Skip to main content
Back to list of all release notes This document provides information about the latest feature updates and enhancements introduced in the Platform Services of AI for Service (XO) v11.x releases. For previous updates, see release notes of 2025 and 2024.

​
v11.23.1 April 11, 2026

This update includes enhancements and bug fixes. The key enhancements included in this release are summarized below.

​
App Settings

Control Access to Original PII Values for End Users Developers can control whether end users see original PII values or masked, redacted, or replaced values. This can be applied at the global level, overriding node-level configurations, or configured individually on agent and entity nodes. When disabled, the platform always redacts the original values. Learn more. Enhanced OAuth v2 Auth Profile Types: mTLS Support and Custom Header Controls The following capabilities have been introduced for the OAuth 2.0 (Client Credentials) and OAuth 2.0 (Password Grant Type) Auth Profile types:
  • mTLS with OAuth Support: Enables combined mTLS and OAuth for Service Nodes via the Client Certificate Exchange toggle. When enabled, certificate-based client authentication is enforced during the TLS handshake, strengthening security across the OAuth lifecycle. The toggle is enabled by default, with certificate provisioning managed through backend onboarding.
  • Custom Authorization Header Support: Enables custom headers in requests to improve compatibility with external systems that require additional auth parameters. The Apply these request headers to the Refresh Token call option determines whether headers are included in Refresh Token requests.
Learn more

​
Administration

Audit Report Enhancement: App Deletion Logging The audit report in the Admin Console now captures app deletion events within a workspace, giving admins complete visibility and traceability of this action. Learn more

​
v11.23.0 March 28, 2026

This update includes enhancements and bug fixes. The key enhancements included in this release are summarized below.

​
LLM & Generative AI

Google Gemini Integration AI for Service now supports Google Gemini as an out-of-the-box (OOB) integration, allowing platform users to access Google Gemini models directly within the Platform across all GenAI features. Users must create and manage their own prompts for their use cases.
  • Simple Integration Setup: Configure the integration using an API key.
  • Supported models: Gemini 3.1 Pro Preview, Gemini 3 Flash Preview, Gemini 2.5 Pro, Gemini 2.5 Flash, and Gemini 2.5 Flash-Lite.
Learn more.

​
Channels

Session Isolation by Inbound Number for WhatsApp Infobip Channel The channel-based session is a new setting in WhatsApp channel configurations that prevents unintended session merging when users interact with multiple inbound numbers in the same app. It uniquely identifies sessions based on inbound numbers, considering each number as an independent channel associated with a specific flow. When you enable it for an existing app, it may disrupt ongoing sessions if the inbound numbers are linked to experience flows. Learn more. Support for Multiple WhatsApp Infobip Accounts The Platform now supports configuring up to 10 Infobip accounts for the WhatsApp infobip channel, enabling organizations with multiple business units to manage their WhatsApp operations independently. You can map each account to one or more inbound numbers, which are treated as distinct channels at runtime to ensure accurate session handling, flow execution, and response routing. Learn more.

​
App Language

Spanish Language Support Support for Spanish (Beta) as a new App language is now available via profile menu > app language. Learn more.

​
v11.22.1 March 14, 2026

This update includes an enhancement and bug fixes. The key enhancement included in this release is summarized below.

​
Security & Control

SSO Enhancements: Onboarding and Login Controls AI for Service supports both Identity Provider (IdP)-Initiated and Service Provider (SP)-Initiated SSO. In the IdP-initiated flow, authentication begins at the IdP, which sends a SAML response to the platform for validation. In the SP-initiated flow, authentication begins at the platform, which redirects the user for authentication before creating a session. This enhancement adds the following capabilities:
  • Restrict Auto-Onboarding: By default, new users are automatically onboarded during IdP-initiated login. When this toggle is enabled, automatic onboarding is disabled, keeping user provisioning fully controlled by your external system.
  • Skip 2FA During First-Time Login: Administrators can now skip OTP-based authentication for first-time logins, providing flexibility to align the login experience with your organization’s security policies especially where authentication is already enforced at the IdP level.
Learn more.

​
Channels

Email Channel Enhancements DKIM Configuration DomainKeys Identified Mail (DKIM) is now available as a standalone module, allowing users to verify a domain independently before setting up an email channel and reuse it across multiple channels — eliminating repeated verification.
  • Advanced Email Channels: DKIM verification is mandatory for the channel setup. The platform checks for a verified DKIM record and requires completed verification before proceeding.
  • Microsoft Exchange: DKIM signing is optional and off by default. Without it, the platform sends emails through the Microsoft Graph API using Microsoft’s native delivery. To enable DKIM signing, you must verify a DKIM record before completing the channel setup.
Manual Email Configuration for Microsoft Exchange Exchange channels now support manually adding email IDs, in addition to configuring them through a Microsoft 365 Group. Manually added email IDs default to Outbound usage, allowing agents to use them for outbound conversations. User Identity Source The platform now supports using the Reply-To address for user and session identification, rather than the From address. This is useful when an intermediary email aggregator is in use, where multiple conversations share the same From address but have distinct Reply-To values. This option is off by default. Improved HTML Email Processing The Email channel now efficiently handles large HTML emails. Raw text is extracted for processing while the full HTML structure — including lists, hyperlinks, and text alignment — is preserved for accurate display in Agent Desktop. Learn more.

​
Analytics

Task Execution Logs Enhancement Task Execution Logs now capture execution details for Agent, Prompt, and SearchAI nodes, including LLM calls and any associated pre- or post-processor scripts. These details appear in the API Calls and Script Execution sections, making it easier to analyze execution flow and debug AI agent behavior. Learn more.

​
App Settings

Channel-Level Control for Session Closure Messages Specific channels can now be excluded from receiving session closure messages via the Additional Settings option in the Session Closure Behavior section. When the Send a Message toggle is enabled, users can select which channels should not receive these messages. Email is excluded by default for new apps to avoid unnecessary inbox notifications. For newly added channels, session closure messages remain enabled by default. Learn more.

​
v11.22.0 February 28, 2026

This update includes enhancements and bug fixes. The key enhancements included in this release are summarized below.

​
LLM & Generative AI

Change Log Enhancement Change Logs will track the entire prompt lifecycle, including creation, updates, and deletions, providing a clear, auditable history of all prompt changes.

​
API

Enhanced User Engagement Trend API (v2) The User Engagement Trend API now delivers all user engagement metrics through a single endpoint. This includes counts for unique, new, and returning users, along with daily or hourly averages for each category.

​
App Settings

Auto-Token Regeneration for OAuth2 Password Grant Type The Platform now automatically regenerates Auth and Refresh tokens for the OAuth 2.0 Password Grant Type using stored credentials, ensuring uninterrupted service when tokens expire. End-to-End Payload Encryption Extended to Additional APIs Payload encryption is now supported for the LLM and Generative AI Usage Logs API and the Conversation Details and Summary API. When the ‘Enforce Request and Response Payload Encryption’ setting is enabled in the JWT application, and the relevant scopes — Gen AI and LLM Usage Logs and Chat History — are selected, request and response payloads are automatically encrypted and decrypted using the symmetric key associated with those scopes.

​
Channels

Typing Indicator Support for MS Teams The platform now shows typing indicators in MS Teams, providing users with real-time visual feedback as an AI or human agent composes a response. This keeps users informed during the interaction and makes conversations feel more natural. Proactive Welcome Message for MS Teams Validation The MS Teams Channel Adapter now automatically sends a welcome message when the app is installed in the personal scope. This ensures compliance with Microsoft Teams Marketplace validation and certification requirements. As a result, the app distribution process is smoother.

​
v11.21.1 January 31, 2026

This update includes an enhancement and bug fixes. The key enhancement included in this release is summarized below.

​
Channels

Right-to-Left Language Support in WebSDK The WebSDK channel now supports right-to-left (RTL) languages. Responses in Arabic and other RTL languages automatically align in RTL format, improving readability and delivering a more natural user experience. MS Teams Channel Analytics Enhancement MS Teams channel analytics now supports the team channel login email ID instead of the alphanumeric channel ID across the platforms. Enable the toggle “Show email ID instead of channel ID” in the channel integration settings to replace channel user ID with email IDs throughout your analytics dashboards.

​
Admin Console

Support for External ID in BYOK Configurations BYOK AWS configurations now include an auto-populated External ID field for secure cross-account IAM role assumption, in line with AWS best practices.

​
v11.21.0 January 17, 2026

This update includes enhancements and bug fixes. The key enhancements included in this release are summarized below.

​
LLM & Generative AI

Prompts Library: Usage Status and Association Tracking The Prompts Library will display “In Use” and “Not in Use” statuses for custom prompts based on actual usage at the feature or node level, replacing the previous “Active” and “Inactive” labels.

​
Channels

Email Thread Continuity When Adding Recipients The email channel now supports adding To, CC, and BCC recipients mid-conversation without breaking the email thread. When users or agents add recipients, the platform maintains the existing thread and preserves conversation context, allowing all participants to join and respond seamlessly. Email Channel Session Configuration and Analytics Updates Changes to channel-based and thread-based session configurations (enable or disable) are now captured in change logs for improved audit tracking. Email Channel analytics updates are reflected in Generative AI Usage Logs and Get Analytics API. New Channel Integration: Microsoft Copilot Microsoft Copilot is now available as a communication channel, expanding integration options beyond the existing Microsoft Teams channel.

​
App Settings

CVV Data Type in Global PII Settings The Global PII settings now include a CVV data type for redacting credit card verification values (3 or 4 digits) at entry. This prevents CVV data from persisting in logs or storage, and automatically purges it after session closure. Dialog Filter for Locale-Specific Responses Language Management now offers a Dialog filter, in addition to the existing Language and Component Type filters, for efficiently managing locale-specific responses. Localization Support for Standard Responses Standard Responses now support language-specific configurations across conversation management areas, including Dialog Interruptions, DialogGPT Events, Virtual Assistant Events, Intent Events, and Conversation Events. Centralized URL Management and Revocation Controls Admins can now centrally manage security settings for Platform-generated URLs (chat history and attachments). They can configure expiry times and optional access limits at the app level, and instantly revoke all active URLs using an emergency revocation control for enhanced security and compliance.

​
Analytics

Unified Interactions Dashboard Availability The ‘Interactions Dashboard’ has been renamed to “Conversations” and is now accessible to all licensed users under ‘Analytics’ > ‘Overview’. It provides unified access to real-time latency reports and session analytics across all products.