Kore Service Agent AI Release Notes

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

UI Enhancements

Pass Metadata Support in Search AI Configuration

In the newly available Pass Metadata configuration section, you can select Landing Summary, Agent-Customer Chat History, and User Context to pass as metadata. This improves response relevance, personalization, and accuracy without requiring manual query rephrasing.

Spanish Support for the Agent AI UXO App Language

Support for Spanish as an App Language is now available via profile menu > app language.

Integration Enhancements

Custom Field Support for Salesforce Email Channel

Agent AI integration with the Salesforce Email Channel now supports custom field objects. Salesforce admins can configure custom data in the Agent AI Configuration page by mapping payload keys to Case field API names using a .json file. The system resolves these fields at runtime and sends case data to the Agent AI widget.

Agent AI integration with Five9 Voice

Agent AI integration with Five9 Voice supports Automation, Agent Coaching, Agent Playbook, Sentiment Analysis, Transcription, end-of-call summary, and Custom Data. It also supports Secure Custom Data transfer, such as agent name and ID, to the Agent AI widget.

SDK Enhancement

Headless SDK for Cross-Platform Integration

The new headless SDK for browser and Node.js environments, with support for standard loading methods, enables message handling, internal transfers, summary generation, and conversation closure through a unified API. It removes UI dependencies and simplifies integrations.

Original source Report a problem

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

Integration Enhancements

Open Knowledge Base Articles Within the Salesforce Workspace

The Agent AI widget in Salesforce now allows agents to access knowledge base (KB) articles directly from the Search tab within a workspace subtab of the current browser session. This keeps agents in the active session, preventing reauthentication prompts or interruptions to the customer interaction.

Automatic Conversation Summary After Einstein Bot Handoff in Salesforce

The Agent AI widget in Salesforce now automatically generates a conversation summary when a customer interaction is handed off from Einstein Bot to a live agent. The summary is displayed in the Assist tab, giving agents quick context on the customer’s issue and actions already taken — without reviewing the full chat transcript. The summary is also stored in interaction metadata for downstream use.

Automatic Summary Updates for Email-to-Case in Salesforce

The Agent AI widget for the Email-to-Case channel in Salesforce now keeps the Assist tab summary up to date with the latest email conversation. When the widget loads, it displays a summary of the existing email thread. As new emails arrive or agents generate or submit a summary, the Assist tab updates to reflect the latest context.

UI Enhancements

Expand and Collapse Controls for Customer Messages and Agentic NBA Suggestions

In the Agent AI widget’s Assist tab, customer messages and Agentic Next Best Action (NBA) suggestions now include expand and collapse buttons that appear on hover. By default, the messages and the previous suggestions (sent or unsent) are collapsed, while the latest suggestion appears expanded. This prevents messages from automatically collapsing while agents copy suggestion content.

Original source Report a problem

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

Widget Enhancements

Feedback for Agentic Copilot Next Best Action Suggestions

Agents can now give ‘Thumbs Up’ or ‘Thumbs Down’ feedback on Agentic Copilot Next Best Action (NBA) suggestions directly in the Agent AI widget. For negative feedback, agents can select from multiple configurable reasons and add optional comments. Admins can manage the available reasons in Feedback Settings. All feedback is logged and accessible through the Raw Data API to support performance analysis and continuous improvement.

Configurable Summary Sharing for Cold Transfers

Admins can now choose which conversation summary is shared during cold transfers — either only the latest transferring agent’s intermittent summary, or the full conversation, including bot and all participants.

Extended Session Closure for Exit Event Workflows

Agent AI now supports delaying session closure beyond the End of Conversation event, giving agents time to complete workflows configured in Agentic Platform Exit Events before the session closes.

Configurable Intermittent Summary Generation Limit

Admins can now configure how many intermittent summaries are generated per agent, up to a maximum of 20.

API Enhancements

Enhanced Raw Data API for Agent Coaching and Playbooks Data

The Raw Data API now includes additional Agent Coaching and Playbook data, such as playbook type (primary and dynamic), stage and step details, scenario completion status, configuration-based triggers, step execution order, and step adherence validation. It also captures triggered coaching events, actions, and details on action adherence. This enables customers to build custom metrics, create external dashboards, and audit Playbook analytics.

Conversation Termination API

Agent AI uses the Hooks API to notify the system when a conversation terminates, enabling reliable execution of configured post-conversation actions. Invoke this API once at the final termination of the call—whether it ends normally or unexpectedly—to ensure accurate event handling and prevent duplicate processing.

Integration Enhancements

Direct OAuth Configuration for Email-to-Case Summary Enrichment

Agent AI administrators can now configure external API access for Email-to-Case summary enrichment using direct OAuth credentials (Client ID and Client Secret), instead of Salesforce Named Credentials. This simplifies setup and removes Salesforce dependencies by enabling OAuth configuration directly within Agent AI.

Runtime Bot/App Context Metadata Support for Advanced Search Filtering

Agent AI now provides runtime access to the full Bot/App context object—including direct context variables, BotUserSession, and app context attributes—and supports passing these values to the Advanced Search API as metaFilters. This enables context-aware and more accurate search results.

Real-Time Transcription Support for NICE CXone Softphone in Salesforce

Agent AI now supports real-time call context initialization and voice transcription for agents using the NICE CXone softphone in Salesforce. When a call is accepted, the widget automatically initializes, retrieves the session identifier, and starts live transcription — enabling real-time assistance and accurate post-call summaries.

Unified Refresh for Email and Sprout Social Cases in Salesforce

Enhanced Agent AI “Refresh / Next Best Action” button functionality on Salesforce Case pages now supports both Email- and Sprout Social-originated cases with a single unified refresh action. This improvement ensures that agents receive accurate, context-aware recommendations within the Agent AI widget, regardless of the originating channel.

Original source Report a problem

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

Widget Enhancements

Improved Copy and Send Behavior for Agentic Copilot Responses

Agentic Copilot responses now use a delimiter

===AGENT_NOTES===

. When the copilot response received from Agent Platform contains this delimiter separating the customer-facing content and agent-specific information, only the customer-facing content above the delimiter is copied or sent when an agent clicks Copy or Send. Agent-specific information remains visible to agents only. This reduces manual edits and helps lower average handling time (AHT).

Agentic Copilot Streams Next Best Responses

Agentic Copilot now streams suggestions incrementally during live conversations, rather than waiting for the full response to be generated. This reduces perceived latency and allows agents to respond faster. Admins can enable this feature by toggling Agentic Response Streaming under Widget Settings > Agent AI Channel Specific Settings.

Conversation Metadata Support for Agentic App

Agent AI now passes selected conversation metadata—such as landing summaries, agent-customer chat history, intermittent summaries, and custom data—to the Agentic App. This preserves context during conversation transfer from automation to human agents, enabling Agentic Copilot to deliver relevant, context-aware responses.

Playbook State Persistence on Widget Reloads and Transfers

The system now preserves playbook checklist progress and step adherence during widget reloads and conversation transfers, ensuring agents resume exactly where they left off without losing workflow continuity.

UI Enhancements

Support for Multiple Search Apps Integration

The Search AI integration in UX 11 now supports configuring multiple Search Apps across XO 10 and XO 11. Admins can use the inbuilt XO 11 Search App (AI Agent) or configure up to three Search Apps across XO 10 and XO 11.

Search Result Layout Option in Widget Theming

The Widget Theming > Layout Customization section now includes the Search Result Layout subsection. Admins can select one of the following options:

• Classic Search: Shows only the current search results.
• Conversational Search: Shows a history of previous questions and answers to reduce repetition and make it more contextual.

Integration Enhancements

Salesforce Omnichannel Web Chat Pre-handoff Conversation Context in Agent AI

Agent AI now automatically retrieves, stores, and accesses the complete pre-handoff conversation context when a Salesforce Einstein Bot transfers a Web Chat to a live agent. This includes the full bot conversation history and all pre-chat attributes stored in the Agent AI Bot Context (custom data), which are available in the Agent AI widget for use in dialog tasks and workflows. After handoff, Agent AI automatically detects customer intent using the Bot Platform.

Proactive Cross-Channel Customer Summaries in Salesforce-Agent AI Integration

Agent AI automatically analyzes and summarizes a customer’s recent interactions across all channels, including orders, returns, exchanges, chat, email, SMS, WhatsApp, phone calls, product registrations, and other activities available through Harman’s APIs. This summary helps agents quickly understand the customer context, anticipate call intent, and assist customers efficiently without navigating multiple CRM pages.

Original source Report a problem