Kore AI Release Notes

Patch Release

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

Configuration

Fallback Messages for No Agent Available and Out-of-Office Flows

Admins can now configure channel-specific fallback messages under Conditional Flows for No Agent Available and Out-of-Office Hours scenarios. These messages are displayed when a conversation encounters either scenario and no conditional flow is configured to handle it, ensuring a consistent response regardless of routing context.

Configurable Conversation Timer Metric

Admins can now select which timer metric is displayed in the Agent Console, choosing from Total Chat Handling Time (default), Agent Handling Time, Agent Last Message Time, or Interaction Handling Time. The setting applies to all agents, and existing deployments are unaffected.

Analytics

View Last Handling Agent for Work Bin Conversations

Supervisors can now see the last agent who handled a conversation before it was moved to the Work Bin, visible in both the Queues and Interactions views in the Monitor tab.

Agent Response Usage Report

A new daily usage report tracks how many times agents used each standard response and secure form over a selected date range of up to 92 days or the last quarter, exported as CSV with a configurable date format.

API

Translation and Snooze Fields Added to Call Details API v2

Two new fields are now available in every AgentSegment object in the Call Details v2 API:

chosenTranslation indicates whether the agent used translation during their segment.

snoozeinfo returns an array of snooze periods with start and end timestamps, available when requested using selectedFields.

Patch Release

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

Widget Enhancement

Data Export for the Feedback Dashboard

The Feedback dashboard now supports CSV export of View All data, along with agent details, for the Overall Agent AI Widget Feedback, Suggestions Feedback, and Summary Feedback sections.

API Enhancement

Agent AI Configuration Management Through Export and Export Status APIs

The platform Export and Export Status APIs now support Agent AI-specific configurations, including coaching rules, playbooks, widget settings, widget preferences, and connect/exit events. To export all supported configurations, pass exportType : latest in the request payload.

Patch Release

This update includes enhancements summarized below.

Public-Key JWE Authentication for Hosted Exchange Web SDK

Hosted Exchange Web SDK now supports public-key JWE authentication, enabling secure authentication using customer-managed public keys while maintaining compatibility with existing authentication flows.

Environment-Specific SAML Entity IDs

Each deployment environment now uses a unique SAML Service Provider (SP) Entity ID, allowing administrators to configure separate SAML applications within their identity provider (IdP) for development, staging, and production. Existing SAML SSO configurations must be updated with the new SP Entity ID after upgrading to this release.

Minor Release

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

Console

Copy Option for AI-generated Conversation Summaries

Agents can now copy the auto-generated end-of-conversation summary to the clipboard with a single click across Chat, Voice, and Email. A notification confirms whether the copy action succeeded or failed.

Template-level Shortcuts for Agent Response Templates

Agents can now invoke individual response templates directly using a nested shortcut format, such as /billing/refundpolicy , instead of navigating a group shortcut and manually selecting from a list.

Timeline Events for Chat Transfers in the Console and Transcripts

Chat transfers now appear as system-generated timeline events in the conversation, showing the transferring agent, timestamp, and transfer target-whether a queue or another agent. These events are visible to receiving agents, in supervisor monitoring views, and in conversation transcripts.

Configuration

Network Disruption Notification Delay

Administrators can now configure a delay of 3 seconds to 1 minute before agents see a Customer got disconnected notification, suppressing it if the customer reconnects within that window. This reduces notification noise from short-lived connectivity interruptions, such as SDK reloads.

Video Call Recording Consent Prompt

A new Display Recording Consent Prompt setting under Video Call Recording Control lets administrators disable the Web SDK’s built-in recording consent prompt, useful when consent is already collected earlier in a customized video call flow. The setting is enabled by default for new and existing configurations.

Queue-Based and Combined Skill-Queue Conditions for Waiting Experience

Waiting Experience configurations can now be triggered by queue or by a combination of skill and queue using AND logic, in addition to the existing skill-only condition. Existing skill-only configurations continue to work unchanged.

Analytics

Center Wide Abandoned Wallboard-Manual Scrolling and Updated Top-line Widgets

A new Allow manual scrolling option in the Center Wide Abandoned Wallboard configuration disables auto-scroll for the Queue-Skill table, allowing users to scroll and sort manually.

The Agents’ top-line widget now displays available and system-busy agents relative to the total number of active agents, and the Longest Wait widget has been replaced with Capacity Utilized, which shows active conversations relative to available agent slots.

Download Plain Text Transcript from the Conversations Dashboard

A new Download Plain Text Transcript option is now available in the Conversations Dashboard, alongside the existing Download Transcript option. An Export Plain Text Transcripts bulk action is also available, supporting up to 25 conversations at a time.

API

New callContactAt API for Scheduling Agentless Campaign Callbacks

A new callContactAt API lets one or more contacts be scheduled for a callback at a specified date and time within an Agentless Campaign, supporting scenarios where a contact requests to be called back later.

Minor Release

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

UI Enhancements

Agent-specific Summaries for Warm and Cold Transfers

Agent AI now generates transfer summaries tailored to each agent involved in a warm or cold transfer. The Agent Transfer Summary setting lets admins choose whether to generate summaries for all participating agents or only for the transferring agent.

Agent AI Analytics and Dashboard Enhancements

Agent AI Analytics dashboards include the following enhancements:

• Overview: Added Search AI metrics, along with two new panels What are your customers looking for (Automation) and What are your agents looking for (Search).
• Performance: A new dashboard that shows the average times for generating the closing summary, the mid-conversation summary, and the AI response (non-streaming).
• Feedback: Now also shows feedback for all summary types.
• Conversation Logs: Added an Insights tab showing search queries and results. The Transcript tab now shows timestamps in HH:MM:SS format for each message.

Integration Enhancements

Agent AI integration with Five9 Outgoing Calls

Agent AI integration with Five9 now supports outbound calls. When an outbound call connects, the Agent AI widget automatically loads and provides real-time transcription, intent detection, sentiment analysis, coaching, and playbooks. After the call ends, Agent AI generates a post-call summary. Learn more.

Agent AI Integration with NICE Agent Desktop Chat

Agent AI now integrates with NICE Agent Desktop Chat. Agents can access real-time assistance, intent detection, sentiment analysis, and chat summaries within the NICE Agent Desktop. Agents can also send or copy Agent AI responses into the chat conversation. Learn more.

Call SID Visibility in Agent AI Logs

Agent AI now displays the Call SID alongside the Agentic Session ID in the UI and logs. Teams can use these identifiers to trace calls and diagnose transcript-generation issues.

Agent AI landing summary for Five9 voice bot transfers

Agent AI now automatically loads on the Five9 agent desktop when a call transfers from a Kore voice bot to a human agent. Agents can view the full conversation transcript and summary on widget load, giving them immediate context to assist the customer.

API Enhancement

Conversation Records API enhancements

The Conversation Records API includes the following updates:

• Supports searching by conversationIds and filtering by the widgetLoaded flag.
• Returns landing, interim, and final summaries, each with a generatedAt timestamp.
• Exposes customer messages, AI suggestions, agent responses, conversation summaries, and feedback data in the response for custom analytics exports.

Patch Release

This update includes new features and enhancements summarized below.

Arch AI Enhancements

Arch AI now provides a more reliable experience for authoring, generation, and evaluation. Improvements include support for larger source documents, more reliable preservation of handoffs across multiple sources, refined validation to reduce unnecessary generation failures, and non-blocking diagnostics to help identify issues without interrupting the generation process.

Language-Aware ON_START Messages

The Web SDK session interaction language is now accessible within the ON_START event, enabling language-specific welcome messages without requiring workflow-based workarounds. This simplifies multilingual agent design, reduces unnecessary latency, and allows startup logic to use standard ABL conditional expressions.

Major Release

This update includes new features and enhancements summarized below.

Multi-Agent Orchestration

Enhanced Delegation and Handoff Workflows

Multi-agent workflows now support both returning and non-returning delegation patterns, enabling more flexible interruption, escalation, and transfer scenarios. DELEGATE and HANDOFF behaviors are now distinguished, making it easier to implement workflows where conversations either return to the originating flow or are permanently handed off to specialized agents.

Smarter Supervisor Direct Responses

Supervisors can now respond directly to user requests by default, reducing unnecessary routing between agents. This ensures delegated responses are returned to users while still allowing Supervisors to operate as routing-only orchestrators when needed via the canRespondDirectly setting.

Web SDK

Web SDK Multi-Language UI Customization

The Web SDK chat widget now supports language-based customization of UI elements such as chatbot names and typing hints, making it easier to support multilingual deployments.

Simplified Web SDK Integration

Web SDK deployments can now be configured with public API keys and origin allowlists, eliminating the need to generate per-channel embed tokens and simplifying setup with greater control over embedded deployments.

Web SDK Distribution via NPM and CDN

The Web SDK is now available through npm and CDN distribution channels, making it easier to integrate into modern web development workflows and deployment pipelines. The SDK is available here.

Voice

Enhanced SIP Header Support for Voice Channels

SIP header information from inbound and transferred voice calls is now available, enabling routing and business logic based on telephony metadata — including queue information, customer identifiers, language preferences, campaign data, and transfer context.

Security and Compliance

OCI Vault Support for Customer-Managed Encryption Keys

Bring Your Own Key (BYOK) now supports Oracle Cloud Infrastructure (OCI) Vault Key Management Service (KMS), in addition to AWS KMS, Azure Key Vault, Google Cloud KMS, and external REST-compatible KMS, providing greater flexibility to manage customer-controlled encryption keys and compliance requirements.

Minor Release

This update includes new features and enhancements summarized below.

Search AI and Knowledge Management

Enhanced Search Tool Configuration

Search Tool parameters, such as filters and retrieval settings (for example, topK), can now be configured as mandatory or optional, providing greater control over knowledge retrieval behavior and ensuring that required parameters are consistently applied during tool execution improving retrieval accuracy and reducing reliance on prompt-based instructions.

Custom HTTP Connector for Knowledge Bases

Content can now be ingested into a Knowledge Base from custom HTTP-based data sources. The connector supports scheduled synchronization, schema discovery, field mapping, and secure connectivity options including mTLS, making it easier to integrate proprietary enterprise systems and external data sources with RAG applications. Ingestion workflows also support JavaScript-based content transformations, allowing data to be preprocessed before chunking and indexing.

AI Engineering Tools

Expanded Model Support

The Platform now supports Anthropic's Claude Opus 4.8 model.

Other Improvements

SSO Enhancements

The platform now auto-generates SAML and OIDC endpoint URLs for identity provider configuration. These system-managed URLs ensure consistent setup, reduce manual errors, and are available only to organization owners and admins.

Patch Release

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

Analytics

Stable Sorting for the Engaged Column and Transcript Slider Improvements

In the Monitor tab, sorting by the Engaged column (descending) now remains stable when new conversations arrive — incoming conversations are placed in the correct sort position rather than moving to the top. Supervisors can also switch between conversations while the transcript slider is open; the slider refreshes automatically with the transcript of the selected conversation without requiring a manual close and reopen.

Enterprise Search

This update includes new features and feature enhancements summarized below.

A dedicated Search experience is now available alongside Chat, with its own tab in the left panel. Search results pull from all connected connectors, with connector-specific tabs and filters for People and Timeline. Related Searches appear after the first four results, triggering new searches in the same thread without creating a new one.

Administrators can enable Enterprise Search under Assistant Configurations and select one enterprise knowledge source for search results.

User Management — Partners

A new Partners tab in User Management lets administrators view, invite, and manage partner users. All partners invited to the account appear under this tab. Administrators can view partner details, change roles, suspend, delete, permanently delete, and export partner users.

Partner invitations are restricted to configured partner domains. If an email address does not belong to a partner domain, an inline error displays: “Invalid domain.” If no partner domains exist in Domain Management, the Partners page shows an empty state prompting the administrator to add partner domains first, with a link to Domain Management.

Additional Language Support

German, Japanese, Spanish, and French are now available as supported languages. Users can select a preferred language from the language settings, and the selected language applies immediately across the application. All system text, including menus, buttons, labels, messages, and notifications, reflects the selected language.

New LLM Models

The General Purpose LLM configuration now supports three additional models: gemini-flash-3.5, gemini-flash-lite-3.1, and openai-5.5. Administrators can add these models from the LLM configuration page and use them across agents and platform tools.

Theme Settings — Dark and Light Themes

Users can now select a theme from the profile settings popup in the end-user application. Available options are System Default, Dark, and Light. The selected theme applies immediately across the application UI, persists across sessions, and synchronizes bidirectionally between the end-user application and the Admin Console.

Minor Release

This update includes new features and enhancements summarized below.

Updates to Web SDK Experience

Improved the Web SDK experience with welcome-message lifecycle enhancements, theme refinements, markdown rendering improvements, and footer-link fixes. Enhanced the Web SDK session handling by preserving and securely resuming idle sessions instead of recreating conversations.

Updates to SearchAI and Knowledge Management

Simplified the SearchAI Knowledge tool DSL, improved knowledge-tool binding and resolution behavior, and enhanced structured-data processing and knowledge ingestion reliability.

Updates to Tool and Gather Definitions

Added support for the effect and provides properties in AgentTool definitions and the satisfiedBy property in GatherField definitions.

Minor Release

This update includes new features and enhancements summarized below.

Credential Management Updates

Introduced Config Variables ({{config.X}}) and Auth Profiles as the new credential management model, replacing Tool Secrets and the Tool Secrets Management API.

New Memory and Handoff Capabilities

Added support for the per_activation reset mode for session variables. Enhanced handoff workflows with ON_RETURN.set, ON_RETURN.map, and typed handoff history support.

Validation and Tool Execution Enhancements

Added batched LLM validation for fields using VALIDATION_PROCESS: LLM and clarified last__result storage behavior, including store_result semantics.

Project Import and Tooling Improvements

Added support for tool-stub synthesis during project bundle import, allowing tool definitions to be generated from inline agent TOOLS: signatures and re-exported automatically.

ABL Syntax and Field Updates

Updated the ABL expression syntax with method-call operators such as input.contains(), .matches(), and abl.is_number(). Updated the human-agent escalation fields to use user.wants_human_agent.