason and utterance](./notes/25.05#handoff-reason-and-utterance)**: You can now include `reason` and `utterance` fields when writing a handoff implementation in a KB topic, flow, or function call.
* **[Entities and Intents in Conversation Review](./notes/25.05#entities-and-intents-in-conversation-review)**: View detected intents and extracted entities directly inside the [Conversation Review](/analytics/conversations/review) page.
* **[Improved multi-language ASR accuracy](./notes/25.05#improved-multi-language-asr-accuracy)**: Speech recognition updates improve accuracy for numbers, dates, and accented speakers across several languages.
* **[Conversation review: session duration filter](./notes/25.05#conversation-review-session-duration-filter)**: Filter conversations by session length to focus QA on very short or long calls.
Click the **bolded** titles for a breakdown of what's new, or go to the [notes tab](./notes/25.04) for full details.
* **[Information architecture updates](./notes/25.04#information-architecture-updates)**: Tools have been regrouped by function. "Analyze" is now "Manage", and sections like Voice and Environments & Versions have moved or been renamed.
* **[Metrics](./notes/25.04#metrics)**: Use the new Agent Analysis tab to run custom metrics across batches of calls and generate insight-rich evaluations.
* **[Live collaboration support](./notes/25.04#live-collaboration-and-edit-history)**: Agent Studio now shows who else is editing a draft, alerts you when updates are saved, and lets you review edit history to avoid accidental overwrites.
* **[Call categorization](./notes/25.04#call-categorization)**: Use an LLM to rate calls for tone, intent, or compliance. Categories are defined per project. Contact your PolyAI rep to configure.
* **[Workspace filter in Conversations](./notes/25.04#workspace-filter-in-conversations)**: Filter conversation review by workspace to focus on your team's calls.
* **[Utility function – extract\_address](./notes/25.04#utility-function--utilsextract_address)**: Extracts a structured address from a user message. Returns a typed object, or a clear error. Opt-in only.
* **[Conversation history access – conv.history](./notes/25.04#conversation-history-access--convhistory)**: Use `conv.history` to access earlier turns from inside a utility function. Supports custom logic and debugging.
* **[Import and export variants](./notes/25.04#import-and-export-variants)**: Export all variant data to CSV, edit it, then re-import across agents. Includes overwrite protection.
* **[Variant ID added to conversations](./notes/25.04#variant-id-added-to-conversations)**: Each call now shows the variant ID used–helpful for QA and tracking.
* **[Multi-voice agents](./notes/25.04#multi-voice-agents)**: Assign multiple TTS voices to an agent and control their distribution. Great for A/B testing or simulating real-world voice teams.
Click the **bolded** titles for a detailed breakdown of the released feature, or open the [notes tab](./notes/25.03) on the sidebar for the full release notes.
* **[Overview dashboard enhancements](./notes/25.03#overview-dashboard-enhancements)**: Additions to the dashboard include call volumes, durations, containment rate, SMS and function stats–refreshed hourly.
* **[Safety dashboard enhancements](./notes/25.03#safety-dashboard-enhancements)**: A refreshed version of the safety dashboard to match the new overview, with faster load times and a clearer layout.
* **[Open matched topics in a new tab](./notes/25.03#open-matched-topics-in-a-new-tab)**: In conversation review, clicking a matched topic opens it in a new browser tab–letting you keep your place while checking the KB.
* **[Version tracking in conversation review](./notes/25.03#version-info-added-to-conversation-review)**: Each conversation now shows which version of the agent it ran on.
* **[Add voices directly in Agent Studio](./notes/25.03#add-new-voices-in-agent-studio)**: Voices can now be added or managed without leaving the platform.
* **[Filter voices by language, accent, or gender](./notes/25.03#filter-voices-by-language-accent-and-gender)**: The voices page now supports helpful filters to speed up selection.
* **[Send SMS immediately during function calls](./notes/25.03#send-sms-during-a-function-call)**: SMS messages now send in real time as part of the function, so agents won't falsely confirm delivery if the message fails.
* **[Improved KB search for actions and tags](./notes/25.03#improved-kb-search-for-actions)**: You can now search for SMS, handoff, and function names in the Knowledge area using the main search bar.
Click the **bolded** titles for a detailed breakdown of the released feature, or open the [notes tab](./notes/25.02) on the sidebar for the full release notes.
* **[View Knowledge differences between versions](./notes/25.02#view-knowledge-base-differences-between-versions)**: Easily compare changes across different versions of your Knowledge for better content tracking and updates.
* **[Utterances for high latency functions](./notes/25.02#function-latency-control)**: Manage function latency effectively by configuring filler utterances and dynamic delay timing.
* **[Upload custom audio to replace cached items](./notes/25.02#upload-audio-to-replace-cached-items)**: Upload pre-recorded audio directly from the Agent Studio audio management resource.
* **[Add variants to Knowledge items](./notes/25.02#reference-variants-in-the-knowledge-base)**: Add variant attributes to Knowledge content dynamically.
* **[Manage transition functions in a flow](./notes/25.02#managing-transition-functions-in-a-flow)**: Improve transition function management within flows, preventing unintended deletions.
* **[New conversation review annotations](./notes/25.02#conversation-review-annotations)**: Add annotations and comments to conversations for better review and collaboration.
* **[A new version of the overview dashboard](./notes/25.02#enterprise-overview-dashboard)**: A new standardized dashboard displaying key operational data like total calls, duration, and handover rates.
Click the **bolded** titles for a detailed breakdown of the released feature, or open the [notes tab](./notes/25.01) on the sidebar for the full release notes.
* **[Enterprise safety dashboard](./notes/25.01#safety-dashboard)**: A new dashboard focused on flagged calls and safety filter trigger analysis.
* **[Custom dashboards](./notes/25.01#custom-dashboards)**: Track project-specific success metrics with tailored dashboards.
* **[In-app calling](./notes/25.01#in-app-calling)**: Test voice interactions directly in-studio without telephony setup, enabling faster and simplified workflows.
* **[Audio management](./notes/25.01#audio-management)**: Delete or regenerate cached TTS audio for improved flexibility.
* **[A new Knowledge structure](./notes/25.01#knowledge-base-structure)**: Separate questions and content for better organization.
* **[End-of-conversation functions calls](./notes/25.01#end-functions)**: Trigger automatic function calls when a conversation ends to log data, create tickets, or call APIs.
* **[API enhancements](./notes/25.01#variants-in-the-conversations-api)**: Variant information now included in the Conversations API.
Click the **bolded** titles for a detailed breakdown of the released feature, or open the [notes tab](./notes/24.12) on the sidebar for the full release notes.
* **[Multi-site config](./notes/24.12#multi-site-config)**: Manage multiple site-specific Knowledge configurations in a single agent, with location-specific variants for tailored responses.
* **[Global ASR corrections, biasing, and keyword boosting](./notes/24.12#asr-updates)**: Customize Automatic Speech Recognition (ASR) corrections to refine transcribed text, improving LLM input accuracy.
* **[Audio management](./notes/24.12#audio-management)**: Browse, delete, regenerate, or upload cached TTS audio for better quality control.
* **[Customize latency response delay](./notes/24.12#customize-latency-response-delay)**: Set dynamic response delays to fit conversational tone and audience preferences.
* **[Copy and paste flows](./notes/24.12#copy-paste-flows)**: Transfer flows or nodes between projects to reuse configurations across builds.
* **[Call recordings download](./notes/24.12#call-recordings-download)**: Download call recordings directly from the conversation detail page, with required permissions.
Click the **bolded** titles for a detailed breakdown of the released feature, or open the [notes tab](./notes/24.11) on the sidebar for the full release notes.
* **[In-app function debugging](./notes/24.11#in-app-function-debugging)**: View and copy input, output, and error messages for function calls directly in the Conversation Review and agent Chat Panel.
* **[Enhanced SMS](./notes/24.11#enhanced-sms-functionality)**: agents can send SMS messages to alternative numbers specified by callers and upgrade SMS templates to advanced functions with added logic and configurations.
* **[Knowledge export](./notes/24.11#knowledge-base-export)**: Export Knowledge topics to a CSV file for version control and reuse.
* **[Barge-in feature](./notes/24.11#barge-in-feature)**: Enable agents to be interrupted by callers, improving natural conversation flow and reducing latency.
* **[Stop keywords](./notes/24.11#stop-on-keyword)**: Configure specific words or phrases to automatically halt the agent's response and trigger a function.
Click the **bolded** titles for a detailed breakdown of the released feature, or open the [notes tab](./notes/24.10) on the sidebar for the full release notes.
* **[Separate voice disclaimer with ringing tone](./notes/24.10#disclaimers)**: Customize greetings and dial tones to enhance user interaction.
* **[ASR biasing for flows](./notes/24.10#asr-biasing-for-flows)**: Configure speech recognition biasing for specific input types, like alphanumerics, times, or precise dates, and improve ASR performance and accuracy.
* **[UK and EU regions](./notes/24.10#uk-and-eu-regions)**: Regional expansion for improved performance and compliance.
* **[View versions](./notes/24.10#view-versions)**: Access and manage historical and live versions of agents for better development and maintenance.
* **[Content safety filters](./notes/24.10#content-safety-filters)**: Full control over content filter severity and configurations for project-specific needs.
***
Updates will be added to this page sequentially with product releases.