> ## Documentation Index
> Fetch the complete documentation index at: https://koreai.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent Platform Release Notes

This document provides information on the feature updates and enhancements introduced in the recent Agent Platform \{ **Artemis** } releases.

***

## June 2026

<p className="rn-heading">\{ Artemis 1.2.1 } June 25, 2026 </p>

<Badge>Patch Release</Badge>

This update includes new features and enhancements summarized below.

<p className="rn-subtitle">Arch AI Enhancements</p>

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.

<p className="rn-subtitle">Language-Aware ON\_START Messages</p>

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.

***

<p className="rn-heading">\{ Artemis 1.2.0 } June 20, 2026 </p>

<Badge>Major Release</Badge>

This update includes new features and enhancements summarized below.

<p className="rn-title">Multi-Agent Orchestration</p>

<p className="rn-subtitle">Enhanced Delegation and Handoff Workflows</p>

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.

<p className="rn-subtitle">Smarter Supervisor Direct Responses</p>

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.

<p className="rn-title">Web SDK</p>

<p className="rn-subtitle">Web SDK Multi-Language UI Customization</p>

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.

<p className="rn-subtitle">Simplified Web SDK Integration</p>

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.

<p className="rn-subtitle">Web SDK Distribution via NPM and CDN</p>

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](https://www.npmjs.com/package/@koredev/artemis-web-sdk).

<p className="rn-title">Voice</p>

<p className="rn-subtitle">Enhanced SIP Header Support for Voice Channels</p>

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.

<p className="rn-title">Security and Compliance</p>

<p className="rn-subtitle">OCI Vault Support for Customer-Managed Encryption Keys</p>

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.

***

<p className="rn-heading">\{ Artemis 1.1.4 } June 16, 2026 </p>

<Badge>Minor Release</Badge>

This update includes new features and enhancements summarized below.

<p className="rn-title">Search AI and Knowledge Management</p>

<p className="rn-subtitle">Enhanced Search Tool Configuration</p>

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.

<p className="rn-subtitle">Custom HTTP Connector for Knowledge Bases</p>

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.

<p className="rn-title">AI Engineering Tools</p>

<p className="rn-subtitle">Expanded Model Support</p>

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

[Learn more →](/agent-platform/supported-models)

<p className="rn-title">Other Improvements</p>

<p className="rn-subtitle">SSO Enhancements</p>

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.

[Learn more →](/agent-platform/administration/workspace-and-team#single-sign-on-sso)

***

<p className="rn-heading">\{ Artemis 1.1.3 } June 11, 2026 </p>

<Badge>Patch Release</Badge>

This release includes bug fixes and usability improvements across the platform.

***

<p className="rn-heading">\{ Artemis 1.1.2 } June 08, 2026 </p>

<Badge>Patch Release</Badge>

This release includes bug fixes and usability improvements across the platform.

***

<p className="rn-heading">\{ Artemis 1.1.1 } June 05, 2026 </p>

<Badge>Minor Release</Badge>

This update includes new features and enhancements summarized below.

<p className="rn-subtitle">Updates to Web SDK Experience</p>

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.

<p className="rn-subtitle">Updates to SearchAI and Knowledge Management</p>

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

<p className="rn-subtitle">Updates to Tool and Gather Definitions</p>

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

***

<p className="rn-heading">\{ Artemis 1.1.0 } June 01, 2026 </p>

<Badge>Minor Release</Badge>

This update includes new features and enhancements summarized below.

<p className="rn-subtitle">Credential Management Updates</p>

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

<p className="rn-subtitle">New Memory and Handoff Capabilities</p>

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.

<p className="rn-subtitle">Validation and Tool Execution Enhancements</p>

Added batched LLM validation for fields using `VALIDATION_PROCESS: LLM` and clarified `last_<tool_name>_result` storage behavior, including `store_result` semantics.

<p className="rn-subtitle">Project Import and Tooling Improvements</p>

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.

<p className="rn-subtitle">ABL Syntax and Field Updates</p>

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`.

***

## May 2026

<p className="rn-heading">\{ Artemis 1.0.4 } May 29, 2026 </p>

<Badge>Minor Release</Badge>

This update includes a feature enhancement summarized below.

<p className="rn-subtitle">Updates to Filler Messages</p>

Enhanced Filler Messages with contextual filler history support. Administrators can now configure how much recent conversation history and how many previously generated filler messages are used when generating new filler responses. The filler prompt also supports the new `{{conversationHistory}}` and `{{previousFillers}}` placeholders for more context-aware filler generation.

***

<p className="rn-heading">\{ Artemis 1.0.3 } May 29, 2026 </p>

<Badge>Minor Release</Badge>

This update includes new features and enhancements summarized below.

<p className="rn-subtitle">Tool Readiness Evidence in Arch AI</p>

Arch AI now shows readiness evidence for the tools it adds while building your agents. Each tool is clearly labeled as backed by a live integration or by a stub/mock placeholder, and a project health view surfaces what still needs to be configured before the agent is ready to go live.

<p className="rn-subtitle">More Reliable Agent Generation from SOPs</p>

Generating agents from Standard Operating Procedures (SOPs) now produces more complete agent topologies. Arch AI avoids incomplete builds and validates the generated structure for quality, so SOP-derived projects start from a fuller, more accurate design.

<p className="rn-subtitle">Authoring Evidence in Arch AI Reviews</p>

Arch AI authoring reviews now display evidence badges and incorporate evaluation results. Authoring guidance for constructs such as `MEMORY`, `HANDOFF`, `TOOLS`, `GATHER`, `AGENT`, `SUPERVISOR`, and guardrails is rendered from the Platform's own construct definitions, giving you clearer, more consistent recommendations as you build.

{/* CATEGORY: Bug Fix — stale-error clearing, new-chat-after-error, and no-full-refresh are reliability/UX fixes to existing chat */}

<p className="rn-subtitle">A Smoother Arch AI Chat Experience</p>

Several reliability improvements make working in the Arch AI chat smoother: errors that have already been resolved (such as model or provider configuration issues) no longer linger in the interface, you can start a new chat even when a previous session ended in an error, and sending a routine message no longer triggers a full refresh of the interface.

<p className="rn-subtitle">DELETE Method for HTTP Tools</p>

HTTP tools now support the `DELETE` method, alongside `GET`, `POST`, `PUT`, and `PATCH`. Your agents can now call REST endpoints that remove resources directly from an HTTP tool.

***

<p className="rn-heading">\{ Artemis 1.0.2 } May 29, 2026 </p>

<Badge>Minor Release</Badge>

This update includes new features and enhancements summarized below.

<p className="rn-title">Agents and Arch AI</p>

<p className="rn-subtitle">Evidence-grounded authoring in Arch AI</p>

Arch AI now grounds its authoring review in real parser and evaluation evidence, surfaces authoring-automation health and improvement opportunities, and routes proven best practices into generated agents — so the guidance you see while building reflects what the compiler and evals actually report.

<p className="rn-subtitle">Stronger evaluation gating</p>

Invalid eval imports are now marked non-runnable, runs with zero coverage are blocked before they start, cancelled runs are preserved, and the winning evaluation status is reported clearly — making evaluation results more trustworthy.

<p className="rn-subtitle">More reliable agent generation</p>

Improved the reliability of the Arch AI build experience: blueprint generation recovers from blank turns, BUILD topology failures are now recoverable instead of terminal, and the chat/generation experience handles error states more gracefully.

<p className="rn-subtitle">Canvas delegate edges render correctly</p>

Fixed a regression on the agent canvas where delegate relationship edges were drawn as handoff edges. Delegation and handoff relationships are now visually distinct.

<p className="rn-subtitle">Behavior Profile honors all CONVERSATION fields</p>

The Behavior Profile CONVERSATION block now applies all configured fields, resolving a case where only style and tone were applied and other fields were silently dropped.

<p className="rn-title">Tools and Workflows</p>

<p className="rn-subtitle">Tools page "New Tool" menu fix</p>

The Studio Tools page "+ New Tool" continues to be visible when the current tab has no tools. Now, you can create any type of tool regardless of which tab is active.

<p className="rn-subtitle">ABL workflow triggering from the AI4W channel</p>

Fixed an issue where ABL workflows didn't trigger when invoked from the AI for Work (AI4W) channel.

<p className="rn-title">Insights and Dashboards</p>

<p className="rn-subtitle">Agent Transfer dashboard</p>

Added an Agent Transfer insights dashboard. You can now analyze how and when conversations are transferred between agents.

<p className="rn-title">Voice</p>

<p className="rn-subtitle">Reliable voice channel provisioning</p>

Fixed an issue to improve the reliability of voice channel setup, during Jambonz WSS application provisioning.

<p className="rn-title">Studio and Administration</p>

<p className="rn-subtitle">Consistent Audit Log date formatting</p>

Audit Logs now use a consistent date format between the From–To filter and the results table, along with display fixes for smaller screen resolutions.

<p className="rn-subtitle">Git integration fixes</p>

Git-sync failures are now surfaced clearly in Studio, and import-error messages are normalized for easier troubleshooting.

<p className="rn-title">Security and Privacy</p>

<p className="rn-subtitle">SDK origin allowlist enforcement</p>

The Web SDK public-key embed now respects the selected channel's origin allowlist.

<p className="rn-subtitle">Hardened SearchAI downloads and outbound requests</p>

Strengthened security across SearchAI file downloads and outbound webhooks (including redirect handling) and hardened rich-content sanitization in the Web SDK.

<p className="rn-subtitle">Credential scrubbing in debug traces</p>

Tool credentials and other secrets are now scrubbed from debug traces and compile-time trace events, preventing sensitive values from appearing in diagnostics.

<p className="rn-subtitle">Cleaner euser error handling</p>

A failed LLM response is no longer misclassified as an empty response, and internal developer diagnostic strings aren't displayed to the users.

***

<p className="rn-heading">\{ Artemis 1.0.1 } May 25, 2026 </p>

<Badge>Minor Release</Badge>

This update includes new features and enhancements summarized below.

<p className="rn-title">Agents and Arch AI</p>

<p className="rn-subtitle">Reusable Agent Modules</p>

Package agent logic as modules and reuse them across multiple projects instead of rebuilding per project. Imported tools now route correctly into the agent's `TOOLS:` section.

Learn more about [Catalog Settings →](/agent-platform/administration/catalog-settings) and [Create & Manage Projects →](/agent-platform/projects).

<p className="rn-subtitle">Arch AI — one-shot generation and contract-driven authoring</p>

Arch AI adds a one-shot generate endpoint (describe an agent and get a working blueprint), and its generated constructs are now derived from the compiler contracts with enforced typed topology and validated tool contracts — producing more reliable, deploy-ready agents.

[Learn more →](/agent-platform/arch-ai)

<p className="rn-subtitle">Runtime guardrail enforcement</p>

Guardrails configured on an agent are now reliably applied at run time, closing a gap where policies could be skipped during live conversations.

[Learn more →](/agent-platform/safety-and-guardrails)

<p className="rn-title">Knowledge and Search AI</p>

<p className="rn-subtitle">Clearer web-crawl ingestion</p>

The knowledge web-crawler setup now gates the wizard so you can only advance when the source is ready to crawl, and a crawl indexing lifecycle with a live status strip shows ingestion progress from submission to searchable content.

<p className="rn-subtitle">Knowledge fast-path search</p>

A faster knowledge-retrieval path for agent chat, with the schema-preview endpoint now
accepting JSON Schema for type extraction — lower-latency answers in conversation.

[Learn more →](/agent-platform/knowledge)

<p className="rn-subtitle">Custom pipeline authoring redesign (contract-first)</p>

A redesigned authoring experience for custom indexing/processing pipelines with
contract-first validation, making pipeline configuration clearer and less error-prone.

[Learn more →](/ai-for-service/searchai/index-configuration)

<p className="rn-subtitle">Crawler reliability improvements</p>

Fixes to web-crawl ingestion (including docling filename/extension handling) improve the reliability of content ingested into knowledge.

[Learn more →](/ai-for-service/searchai/content-sources)

<p className="rn-title">Voice</p>

<p className="rn-subtitle">Unified voice provider registry and capability matrix</p>

A single registry of voice (STT/TTS) providers and their capabilities gives consistent provider selection and configuration across voice agents.

[Learn more →](/agent-platform/administration/ai-configuration#voice-services)

<p className="rn-subtitle">Configurable Gemini Live VAD sensitivity</p>

Gemini Live voice-activity-detection (VAD) sensitivity is now exposed in the speech-to-speech channel configuration, letting teams tune turn-taking and interruption behavior.

[Learn more →](/agent-platform/administration/ai-configuration#voice-services)

<p className="rn-title">Channels, Contact Center, and Connectors</p>

<p className="rn-subtitle">Contact-Center "After Call Work" (ACW) handling</p>

The runtime now receives and processes ACW/disposition events after a human-agent call closes (emitting `acw_completed` and `agent_disconnected` with SmartAssist event data, keeping sessions alive to capture disposition) — enabling accurate post-call workflows after an agent transfer.

[Learn more →](/agent-platform/escalate)

<p className="rn-subtitle">AI-for-Work channel type</p>

A dedicated channel lets AI for Work invoke ABL agents directly.

[Learn more →](/agent-platform/deployment)

<p className="rn-subtitle">Service Management connector category</p>

A new connector category groups Zendesk and ServiceNow under Service Management.

[Learn more →](/ai-for-service/searchai/connectors/connector-directory)

<p className="rn-title">LLM and Models</p>

<p className="rn-subtitle">AWS Bedrock provider integration</p>

Adds AWS Bedrock as an LLM provider with IAM role support and additional connection and configuration options.

Learn more about [AI Configuration →](/agent-platform/administration/ai-configuration) · [Supported AI Models →](/agent-platform/supported-models)

<p className="rn-title">Studio, Insights, and Analytics</p>

<p className="rn-subtitle">Insights Auditing — automated metric analysis & recommendations</p>

Automated analysis of agent and quality metrics with improvement recommendations, wired across the agent-performance, quality-monitor, and customer-insights dashboards.

[Learn more →](/agent-platform/analytics-insights/performance-quality)

<p className="rn-subtitle">Studio feedback viewer</p>

A recent-feedback table with filters in Studio to review captured user feedback.

[Learn more →](/agent-platform/analytics-insights/customer-insight)

<p className="rn-subtitle">Studio navigation redesign and design-system standardization</p>

Refreshed Studio navigation and a standardized design system, including sidebar localization labels.

<p className="rn-title">Security, Administration, and Runtime</p>

<p className="rn-subtitle">Platform domain allowlist and DB-managed Platform admins</p>

Adds a configurable Platform domain allowlist and database-managed Platform admin roles for tighter access governance.

[Learn more →](/agent-platform/administration/workspace-and-team)

<p className="rn-subtitle">JWE encryption for Hosted Exchange WebSDK auth</p>

Adds JWE support to secure the Hosted Exchange WebSDK authentication flow, with enforced JWE policy scope and hardened browser-SDK CORS handling.

[Learn more →](/agent-platform/sdks)

<p className="rn-subtitle">Response metadata: LLM-generated versus scripted</p>

Responses now carry metadata indicating whether a reply was LLM-generated or scripted, surfaced over the SDK/WebSocket structured content.

<p className="rn-title">Tools and WebSDK</p>

<p className="rn-subtitle">URL-encoded request body support</p>

HTTP tools now support `application/x-www-form-urlencoded` request bodies, with the body type selection preserved.

[Learn more →](/agent-platform/tools/http)

<p className="rn-subtitle">2xx responses return the response body</p>

Non-2xx HTTP responses now return the response body instead of being treated as outright execution failures, so agents can act on error payloads.

[Learn more →](/agent-platform/tools/http)

{/* CATEGORY: Feature Enhancement — WebSDK now renders hyperlinks, paragraph formatting, and lists instead of plain text */}

<p className="rn-subtitle">Rich-text rendering</p>

The WebSDK now renders hyperlinks, paragraph formatting, and lists instead of showing them as plain text.

[Learn more →](/agent-platform/sdks)

***

<p className="rn-heading">\{ Artemis 1.0 } May 21, 2026 </p>

Kore.ai Agent Platform \{ Artemis } is now available, with the following capabilities:

* Agent Blueprint Language (ABL™) — create and manage agents.
* Arch™ AI — generate agents from SOPs.
* SearchAI — manage and retrieve knowledge.
* Channels — deploy agents on web and voice.
* Tool integrations — connect agents to external tools.
* Insights dashboards — monitor agent performance.

For details, see [Platform Overview](/agent-platform/index).