Kore AI Release Notes

A new customer-facing CLI is now available, letting developers automate the full Agentic lifecycle, including authentication, project sync, eval runs, and deployment, from external systems, without Studio. <br />Learn more →

Microsoft Foundry is now available as a unified provider, replacing the previous Anthropic-only integration. Select models from multiple publishers, including OpenAI, Meta, Mistral, Cohere, and Anthropic, or enter custom deployments. The configuration also supports Azure AD Service Principal authentication with automatic token discovery.

Eval runs can now be scheduled to recur daily, weekly, or monthly, with time zone selection and flexible start and end conditions. <br />Learn more →

Eval runs in Studio now display exact start and completion timestamps alongside the existing relative time labels, across Studio.

Studio now warns you before you lose unsaved work when leaving the agent editor, with the option to save, discard, or stay. …

This update includes new features and feature enhancements summarized below.

You can now share a conversation as a link once the first query receives a response. Select share via link to generate the link, then copy or regenerate it, and use the update action to push later messages to the same link. Recipients open a read-only copy with sources and downloadable files, and they can't continue the conversation. Learn more→

The Enterprise Directory now includes a copy profile link option on contact detail pages, on contact cards in the listing view, and on contact cards in search results. Copying a link displays a confirmation message, so you can share a colleague profile without navigating the directory again. Learn more→

Enterprise Search now runs a query directly from a URL parameter and lands you on the Search tab with results already displayed. Searches you run in the interface update the browser URL with the query, the active tab, and any filters, so back and forward navigation, refresh, and shared links reproduce the same result state. Shared links respect each recipient's own permissions. Learn more→ …

You can now declare a trusted SIP transfer destination directly on the built-in call_transfer tool, instead of relying solely on the project-level transfer target. The destination is authored as a non-model default (default_source: config), so it's never visible to or fillable by the LLM. The compiler validates it at publish time — catching blank values, unresolved templates, and malformed SIP URIs before an agent goes live. <br />Learn more →

You can now set a project-level minimum speech-to-text (STT) confidence threshold for voice interactions. Transcripts below the threshold are treated as no input, preventing low-confidence speech recognition results from triggering agent responses. Set the threshold between 0 and 1; set it to 0 to disable it. <br />Learn more →

<Badge> Patch Release </Badge>

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

Agent AI suggestions now display content in collapsible sections that agents can expand to view. The Copy and Send buttons appear only for the customer-facing section.

Agent AI integration with Genesys now supports passing agent and queue metadata from Genesys to Agent AI. Quality AI uses this metadata to associate interactions and generate agent-level and queue-level quality metrics and analytics. Existing integrations that don't send this metadata continue to work without any changes.

Agent AI now supports mapping Agentic apps based on region and language.

The Agent Coaching Rules API now supports create, read, and update operations for coaching rules and utterances. The API also includes Export and Import endpoints that propagate changes across environments. Learn more→

<Badge> Patch Release </Badge>

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

Artemis sessions now appear as a dedicated channel in the Conversations dashboard and Interactions tab, with inbound and outbound messages routed through the Artemis channel adapter. Learn more→

The new Mask IP Address in Transcripts option lets you mask IP addresses across conversation transcripts on all channels. The option is added under Agent Settings → System Settings → Obscure Customer Info in Analytics - Interactions. Learn more→

This update includes new features and enhancements summarized below.

Tools can now return sensitive values — API keys, tokens, credentials — without exposing them to the LLM. These values are captured into an encrypted, session-scoped vault and kept invisible to the model and the conversation transcript. Use the new {{_secret.X}} syntax to restore a captured secret into a downstream tool's HTTP headers or request body. <br />Learn more →

You can now configure a dedicated Public Switched Telephone Network (PSTN) transfer target number for agent-initiated call transfers, alongside the existing SIP transfer configuration. Outbound PSTN transfers now correctly present the provisioned caller ID. <br />Learn more →

Integrators using the API channel can now issue a platform API key scoped specifically to closing sessions (close-session), instead of requiring a full administrative key to terminate a conversation programmatically. …

This update includes new features and enhancements summarized below.

Workflow builders can now set the default value of fields in a Data Entry node using either static text or expressions. Expressions can reference data from workflow triggers or previous workflow steps. For example, a reviewer's form can be pre-filled with an AI-generated draft for approval or editing. <br />Learn more →

The Web SDK Theme Builder now has a toggle to show or hide the attachment icon in the chat widget's compose bar. This lets FAQ and informational AI agents offer a cleaner, text-only interface when file uploads aren't needed, while keeping attachments enabled by default elsewhere.

Admins can now allow or restrict specific query operations for public-facing analytics dashboard widgets, from a new SQL Validation section in the Public Widget Data Policy settings. Supported restrictions include SQL comments, multiple SELECT statements, JOIN clauses, common table expressions (CTEs), set operations (UNION, INTERSECT, EXCEPT), and OR conditions. …

Feature enhancements and new capabilities introduced in this release are summarized below, followed by the breaking changes that may affect existing projects — review the migration steps before recompiling or republishing them on 1.4.0.

Message ACTIONS buttons and carousel card buttons can be configured with a URL so that clicking it opens the link directly in a new tab, instead of posting an action back to the agent. It is supported on the Web SDK/widget, Telegram, and LINE; other channels automatically fall back to a normal button. <br />Learn more →

Developers can connect a Git repository to a project to sync agent definitions and localization assets with version control, including push and pull from the Studio editor and conflict-resolution tools for simultaneous edits. <br />Learn more →

You can now edit agent logic directly in an inline code editor without leaving the visual canvas.

<Badge> Minor Release </Badge>

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

The Agent AI Logs section now lets admins export conversation log data in JSON format. The export honors date range filters, and the JSON data includes agent and customer messages, Agent AI suggestions, and actions and feedback on AI suggestions. Learn more→

Agent AI now generates only one NBA suggestion based on the latest customer email thread when the widget becomes active, using the case summary generated during widget-inactive time as additional context if the email lacks prior thread context.

Agent AI now supports thumbs-up and thumbs-down feedback for landing summaries across chat, voice, and email channels. Admins can configure feedback reasons for landing summaries under Feedback Settings, and the Feedback Dashboard now displays landing summary feedback. Learn more→

<Badge>Minor Release</Badge>

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

Agents can now switch the Agent Console to dark mode from the profile drop-down menu. The preference is persistent across logins. Learn more→

A new Workbin Duration column in the Agent Workbin displays the elapsed time since a conversation was last parked. The timer updates every minute, resets each time a conversation is re-parked, and agents can sort by this column to view the oldest conversations. Learn more→

Administrators can now independently turn translation on or off for Arrival Summary, Disposition Summary, and Automation Transcript. When turned on, content is displayed in its original language. Learn more→

The Arch AI activity panel now shows live, readable updates on each action as it happens, instead of delayed or raw output. <br />Learn more →

Arch AI now supports an iterative eval-optimize loop, allowing agents to be evaluated and refined through repeated automated passes, including voice-agent evaluation scenarios. <br />Learn more →

Arch AI now produces structured trace events for each internal step of agent generation, optimization, and evaluation, giving visibility into Arch's multi-step reasoning process for debugging and optimization. <br />Learn more →

Arch AI can now offer diagnostic guidance for voice issues like missing audio, TTS failures, or STT misconfiguration.

This update includes new features and feature enhancements summarized below.

Autonomous agents now support skills. When you add an agent, upload a skill as a folder or .zip file to extend what the agent can do. End users work with the agent directly and don't need to build or manage skills themselves. Learn more→

Administrators can now publish AI for Work agents as tools on MCP servers, making them available to MCP-compatible clients such as Claude and ChatGPT. A guided wizard configures the server, its tools, OAuth authentication, and access limits. Learn more→

Agents now support version history. Publish a version with a custom name and description, and the platform autosaves your ongoing changes as a single draft. Preview any version in read-only mode, restore an older version as a new draft, and manage up to 50 versions per agent. Learn more→

<Badge> Patch Release </Badge>

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

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. Learn more→

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.

<Badge>Patch Release</Badge>

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

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. Learn more→

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. Learn more→

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. <br />Learn more →

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.