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. +{/* CATEGORY: Minor Update — DSL simplification plus binding/resolution and ingestion reliability improvements to existing SearchAI/Knowledge behavior */} +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. +{/* CATEGORY: Feature Enhancement — new ABL definition properties (effect, provides, satisfiedBy) extend the tool/gather model */} +Updates to Tool and Gather Definitions
Added support for the `effect` and `provides` properties in AgentTool definitions and the `satisfiedBy` property in GatherField definitions. @@ -32,22 +47,32 @@ Added support for the `effect` and `provides` properties in AgentTool definition This update includes new features and enhancements summarized below. +{/* CATEGORY: New Feature — Config Variables and Auth Profiles are a net-new credential model that replaces Tool Secrets and its API */} +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. +{/* CATEGORY: Feature Enhancement — new per_activation reset mode and ON_RETURN.set/map + typed handoff history extend memory/handoff */} +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. +{/* CATEGORY: Feature Enhancement — batched LLM field validation is a new capability; last_Validation and Tool Execution Enhancements
Added batched LLM validation for fields using `VALIDATION_PROCESS: LLM` and clarified `last_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. +{/* CATEGORY: Feature Enhancement — new ABL expression method-call operators (.contains/.matches/abl.is_number) and updated escalation field */} +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`. @@ -60,6 +85,8 @@ Updated the ABL expression syntax with method-call operators such as `input.cont This update includes a feature enhancement summarized below. +{/* CATEGORY: Feature Enhancement — contextual filler history with new {{conversationHistory}}/{{previousFillers}} placeholders extends filler generation */} +Updates to Filler Messages
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. @@ -72,24 +99,34 @@ Enhanced Filler Messages with contextual filler history support. Administrators This update includes new features and enhancements summarized below. +{/* CATEGORY: New Feature — tool readiness evidence (live vs stub/mock) and a project health view are net-new Arch AI capabilities */} +Tool Readiness Evidence in Arch AI
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. +{/* CATEGORY: Feature Enhancement — more complete SOP-derived topologies with quality validation improves an existing generation flow */} +More Reliable Agent Generation from SOPs
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. +{/* CATEGORY: Feature Enhancement — evidence badges, eval results, and construct-definition-driven guidance enrich Arch AI authoring reviews */} +Authoring Evidence in Arch AI Reviews
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. {/* AG: Should the below reliability improvements be retained in RNs? */} +{/* CATEGORY: Bug Fix — stale-error clearing, new-chat-after-error, and no-full-refresh are reliability/UX fixes to existing chat */} +A Smoother Arch AI Chat Experience
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. +{/* CATEGORY: Feature Enhancement — adds DELETE alongside GET/POST/PUT/PATCH, a new HTTP-tool capability */} +DELETE Method for HTTP Tools
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. @@ -117,72 +154,102 @@ This update includes new features and enhancements summarized below.Agents and Arch AI
+{/* CATEGORY: Feature Enhancement — parser/eval-grounded review, automation health, and best-practice routing extend Arch AI authoring */} +Evidence-grounded authoring in Arch AI
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. +{/* CATEGORY: Feature Enhancement — non-runnable invalid imports, zero-coverage blocking, cancelled-run preservation, and clear winner status strengthen eval gating */} +Stronger evaluation gating
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. +{/* CATEGORY: Bug Fix — blank-turn recovery, recoverable BUILD failures, and graceful error states are reliability fixes to the build flow */} +More reliable agent generation
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. +{/* CATEGORY: Bug Fix — fixes a canvas regression that drew delegate edges as handoff edges */} +Canvas delegate edges render correctly
Fixed a regression on the agent canvas where delegate relationship edges were drawn as handoff edges. Delegation and handoff relationships are now visually distinct. +{/* CATEGORY: Bug Fix — resolves silently dropped CONVERSATION fields (only style/tone were applied) */} +Behavior Profile honors all CONVERSATION fields
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.Tools and Workflows
+{/* CATEGORY: Bug Fix — keeps "+ New Tool" visible/usable when the active tab has no tools */} +Tools page "New Tool" menu fix
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. +{/* CATEGORY: Bug Fix — fixes ABL workflows not triggering when invoked from the AI4W channel */} +ABL workflow triggering from the AI4W channel
Fixed an issue where ABL workflows didn't trigger when invoked from the AI for Work (AI4W) channel.Insights and Dashboards
+{/* CATEGORY: New Feature — net-new Agent Transfer insights dashboard */} +Agent Transfer dashboard
Added an Agent Transfer insights dashboard. You can now analyze how and when conversations are transferred between agents.Voice
+{/* CATEGORY: Bug Fix — improves reliability of Jambonz WSS voice-channel provisioning */} +Reliable voice channel provisioning
Fixed an issue to improve the reliability of voice channel setup, during Jambonz WSS application provisioning.Studio and Administration
+{/* CATEGORY: Bug Fix — consistent date format between filter and table plus small-screen display fixes */} +Consistent Audit Log date formatting
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. +{/* CATEGORY: Bug Fix — surfaces git-sync failures and normalizes import-error messages */} +Git integration fixes
Git-sync failures are now surfaced clearly in Studio, and import-error messages are normalized for easier troubleshooting.Security and Privacy
+{/* CATEGORY: Bug Fix — security hardening; public-key embed now respects the channel origin allowlist */} +SDK origin allowlist enforcement
The Web SDK public-key embed now respects the selected channel's origin allowlist +{/* CATEGORY: Bug Fix — security hardening of SearchAI downloads, outbound webhooks/redirects, and Web SDK rich-content sanitization */} +Hardened SearchAI downloads and outbound requests
Strengthened security across SearchAI file downloads and outbound webhooks (including redirect handling) and hardened rich-content sanitization in the Web SDK. +{/* CATEGORY: Bug Fix — security hardening; scrubs credentials/secrets from debug and compile-time traces */} +Credential scrubbing in debug traces
Tool credentials and other secrets are now scrubbed from debug traces and compile-time trace events, preventing sensitive values from appearing in diagnostics. +{/* CATEGORY: Bug Fix — failed LLM responses no longer misclassified as empty; internal diagnostic strings hidden from users */} +Cleaner euser error handling
A failed LLM response is no longer misclassified as an empty response, and internal developer diagnostic strings aren't displayed to the users. @@ -216,18 +283,24 @@ This update includes new features and enhancements summarized below.Agents and Arch AI
+{/* CATEGORY: New Feature — package and reuse agent logic as modules across projects; includes TOOLS: import routing fix */} +Reusable Agent Modules
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). +{/* CATEGORY: New Feature — new one-shot generate endpoint plus contract-derived, typed-topology, validated-tool authoring */} +Arch AI — one-shot generation and contract-driven authoring
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) +{/* CATEGORY: Bug Fix — closes a gap where configured guardrails could be skipped at run time */} +Runtime guardrail enforcement
Guardrails configured on an agent are now reliably applied at run time, closing a gap where policies could be skipped during live conversations. @@ -236,10 +309,14 @@ Guardrails configured on an agent are now reliably applied at run time, closingKnowledge and Search AI
+{/* CATEGORY: Feature Enhancement — wizard gating plus a crawl indexing lifecycle and live status strip extend the crawler setup */} +Clearer web-crawl ingestion
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. +{/* CATEGORY: Feature Enhancement — lower-latency knowledge retrieval path for chat; schema-preview now accepts JSON Schema */} +Knowledge fast-path search
A faster knowledge-retrieval path for agent chat, with the schema-preview endpoint now @@ -247,6 +324,8 @@ accepting JSON Schema for type extraction — lower-latency answers in conversat [Learn more →](/agent-platform/knowledge) +{/* CATEGORY: New Feature — redesigned contract-first authoring experience for custom indexing/processing pipelines */} +Custom pipeline authoring redesign (contract-first)
A redesigned authoring experience for custom indexing/processing pipelines with @@ -254,6 +333,8 @@ contract-first validation, making pipeline configuration clearer and less error- [Learn more →](/ai-for-service/searchai/index-configuration) +{/* CATEGORY: Bug Fix — web-crawl ingestion fixes including docling filename/extension handling */} +Crawler reliability improvements
Fixes to web-crawl ingestion (including docling filename/extension handling) improve the reliability of content ingested into knowledge. @@ -262,12 +343,16 @@ Fixes to web-crawl ingestion (including docling filename/extension handling) impVoice
+{/* CATEGORY: New Feature — single STT/TTS provider registry and capability matrix for consistent voice provider selection */} +Unified voice provider registry and capability matrix
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) +{/* CATEGORY: Feature Enhancement — exposes Gemini Live VAD sensitivity in speech-to-speech channel config */} +Configurable Gemini Live VAD sensitivity
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. @@ -276,18 +361,24 @@ Gemini Live voice-activity-detection (VAD) sensitivity is now exposed in the speChannels, Contact Center, and Connectors
+{/* CATEGORY: New Feature — runtime now processes ACW/disposition events (acw_completed, agent_disconnected) enabling post-call workflows */} +Contact-Center "After Call Work" (ACW) handling
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) +{/* CATEGORY: New Feature — dedicated channel that lets AI for Work invoke ABL agents directly */} +AI-for-Work channel type
A dedicated channel lets AI for Work invoke ABL agents directly. [Learn more →](/agent-platform/deployment) +{/* CATEGORY: Minor Update — new connector category grouping Zendesk and ServiceNow under Service Management */} +Service Management connector category
A new connector category groups Zendesk and ServiceNow under Service Management. @@ -296,6 +387,8 @@ A new connector category groups Zendesk and ServiceNow under Service Management.LLM and Models
+{/* CATEGORY: New Feature — adds AWS Bedrock as an LLM provider with IAM role support */} +AWS Bedrock provider integration
Adds AWS Bedrock as an LLM provider with IAM role support and additional connection and configuration options. @@ -304,36 +397,48 @@ Learn more about [AI Configuration →](/agent-platform/administration/ai-configStudio, Insights, and Analytics
+{/* CATEGORY: New Feature — automated metric analysis with recommendations across performance/quality/customer-insight dashboards */} +Insights Auditing — automated metric analysis & recommendations
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) +{/* CATEGORY: Feature Enhancement — new recent-feedback table with filters in Studio */} +Studio feedback viewer
A recent-feedback table with filters in Studio to review captured user feedback. [Learn more →](/agent-platform/analytics-insights/customer-insight) +{/* CATEGORY: Feature Enhancement — refreshed navigation, standardized design system, sidebar localization labels */} +Studio navigation redesign and design-system standardization
Refreshed Studio navigation and a standardized design system, including sidebar localization labels.Security, Administration, and Runtime
+{/* CATEGORY: New Feature — configurable platform domain allowlist and database-managed Platform admin roles */} +Platform domain allowlist and DB-managed Platform admins
Adds a configurable Platform domain allowlist and database-managed Platform admin roles for tighter access governance. [Learn more →](/agent-platform/administration/workspace-and-team) +{/* CATEGORY: Feature Enhancement — adds JWE to secure Hosted Exchange WebSDK auth, with enforced policy scope and hardened CORS */} +JWE encryption for Hosted Exchange WebSDK auth
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/api-reference/sdks) +{/* CATEGORY: Feature Enhancement — responses now carry LLM-generated-vs-scripted metadata over SDK/WebSocket structured content */} +Response metadata: LLM-generated versus scripted
Responses now carry metadata indicating whether a reply was LLM-generated or scripted, surfaced over the SDK/WebSocket structured content. @@ -342,12 +447,16 @@ Responses now carry metadata indicating whether a reply was LLM-generated or scrTools and WebSDK
+{/* CATEGORY: Feature Enhancement — HTTP tools now support application/x-www-form-urlencoded bodies with preserved body-type selection */} +URL-encoded request body support
HTTP tools now support `application/x-www-form-urlencoded` request bodies, with the body type selection preserved. [Learn more →](/agent-platform/tools/http) +{/* CATEGORY: Minor Update — non-2xx HTTP responses now return the body instead of being treated as outright failures */} +2xx responses return the response body
Non-2xx HTTP responses now return the response body instead of being treated as outright execution failures, so agents can act on error payloads. @@ -356,6 +465,8 @@ Non-2xx HTTP responses now return the response body instead of being treated as {/* AG: Should the below improvement be retained in RNs? */} +{/* CATEGORY: Feature Enhancement — WebSDK now renders hyperlinks, paragraph formatting, and lists instead of plain text */} +Rich-text rendering
The WebSDK now renders hyperlinks, paragraph formatting, and lists instead of showing them as plain text. @@ -364,6 +475,8 @@ The WebSDK now renders hyperlinks, paragraph formatting, and lists instead of sh --- +{/* CATEGORY: New Feature — initial GA release of Agent Platform { Artemis } (ABL, Arch AI, SearchAI, channels, tools, insights) */} + ## v1.0 May 21, 2026 Kore.ai Agent Platform \{ Artemis \} is now available, with the following capabilities: