What's new in IBM® watsonx Orchestrate®

Monitor agent metrics on watsonx.governance

Users that have watsonx Orchestrate tenants from IBM Cloud can now enable a monitoring agent feature to track key performance and usage metrics in depth of deployed agents on watsonx.governance. After builder or admin enabled it, these metrics are automatically sent to watsonx.governance, where you can view them in a dedicated dashboard for better visibility and control.

The benefits are:

• Gain insights of agent activity and performance.

• Monitor compliance and governance metrics in one place.

• Simplify troubleshooting and optimization with centralized data.

This feature is supported by the following regions on IBM Cloud:

• Dallas (us-south), in Texas, US

• Frankfurt (eu-de), in Germany

• London (eu-gb), in England

• Tokyo (jp-tok), in Japan

• Sydney (au-syd), in Australia

• Toronto (ca-tor), in Canada

See how to enable the monitoring agent on your watsonx Orchestrate to access the metrics dashboard on watsonx.governance in Monitoring agent analytics.

Use partner A2A agents

This release introduces the Partner A2A (Agent2Agent) agents, which enable your agent to seamlessly communicate with automated agent platforms outside watsonx Orchestrate. You can add a Partner A2A agent from the catalog as a collaborator to delegate work to an external agent and receive results automatically.

For more information, see Accessing partner A2A agents.

Manage structured data in the chat

Users can now manage structured data directly within their chat experience. This feature allows users to edit tables inline without leaving the chat interface, which provides a fast and intuitive method for entering and updating structured data.

Default greeting message for agents

This release adds a capability that enhances the user experience during voice interactions: a default greeting message for agents. Builders can define the welcome message that the agent delivers at the start of a voice interaction during the voice configuration.

See the details in Selecting the voice in the agent.

Updates for tools and flow builder

New prebuilt and partner agents available in the catalog

Foundation models deprecated

IBM watsonx Orchestrate no longer supports the following foundation models from 29 January 2026:

• llama-3-2-90b-vision-instruct

• llama-3-405b-instruct

For more information, see Deprecated and withdrawn models.

Other enhancements and changes

The following table details the fixes that are delivered in this release and the user role that is affected by the fix:

The following table lists the enhancements available in the current release corresponding to the user role:

Documentation updates

See the updates in the watsonx Orchestrate documentation and other contents for this release.

New sections

• IBM Watson Commerce now is named Supply chain IBM SIP. See more information in Connecting to Supply chain IBM SIP.

• The Overview of document processing section helps new users to work with document processing on watsonx Orchestrate.

• The GPT-OSS model behavior and instruction guidelines section guides builders to use the advanced capabilities of the GPT-OSS model in their agents

Updated sections

• The Known issues and limitations topic now has the following entry:

Models

• GPT-OSS 120B — OpenAI (via Groq)

Support for FedRAMP through AWS GovCloud (US)

IBM watsonx Orchestrate is now available on AWS GovCloud (US), a secure and cloud-based environment that is designed to support US government agencies and organizations handling sensitive and regulated data. It provides a compliant infrastructure to meet stringent federal requirements. AWS GovCloud (US) inherits the robust compliance framework of AWS, enabling customers to align with critical standards such as:

• Enhanced compliance alignment: AWS GovCloud (US) now offers improved support for FedRAMP requirements, streamlining authorization processes for government workloads.

• Strengthened data sovereignty: Expanded operational controls can ensure that all regions remain managed exclusively by US citizens, reinforcing compliance with government regulations.

• Improved isolation architecture: Logical and physical isolation enhancements provide greater security for sensitive workloads.

For more information, see:

• AWS GovCloud (US): compliance overview

• Licenses and entitlements for watsonx Orchestrate on Amazon Web Services (AWS) GovCloud (US)

Other updates in the documentation:

• The Feature parity based on deployments section was updated with the AWS GovCloud (US) deployment and its supported features.

• The Regulatory compliance and High availability, business continuity, backups, and disaster recovery on AWS sections were updated to adapt to the AWS GovCloud (US) regulatory compliance.

• The Logging in to IBM watsonx Orchestrate section has a new content for Logging in to IBM watsonx Orchestrate on AWS GovCloud (US).

• The Deployment-based availability of prebuilt agents has a new feature support entry for AWS GovCloud (US).

• Known issue in the Models category: Deprecation notice missing on AWS GovCloud (US)

Import external A2A agents as collaborators

You can now add external agents that use the Agent to Agent (A2A) protocol as collaborators when you build an agent in the UI. This update makes it easier to integrate third-party systems that follow the A2A standard and control how they exchange data during execution. For configuration details, see Adding agents from third-party platforms.

Data isolation support for AWS HIPAA-regulated environments

Deploy watsonx Orchestrate on AWS HIPAA-regulated clusters with data isolation. This capability provides dedicated data storage for stricter security requirements. For more details, see Data isolation on watsonx Orchestrate.

View tool runtime calls in observability traces

You can now see tool execution details inline in the Trace Details view when a flow includes a tool call. This update gives you full visibility into agent behavior and helps you troubleshoot faster. For more information, see Debug tool flow runtime issues.

Support single step SSO for embedded chat

You can now use single-step SSO token exchange for embedded chat. This update introduces a new authentication type in the UI that simplifies setup and improves SSO compatibility. Use this option if your identity provider supports direct token exchange for access tokens. For more information, see Configuring single sign-on for applications.

New AI model available for agent creation

You can now use GPT-OSS 120B — OpenAI (via Groq) when creating or editing an agent. This model is available in the AI model drop-down and can be used for supported use cases that require ultra-low latency or cost-efficient, high-volume processing.

Add a phone-like preview for testing DTMF in voice agents

You can now use phone-like preview in voice chats to test DTMF settings without ending the voice chat or making an actual phone call. By using the keypad, you can send DTMF inputs (0–9, *, #) to the agent and validate DTMF-dependent flows. You can also choose to turn off the setting without ending the ongoing voice session. For more information, see Configuring voice settings for agents.

Add audio cues for long voice agent responses

Voice agents can now play built-in “typing” sounds and hold music when a response takes longer than expected. These audio cues reassure callers that the agent is still processing their request and help reduce confusion during long pauses. For more information, see Configuring voice settings for agents.

Add DTMF support for SIP and Genesys audio connector

You can now enable Dual-Tone Multi-Frequency (DTMF) input for phone calls that use SIP or Genesys Audio Connector. By using DTMF, your voice agents can collect keypad inputs during a call, supporting IVR-style flows and mixed voice–keypad interactions. You can configure DTMF settings in Manage > Voice when you create or edit a voice configuration. For more information, see Configuring voice settings for agents.

Add Deepgram as a Speech to Text and Text to Speech provider

You can now select Deepgram as a Speech to Text (STT) and Text to Speech (TTS) provider when you create or edit a voice configuration. This update gives you additional language options and faster response times for voice interactions. To use Deepgram, go to Manage > Voice, create or edit a voice configuration, and choose Deepgram in the STT or TTS provider list. The interface shows only the settings that are supported for the selected Deepgram model and language. For more information, see Configuring voice settings for agents.

Copy agent responses

You can now copy any agent response, including plain text and grid responses, directly from Orchestrate Chat. Select the Copy icon next to a response to copy the full output with its formatting, making it easy to reuse content in documents, emails, and workflows.

New prebuilt and partner agents available in the catalog

Other enhancements and changes

The following table lists the enhancements available in the current release corresponding to the user role:

Other enhancements and changes

Documentation updates

See the updates in the watsonx Orchestrate documentation and other contents for this release.

New sections

• The Available AI models section lists all models that you can use in watsonx Orchestrate.

• The Adding AI models through AI Gateway section explains how to integrate models from different providers by using AI Gateway.

• The Design guidelines for agent icons section describes the specifications that you must follow when you upload an agent icon.

Updated sections

• The Connecting to an Astra DB content repository, Connecting to an Elasticsearch content repository and Connecting to a Milvus content repository sections now include guidance for passing context variables.

• The Choosing an AI model section now explains how to choose the right model for your use case.

• The Considerations for choosing an AI model section now provides more detailed guidance to help you evaluate model requirements.

• The Configuring voice settings for agents section now includes support for:

  • Phone-like preview for testing DTMF in voice agents

  • Audio cues for long agent responses

  • DTMF support for SIP and Genesys Audio Connector

  • Deepgram as a Speech to Text and Text to Speech provider

• The Adding agents for orchestration section was fully reorganized to improve clarity and navigation. The main page is streamlined, and new subpages group the different ways you can add agents, including:

  • Adding agents from catalog

  • Adding an agent from a local instance

  • Importing agents from external platforms

    • Adding agents from third-party platforms

    • Adding watsonx Orchestrate assistants as collaborator agents

    • Adding AI assistants as collaborator agents

• The Known issues and limitations topic now has the following entry:

Chat

• Orchestrate chat scrolling in Safari

Simplified navigation for building and analyzing agents

watsonx Orchestrate now features a redesigned navigation to help you build and analyze agents more efficiently.

• Analyze is now available directly in the main menu.

Use this option to quickly access the Agent analytics page. Agent analytics in watsonx Orchestrate provides built-in monitoring and observability, enabling builders to track, analyze, and optimize the performance of agents.

• Assistant builder is moved to the bottom of the main menu to help you focus on creating and managing agents and tools.

• The Build menu now opens the Build agents and tools page directly for quicker access.

This update gives you a clearer, more organized workspace. For more information, see Building agents.

Manage all your knowledge sources from one place

You can now manage all your knowledge sources in a single, centralized location with the new All knowledge section in watsonx Orchestrate.

• You can create a knowledge source independently of any agent from the All knowledge page.

• You can create a knowledge source directly from the Agent Builder page, and it is automatically added to your agent after the creation.

• You can add an existing knowledge source to an agent, allowing you to reuse a single knowledge across multiple agents.

• Each agent continues to support one knowledge at a time, but a knowledge can now be shared across agents for consistency, and easier maintenance.

This improvement streamlines how builders manage and reuse knowledge sources, reducing setup duplication and simplifying updates in agents. For more information, see Building a knowledge source.

Purchase partner agents from the catalog on IBM Cloud

You can now purchase and use partner agents directly from the watsonx Orchestrate catalog on IBM Cloud. This in-app experience enables you to discover, review, and subscribe to partner-built agents without leaving the watsonx Orchestrate workspace.

Partner agents are prebuilt AI agents developed by IBM-approved external partners and available in the watsonx Orchestrate catalog. Agents that require a subscription are marked with a lock icon and can be unlocked after purchase. Once purchased, the agent becomes available for builders in your instance. Builders can start using the purchased agent as a template to create a new agent or add it as a collaborator agent. This enhancement simplifies the way admins and builders discover, subscribe to, and manage partner-built agents, providing faster access to ready-to-use automations. For more information, see Purchasing partner agents.

The following GIF illustrates how admins can purchase partner agents from the catalog.

Note: This video has no narration.

Handle changes in subscription ownership more seamlessly

You can now manage changes in your subscription ownership or admin roles more smoothly on watsonx Orchestrate.

When a new subscription owner or admin is assigned in the SaaS Console, watsonx Orchestrate now reflects the changes consistently across the subscription and its instances. Currently, when new admins are added, the changes do not appear in the MCSP SaaS Console. Only subscription owner changes are synchronized with the MCSP SaaS Console. This update helps ensure that all subscription admins have access to existing and newly created instances without disruption.

Support for latest A2A protocol version

watsonx Orchestrate now supports version 0.3.0 of the Agent-to-Agent (A2A) protocol for external A2A agents. This update ensures compatibility with the latest protocol capabilities and improves reliability when integrating external agents.

Easily connect to MCP servers

You can now easily locate where to add MCP servers when building agents. The Add a tool modal is redesigned to make it simpler to discover and connect to MCP servers, OpenAPI specs, or tools from local instance. This enhancement improves discoverability and usability for builders who need to add or manage MCP tools efficiently. For more information, see Importing tools from an MCP server.

Data center expansion in IBM Cloud

The IBM Cloud data center is now expanded to include the following region:

São Paulo

IBM watsonx Orchestrate data center now includes São Paulo. This expansion helps improve performance, reduce latency, and meet data sovereignty requirements for users in Latin America. For more information, see Regional availability and outbound IP addresses.

Newly added prebuilt agents and tools

IBM watsonx Orchestrate introduces new prebuilt agents and tools to expand automation across key business domains.

For the complete list of available prebuilt agents and tools, see List of prebuilt agents.

IBM® watsonx Orchestrate® API updates

See the updates in the IBM watsonx Orchestrate API for this release.

Other enhancements and changes

The following table details the fixes that are delivered in the current release corresponding to the user role:

Documentation updates

See the updates in the watsonx Orchestrate documentation and other contents for this release.

New sections

• The Connecting to GitLab section shows how to enable the integration with watsonx Orchestrate.

• The Collecting diagnostic data for performance issues section provides instructions for gathering data for performance-related support cases.

• The Building a knowledge base section provides guidance on adding knowledge to agents.

Updated sections

• The Embedding agents in applications section was updated to add information about the noneditable agents.

• The Connecting agents to channels and Connecting agents to chat sections were updated to add information about voice interaction on the Orchestrate Chat home page.

• The Connecting to IBM Planning Analytics section was updated to add information about API key requirement in Basic Authentication.

• The Configuring the agent's behavior section was reorganized and improved to maintain consistency.

• The Connecting to Slack was updated to include steps to enable email visibility on Slack.

• The Known issues and limitations topic now has the following entry:

AI assistant access failure

• AI Assistant access failure for admin users added through SSM

IBM SaaS Console

• Subscription access in SaaS Console

Agents

• Purchasing partner agents

Connect your agent to SMS with Twilio

You can now integrate your agent with SMS by using Twilio. This feature lets your agent send and receive SMS messages, so you can automate alerts, reminders, and updates directly within your workflows. For more information, see Connecting to SMS with Twilio.

Multilingual support for agent knowledge

You can now upload documents to agent knowledge and use Chat with Docs in Brazilian Portuguese, Spanish, French, and German languages. This update helps to get more accurate and relevant responses in supported languages.

Control user access to reasoning traces

You can now choose whether users see the agent’s reasoning trace in chat. This setting is available at the agent level and helps you tailor the experience based on your domain needs. Reasoning traces remain visible in the Agent Builder preview for debugging. For more information, see Using agents in Orchestrate Chat.

Restrict editing agents from the catalog

Partners can now publish agents in non editable mode. You can configure and deploy these agents based on your use case, without modifying their core setup or logic. This update helps maintain the integrity of partner native agents while still allowing you to adjust supported properties like connections and deployment settings. For more information, see partner native agents.

Use watsonx Orchestrate in multiple languages

watsonx Orchestrate now supports French (Canadian), German, Spanish, Portuguese, and Italian. With this update, you can:

• Use the full UI in your preferred language.

• See localized welcome messages, notifications, and subtext.

• You can input and receive responses in your chosen language.

This enhancement improves accessibility and usability for global teams.

Enhance forms with new input types and customization

You can now:

• Add a File upload field to collect documents or images.

• Edit column labels in Multi choice and Single choice fields.

• Use the Field option to display static information during a chat.

These enhancements help you build more dynamic and user-friendly forms. For more information, see Forms in user activities.

Use chat session context as input to improve agentic workflows

You can now use chat session context to enhance agentic workflows.

• Automatically map the last 5 conversation turns to form fields.

• If mapping fails, prompt the user for input in the chat.

These features reduce repetitive input, improve responsiveness, and help you build smarter, context-aware workflows. For more information, see Using the chat session context as input.

Extract semantic key-value pairs from documents

You can now configure a text extractor in an agentic workflow to extract semantic key-value pairs (KVP) from documents. This enhancement helps you extract structured data even when document formats and layouts vary. For more information, see Extracting semantic key-value pairs (KVP) from documents.

Handle interruptions in voice conversations by using VAD settings

You can now define how your Voice agent responds to user interruptions. Voice Activity Detection (VAD) setting help optimize the responsiveness and accuracy of speech recognition by identifying active voice segments and ignoring silence or background noise. It helps reduce latency and improves the user experience in voice-driven workflows. For more instructions, see Configuring voice settings for agents.

Configure ElevenLabs TTS for natural voice output

You can now configure ElevenLabs as a text-to-speech (TTS) provider in an Agent Builder to create voice agents with natural, human-like speech. Add your own API key, choose voice settings like speed and stability, and preview voices before you apply them. For more instructions, see Configuring voice settings for agents.

Support for Genesys Audio Connector integration

You can now connect your agents to the phone by using Genesys Audio Connector, enabling them to handle voice interactions with greater reliability and clarity. For more information, see Connecting to Phone with Genesys Audio Connector.

Support voice interactions through SIP

IBM Cloud

You can now enable agents to manage voice interactions by using SIP in the IBM Cloud US-South region, allowing users to connect and communicate with agents through phone calls.

Newly added prebuilt agents and tools

IBM watsonx Orchestrate introduces new prebuilt agents and tools to expand automation across key business domains.

For the complete list of available prebuilt agents and tools, see List of prebuilt agents.

IBM® watsonx Orchestrate® API updates

See the updates in the IBM watsonx Orchestrate API for this release.

Other enhancements and changes

The following table lists the enhancements available in the current release corresponding to the user role:

Documentation updates

See the updates in the watsonx Orchestrate documentation and other contents for this release.

New sections

• The Licenses and entitlements on Groq section describes how Groq powers IBM watsonx Orchestrate and outlines deployment options and licensing requirements.

• The Connecting to SMS with Twilio section shows how to enable SMS for agents by using Twilio to improve customer engagement and workflow automation.

• The Using Tiny Milvus in IBM watsonx Orchestrate On-premises section explains how to use Tiny Milvus for knowledge search in on-premises deployments.

• The Auditing logs section helps you understand how to track activity and monitor agent behavior by using audit logs.

• The Enabling external logging for AWS section describes how to set up Amazon S3 and CloudWatch to store and view audit and debug logs for agent workflows.

• The Updating your Milvus authentication credentials section explains how to update your Milvus username and connection settings to maintain access to knowledge sources.

• The Connecting to IBM TargetProcess section shows how to enable the integration with watsonx Orchestrate.

Updated sections

• The Partner native agents section was updated to add information about the noneditable agents.

• The Known issues and limitations topic now has the following entry:

Prebuilt apps and skills

• IBM Document Processing skills

Accelerate your enterprise AI deployment with IBM and Groq

You can now accelerate your automation with Groq for IBM watsonx Orchestrate, a new, high-speed, single-tenant AI platform powered by Groq’s Language Processing Units (LPUs). This partnership brings you faster agentic AI capabilities, so you can take immediate action on complex workflows. You can access Groq through your existing watsonx Orchestrate Standard, Premium, or on-premises deployment.

For more information, see Licenses and entitlements on Groq for IBM watsonx Orchestrate.

Support for data isolation in document processing tools

IBM Cloud

Data isolation is now supported in the text extractor, document classifier, and document extractor tools. Data isolation lets you keep your data separate from others and manage the data independently. For more information, see Data isolation on watsonx Orchestrate.

Enhanced error handling for tool and generative prompt nodes in agentic workflows

You can now manage how your tool and generative prompt nodes respond to failures.

• Customize the error message that users see when a node fails.

• Turn on Retry on error to automatically recover from common issues such as timeouts, throttling, or server errors (408, 429, 500, 502, 503).

• Set the number of retries, from 1 to 5 and the wait time between retries, from 1000 to 60000 ms.

These updates help improve reliability and user experience across agentic workflows. For more information, see Error handling for tools and Error handling for generative prompts.

New prebuilt and partner agents available in the catalog

Other enhancements and changes

The following table lists the enhancements available in the current release corresponding to the user role:

The following table details the fixes that are delivered in the current release corresponding to the user role:

Documentation updates

See the updates in the watsonx Orchestrate documentation and other contents for this release.

New sections

• The Partner agents section introduces external partner agents and partner native agents.

• The Filtering catalog agents by application section describes how to filter catalog agents based on application.

• The Add bot schema to Genesys bot list section explains how to add a bot schema to the Genesys bot list.

• The Understanding billing and usage tracking section outlines the details of billing and usage tracking.

Updated sections

• The Using agents in Orchestrate Chat section was updated to remove the outdated information.

• The table of content of the documentation was reorganized to improve visibility and navigation.

• The Discovering the catalog section was updated to improve procedural accuracy and add details about the new filter option based on applications.

Test your draft agents - Preview

Preview

You can test your draft agent’s behavior with real-world prompts before going live. This preview feature in the watsonx Orchestrate interface supports bulk testing with .csv files, targeted test cases, and full test suites.

You can review pass or fail results and key metrics such as relevance and correctness to validate agent quality and catch errors early.

Connect agents to phone with SIP trunk - Preview

You can connect agents to phone by using a SIP trunk (Session Initiation Protocol) to enable scalable and cost-effective voice communication. SIP routes calls over IP networks, reduces infrastructure costs, improves call quality, and simplifies management.

By using this feature, you can:

• Configure SIP connection details, including SIP URI and tenant ID.

• Extract custom SIP headers into the agent context for personalized call handling.

• Add phone numbers manually or by using CSV upload.

• Secure calls with SRTP encryption and SIP authentication.

• Enable ring tone settings for seamless caller experience.

For details, see Connecting to Phone with SIP trunk.

Use partner-built native agents as collaborators

You can now use partner-built native agents as managers and collaborators directly from the catalog. These agents are developed by third-party partners using the Agent Development Kit (ADK) and hosted within the watsonx Orchestrate platform. Each agent profile includes detailed information about its purpose, publisher, supported languages, and configuration details, making it easier to identify collaborators and integrate them into your workflows.

For detailed instructions, see Discovering partner native agents.

Customize welcome message and starter prompts in chat

Customize the welcome message and starter prompts that appear when users open an agent in Orchestrate Chat. Add a branded greeting and clickable suggestions to guide users, improve onboarding, and encourage quick actions.

For more details, see Customizing the starter prompts.

Add rules to guide agent behavior

Add context-aware rules in IBM watsonx Orchestrate to control how your agent responds in specific situations. You can set conditions, trigger actions, assign tools, and update or remove rules anytime. Use these guidelines to make your agents smarter, safer, and more responsive. For more information, see Adding guidelines to agents.

Integrate with Astra DB for agent knowledge

You can now connect to an Astra DB content repository to enable high-performance vector and hybrid search in your agent workflows. Configure embedding and search modes, map fields to agent responses, and apply advanced filters to improve retrieval accuracy for structured and unstructured data.

For more information, see Connecting to an Astra DB content repository.

Build smarter agentic workflows with new capabilities

Flows are now referred to as Agentic workflows across the platform.

You have more ways to automate, organize, and reuse logic in your agentic workflows with the latest updates:

Configure human review in document classifiers and document extractors within agentic workflows

You can now configure a human review for document classifiers and document extractors.

• For document classification, documents that are classified as Other automatically trigger a human review. Only the user who initiated the workflow can perform the review.

• For document extraction, you can set an extraction confidence threshold for all fields or specific fields to trigger a human review.

For more information, see Adding document classifiers and Adding document extractors.

Interrupt Voice AI agents naturally during responses

You can now interrupt Voice AI agents in real time, making conversations feel more natural and responsive. This update lets you redirect, clarify, or stop an agent's response without waiting for it to finish speaking. The agent detects meaningful interruptions and stops speaking within 200 milliseconds, improving the overall interaction.

New prebuilt agents and tools are now available

IBM watsonx Orchestrate introduces new prebuilt agents and tools to expand automation across key business domains.

Other enhancements and changes

The following table lists the enhancements available in the current release corresponding to the user role:

Documentation updates

See the updates in the watsonx Orchestrate documentation and other contents for this release.

New sections

• The Connecting to Dropbox section shows the procedure to integrate Dropbox with watsonx Orchestrate.

• The Connecting to Sterling Order Management System section shows how to enable the integration with watsonx Orchestrate.

• The Connecting to IBM Cloud Object Storage section shows the steps to connect IBM Cloud Object Storage.

• The Connecting to Phone with SIP trunk section explains how to configure SIP trunking for phone connectivity.

• The Connecting to an Astra DB content repository section shows how to connect Astra DB for high-performance vector and hybrid search.

Updated sections

• The Feature parity for IBM watsonx Orchestrate section was updated to reflect the latest platform capabilities.

• The Adding knowledge to agents section was updated to show how to configure Dynamic mode to use retrieved content flexibly for generating responses or completing tasks.

• The Deploying the agent section was updated to add information about the number of tools displayed per page.

• The Comparative overview of skill-based and agentic experiences section was updated to include more details about the different use cases for skill-based and agentic experiences.

• The Known issues and limitations topic now has the following entry:

Connections

• Changing auth type for live connections

Agents

• Evaluation thresholds in metrics reports

• Agent evaluation duration

Rebind tools without reimporting

You can now rebind an imported tool to a different connection directly without needing to re-create the tool.

• Edit tool configuration:

Access the configuration of any imported tool and select a new connection.

• Filter operations by authentication type:

During import, use the Filter by Auth type option to view operations grouped by authentication method, such as Bearer Token, API Key, Basic Auth, No Auth, and Key Value Pair.

• View environment compatibility and configuration status:

  • If your draft and live environments use different authentication types, a note appears to help you manage the transition.

  • When the connection configuration is pending in the live environment, a configuration pending icon appears with a tooltip to indicate incomplete setup.

• Select from valid connections: When rebinding, the app dropdown shows only those connections that match the tool’s authentication type and security schema.

This enhancement reduces rework, prevents broken flows, and supports seamless environment transitions.

Use carousel rich responses in agent chat

You can now use carousel rich responses in agent chat in AI assistant builder. A carousel displays multiple cards side by side in a scrollable format, giving your users a more interactive and visually engaging experience.

Benefits

• Present multiple options, items, or steps in a compact layout.

• Let users swipe through cards and select what they need quickly.

• Make your chat clearer and streamline workflows.

For more information on how to enable rich responses, see Enabling rich responses from AI assistant builder.

Take a final look before you deploy your agent

You now receive a detailed pre-deployment summary before deploying your agent.

Use the summary to:

• Review your deployment: See your agent’s profile, knowledge, tools, collaborators, and behavior in one place.

• Check connection details: View connection name, authentication type (member or team), server, and connection status for the live environment.

• Spot mismatches early: Get alerts if a tool’s authentication type doesn’t match the live connection setup.

• Get warnings: If your agent is missing instructions or knowledge descriptions, you see a warning but you can still deploy.

• See last deployment time: Know exactly when your agent was last successfully deployed.

• Undeploy when needed: Remove your agent from an environment without deleting it.

This feature gives you more control, visibility, and confidence every time you deploy. For more information, see Pre-deployment summary configuration.

New prebuilt agents and tools are now available

IBM watsonx Orchestrate introduces new prebuilt agents and tools to expand automation across key business domains.

Other enhancements and changes

The following table lists the enhancements available in the current release corresponding to the user role:

The following table details the fixes that are delivered in the current release corresponding to the user role:

Documentation updates

See the updates in the watsonx Orchestrate documentation and other contents for this release.

New sections

• The Preparing to build AI agents section outlines the multi-phase approach to designing, building, and governing agents in watsonx Orchestrate.

• The Introduction to AI agents in IBM watsonx Orchestrate section explains how agents interpret language, automate workflows, and operate autonomously across enterprise systems.

• The Understanding the core components of an AI agent section explains the core components that enable intelligent, autonomous behavior in watsonx Orchestrate agents.

• The Pre-deployment summary configuration gives you detailed information about the deployment summary in the Agent Builder.

• The Designing high-performance AI agents structured approach to design high-performance agents with clarity and purpose.

• The Considerations for choosing a foundation model section help you evaluate model types, balance performance tradeoffs, and select the right foundation model for your watsonx Orchestrate agent.

Updated sections

• The Selecting your model was updated to add more clarity to the content.

• The Choosing a style for your agent now includes information about the factors to consider when choosing a style for your agent.

• The Adding knowledge to agents section was updated to include the recommendations for writing effective descriptions.

• The Comparative overview of skill-based and agentic experiences section was updated to provide a comparative overview of skill-based and agentic experiences.

• The Known issues and limitations topic now has the following entry:

Agents

• Token refresh failure

Models

• Gemini tool invocation

• Gemini-2.0-flash usage

Tools

• Duplicate properties in the input schema

Managing credentials in the watsonx Orchestrate interface

To integrate external applications with watsonx Orchestrate, you need to provide credentials. These credentials authorize watsonx Orchestrate to use the selected authentication method and establish secure communication with the external application.

Configuring SSO connection in the watsonx Orchestrate interface

You can now configure single sign-on (SSO) for your connections directly within the watsonx Orchestrate platform interface.

With the SSO connection, users can access multiple applications with a single set of login credentials, improving security and simplifying the login experience. To know how to configure SSO, see Single Sign-On support for applications.

Flow builder updates

This release brings a wealth of important updates and enhancements to the flow builder. From new features to improved usability, you find a lot to explore that empowers builders to create and manage flows more efficiently.

Using Slack as a communication channel

Enable Slack as a communication channel by integrating a Slack app. This integration allows user interactions to flow through Slack, streamlining workflows and enhancing collaboration.

For more information, see Integrate Slack as a communication channel.

Support for Japanese language

Starting with the 29 August release, administrators can configure the Japanese language for their tenants in the agentic experience. With this language supported in the platform, users are able to select Japanese from the menu options in the upper right corner. See the configuration in Set the platform languages.

Accessing embed chat script in Channels

The script for embedding the agent into chats on other platforms is now available in the Channels section of the Agent Builder.

You can customize embedded web chats to design a distinctive and engaging chat interface that aligns with your brand and enhances the user experience on your webpage.

For more information, see Using an agent in embedded chat.

Skill-based experience updates

Deprecated skills: Extraction and Document Classification skills are scheduled for retirement in October 2025.

New prebuilt agents and tools are now available

IBM watsonx Orchestrate introduces new prebuilt agents and tools to expand automation across key business domains.

Other enhancements and changes

The following table lists the enhancements available in the current release corresponding to the user role:

The following table details the fixes that are delivered in the current release corresponding to the user role:

Documentation updates

See the updates in the watsonx Orchestrate documentation and other contents for this release.

New sections

• The Connecting to Oracle Fusion section shows the procedure to integrate Oracle Fusion with watsonx Orchestrate.

• The Connecting to Gmail section shows how to enable the integration with watsonx Orchestrate.

• The Connecting to Slack section shows the configuration to integrate the Slack as a communication channel.

• The Add code blocks is a new section that you find under Code blocks. In this new content, you learn to create code blocks with custom logic in flows.

• The Creating flows section is rearranged with a new page that is dedicated to Add user activities.

• The new section Managing settings is dedicated to content about data retention, API generation, language, and credentials.

Updated sections

• The Explore the documentation section has new links for features such as Monitoring agent analysis, Managing connections, and Securing your instance.

• The Connecting to Workday HCM OAuth2 procedure is now part of the Workday HCM connection page.

• The What to include in an agent description section has a new description for Agent Instruction Design.

• The Known issues and limitations topic now has the following entry:

Agentic experience

• LLM hallucination and incorrect agent routing

• Repeated tool calls with Llama-3-405b-instruct

• Running tool with Gemini model

• Japanese language support

• Version conflicts with the requests library

Adding partner external agents as collaborator agents

External agents that are built by trusted partners are now available in the watsonx Orchestrate catalog. You can add these agents as collaborator agents to work alongside your native agents in chat.

After connecting the agent, by providing required details such as an API key or agent ID, it becomes available in your local instance and can be reused across multiple agents without reconfiguration.

This feature expands the range of automation capabilities and simplifies integrating third-party agents, offering greater flexibility and functionality for your workflows.

In the following video, you can see an external agent being added from the catalog.

Note: This video has no narration.

For more information, see Using partner external agents as collaborators.

Support for Oauth2 Password authentication

You can now configure connections by using the Oauth2 Password grant type when integrating external applications with watsonx Orchestrate.

Oauth2 Password, or Resource Owner Password Credentials, allows the application to directly exchange a user's username and password for an access token. This method is suitable for security, trusted environments where the application manages credentials internally.

Key benefits:

• Connect to systems like ServiceNow and Salesforce that require this authentication model.

• Automate secure workflows without relying on browser-based or interactive login flows.

For configuration details, see Authentication types.

Enabling file upload and download in User activity

You can now add File upload and File download interactions to the User activity node in your flows. These interactions allow users share or receive files directly in the chat, supporting seamless, document-driven workflows like submitting forms, uploading receipts, or receiving reports.

For more information, see User activity.

Support for multilingual content in knowledge

You can now connect your agent’s knowledge to external content repositories such as Milvus, Elasticsearch, or custom repositories, that contain content in Spanish, French, German, and Brazilian Portuguese.

This enhancement enables your agents to retrieve and respond by using multilingual content, expanding support beyond English to build specific experiences for users across different regions.

Customizing the “No answer found” message in knowledge settings

You can now configure a custom “No answer found” message in the knowledge settings.

The agent shows this message when it cannot retrieve a relevant response from the connected content. Use it to guide users on what to do next, maintain a consistent tone, or provide helpful suggestions, improving the user experience when knowledge has no matching answer. Learn more about Customizing knowledge settings.

New prebuilt agents and tools are now available

IBM watsonx Orchestrate introduces new prebuilt agents and tools to expand automation across key business domains.

Other enhancements and changes

The following table lists the enhancements available in the current release corresponding to the user role:

The following table details the fixes that are delivered in the current release corresponding to the user role:

IBM watsonx Orchestrate API updates

Know the two endpoints added to watsonx Orchestrate API for flows:

• /v1/orchestrate/flows/{flow_id}/run/async

• /v1/orchestrate/flows/

For more information, see the IBM watsonx Orchestrate API documentation.

Documentation updates

See the updates in the watsonx Orchestrate documentation and other contents for this release.

New sections

• The Connecting to SAP S/4HANA section provides connection details for integrating with SAP S/4HANA.

• The Managing users on the skill-based experience section describes how to manage members in the skill-based experience.

• The Discovering external agents from partners section gives detailed information about external agents available in the catalog.

• The Adding an external agent from catalog section provides instructions on how to add an external agent from catalog as a collaborator agent.

Updated sections

• The Adding knowledge to agents was updated to include information about switching content repositories and configuring knowledge settings.

• The Overview of authentication types was updated to include a note about the callback URL.

• The Adding AI assistants as agents section was updated to include a note stating that assistants added as collaborator agents in watsonx Orchestrate currently support only text-based interactions.

• The documentation was updated to include a note in the skill-based content clarifying that it is not applicable to the agentic experience due to differences in structure, functionality, and user interaction.

Connecting to Milvus using an alias

You can now configure connections to Milvus by using an alias instead of a specific collection name. This enables you to update or replace collections without any downtime or changes to your client configuration.

Aliases help you:

• Avoid downtime when updating collections or indexes

• Maintain consistent behavior during backend changes

For more information, see Using an alias for collection management.

Enhancing chat-based interactions

The User activity feature includes support for chat-based user interactions, allowing you to build more dynamic and conversational flows. By using chat-based interactions, you can:

• Streamline user engagement by keeping all interactions within a single interface

• Help in decision-making and data collection during flows

• Deliver real-time feedback and guidance to users

• Personalize the experience using flow variables to tailor prompts and messages

This enhancement helps you create flows that are faster, clearer, and more user-friendly.

Each user activity can now include one or more chat interactions that are grouped into two categories:

• Collect from users: Use these interaction types to gather information: Boolean choice, Single choice, Date, Number, and Text.

• Display to users: Use these interaction types to present content: Text (Show a message or instruction) and List (Display multiple items in a structured format).

For more information, see User activities.

Connecting to new channels

Preview

You can now connect your agents to communication channels like Facebook Messenger and Genesys Bot Connector, enabling seamless interactions directly from the tools your team already use.

Facebook Messenger: Integrate your agent with Facebook Messenger to engage with one of the world’s most widely used messaging platforms. This integration allows for real-time conversations, making support and engagement more accessible and familiar. Learn how to connect to Facebook Messenger.

Genesys Bot Connector: Connect your agent to the Genesys Bot Connector to deliver rich, interactive experiences. Features like quick replies and cards enhance usability and make conversations more dynamic and intuitive. Learn how to connect to Genesys Bot Connector.

Support for multilingual embedded AI chat

You can now configure and switch the language of the embedded AI chat to deliver a more accessible and localized experience for your users.

By setting language preferences in the embedded script, you can:

• Display the AI chat interface in a specific language which is set as the default language.

• Let users change the AI chat language anytime using a language selector. All static text, system messages, prompts, and timestamps update instantly.

This update ensures a seamless multilingual experience across the entire AI chat interface. For more details, see Setting default language on initial load.

New prebuilt agents and tools are now available

watsonx Orchestrate introduces new prebuilt agents and tools to expand automation across key business domains.

Other enhancements and changes

The following table details the enhancements that are delivered in the current release corresponding to the user role:

The following table details the fixes that are delivered in the current release corresponding to the user role:

Documentation updates

See the updates in the watsonx Orchestrate documentation and other contents for this release.

New sections

• The Using web chat section provides instructions for embedding web chat.

• The Supported languages section provides a list of languages supported by AI chat on IBM watsonx Orchestrate.

• The Use trace data to debug knowledge runtime issues includes detailed information about trace data and how to interpret it.

• The Uploading diagnostics information section outlines how to capture and share diagnostic data to help support teams identify and resolve issues.

• The Connecting to Facebook Messenger explains how to integrate your agent with Facebook Messenger.

• The Connecting to Genesys Bot Connector describes how to connect your agent with the Genesys Bot Connector.

Updated sections

• High availability, business continuity, backups and disaster recovery on IBM Cloud and High availability, business continuity, backups and disaster recovery on AWS now include expanded guidance on what artifacts are backed up or should be proactively backed up, and how to restore them after a disaster recovery event.

• Enabling the user to interact with documents in the Orchestrate Chat now includes more configuration details.

• Capturing user feedback explains how to enable and manage feedback in embedded chat.

• Choosing a foundation model now covers both watsonx.ai and supported third-party models.

• Terminology was updated throughout the documentation to reflect the change from agentic chat to Orchestrate Chat.

• Managing users on AWS was updated to reflect recent UI changes.

• The Known issues and limitations topic now has the following entry:

  • User activities in nested flows

Connecting to live agents from AI agent chat

You can now connect users to a live agent directly from the chat. Use this feature to make sure that users get human support when the automated chat cannot resolve their issue.

Set an integration with a service desk or contact center to enable this feature. You can use:

• Planned escalation for known situations that always need human help.

• Fallback escalation when the chat cannot answer a question or complete a task.

Key benefits:

• Control when and how your chat escalates to live agent.

• Help users to get the answers that they need, when automation is not enough.

For more information on how to set up an integration, see Connecting to a live agent in agentic experience.

Enabling document-based responses for your agent

You can now decide whether your agent uses documents to answer user questions. Use the Chat with documents toggle in the Agent Builder to turn this feature on or off for each agent and help to customize its behavior. You can enable document-based responses only when needed for a specific use case. For more information, see Enabling the user to interact with documents in the chat.

Other enhancements and changes

The following table details the enhancements that are delivered in the current release corresponding to the user role:

The following table details the fixes that are delivered in the current release corresponding to the user role:

Documentation updates

See the updates in the watsonx Orchestrate documentation and other contents for this release.

New sections

• The Connecting to a live agent section gives detailed information on how to connect to a live agent from AI agent chat.

• The Configuring the agent's behavior section provides information on how to configure your agent by giving instructions.

• The Using context variables in agent instructions provide information on how to use context variables in the agent instructions.

Updated sections

• The Storing the data section now includes a note about data storage in the AWS Mumbai region.

• The Uploading files directly to the agent section explains how to upload CSV files by using Excel.

• The Uploading files during a conversation section now includes information about how to enable the upload feature.

• The Connecting to apps provisioned from prebuilt agents or tools section was updated to give detailed information on how you can connect each external application by using watsonx Orchestrate user interface (UI).

• The Add branches section now includes detailed procedure to add a branch to the flow.

• The Known issues and limitations topic now has the following entry:

  • SSO authentication for Workday

  • Flows fail with MCP tools

Connecting to external apps

This release brings a streamlined approach for managing connections to external applications on watsonx Orchestrate, ensuring secure and efficient integration with the tools your team depends on.

Key features include:

• Authentication methods: Establish connections by using various authentication methods, such as API Keys, Basic Auth, Bearer Tokens, Key-Value Tokens, and OAuth2 (Authorization Code & Client Credential). These connections serve as secure bridges, enabling your agents to interact with external systems and services.

• Manage Connections page: From the Manage > Connections page, you can:

  • View all existing connections

  • Add new connections with custom IDs, display names, and authentication settings

  • Filter connections by environment, status, or authentication type

  • Edit connection details for both draft and live environments

  • Environments: Configure connections in both draft and live environments. This setup allows you to test the integrations before deploying them in production.

• Credential types: Choose between member credentials and team credentials to match your app's requirements. Each credential type supports specific parameters based on the selected authentication method.

This update empowers you with greater control, security, and flexibility when integrating external applications, making it easier to extend your agent's capabilities. Refer to Managing connections for more information.

Customizing agent styles

You can now choose the style for your AI agent directly within the Agent Builder UI. This setting determines how your agent understands and responds to user requests, selects appropriate actions, and engages with tools and agents to complete tasks. You can opt for either the default or ReAct style based on your wanted output quality, speed, and task complexity according to your use cases. For more information, see Choosing an agent style.

Adding IBM watsonx Orchestrate assistants as collaborator agents

You can now add assistants from IBM watsonx Orchestrate as collaborator agents directly from the Agent Builder UI. This feature helps you to create domain-specific agents that focus on particular industries or tasks. By enabling your agents to delegate tasks to these assistants, you can take advantage of their structured and deterministic logic. This setup allows you to reuse and repurpose existing assistants more effectively, improving task accuracy, and modularity.

To learn more, see Adding IBM watsonx Orchestrate assistants as collaborator agents.

Monitoring agent performance

Preview

Use the built-in performance monitoring tool in IBM watsonx Orchestrate to track how your agents and tools are working. This feature helps you quickly spot issues and improve how your agents respond to user requests.

Key features include:

All agents at a glance

Get a high-level view of how all your agents are performing:

• Total messages: See how many messages all agents processed, including successful and failed ones.

• Failed messages: Track errors like service connection failures or server issues.

• Latency average: Measure how long, on average, it takes agents to respond.

Individual agent metrics

Drill down into each agent’s activity:

• View the agent’s name, description, number of requests, failed requests, and average latency.

Agent message traces

Understand how each message was handled:

• See the timestamp, trace ID, status, model used, and latency for every message.

Detailed trace view

Public Preview

Investigate specific issues:

• Review detailed error messages to help you fix problems in the agent’s setup or tool connections.

This feature empowers you to quickly detect and fix issues, improve response times, helping ensure agents run smoothly and reliably. For more information, see Agent analytics.

Importing tools from MCP servers

You can now integrate IBM watsonx Orchestrate with Model Context Protocol (MCP) servers, making it easier to import external tools and expand your agents’ capabilities.

MCP is a standard that allows secure and flexible communication between AI agents and external tools or data sources. With this integration, you no longer need to build custom APIs or manage manual configurations saving you time and effort.

After you connect to the servers, you can import tools and add them to your agents directly from the MCP tools list. Use filters to quickly locate the required tools and set the "Added to agent" switch for the tool to "Yes".

Manage MCP connections by editing connection details, removing unused servers, and monitoring all imported tools from the Connections page.

This update allows you to instantly enhance your agents capabilities by sharing tools across platforms. To learn more, see Importing tools from an MCP server.

Uploading files into chat threads for context-aware responses

You can upload documents directly into chat threads, enabling agents to generate responses based on the content of your files.

Supported file formats include .txt, .pdf, .csv, .docx, .xlsx, .pptx, and .htmlx. After you upload a file, the system validates the file and also provide clear error messages for any issues, such as failed loading, exceeded upload limits, or invalid files.

This feature helps ensure your agents respond with precision and context, by using the documents that you provide, making your conversations more productive and informed. For more information on how to upload a file in the chat, see Uploading files during a conversation.

Mapping data in flows

You can now enjoy enhanced data-mapping options that make configuring data flows between nodes easier and more efficient. With automapping, you can achieve seamless transfers effortlessly. If you prefer more control, you can customize parameters by using blank values, Python expressions, variables, literal values, or defaults tailored to your flow's needs.

These improvements give you greater control and precision over node input parameters, ensuring that your flows are exactly how you want them. Learn more about using data mapping in flows by checking out Data mapping.

Adding custom logic with code blocks

You can now use code block nodes to run Python code directly within your flow. These nodes enable you to insert custom logic as Python code, providing flexibility for data transformation, complex logic implementation, or message formatting.

Code block nodes are ideal for scenarios where standard nodes cannot fulfill your data processing, intricate logic, or message formatting requirements. Access flow variables, write Python by using built-in libraries like datetime, math, or JSON, and pass outputs to the next node.

For more information on how to use code blocks to create flows, see Code block examples.

Uploading and downloading documents in tools

You can now upload and download documents when using tools in both AI agent chat (where you interact with a deployed agent to accomplish tasks) and preview chat (for testing your agent during development).

• Upload files into tools that are set up to receive them.

• Download files generated by tools during a session.

Builders can configure these tools by using the watsonx Orchestrate Agent Development Kit (ADK) to support file uploads and downloads. This gives you a smoother experience when working with document-based tools, and allowing builders to control how files are handled.

Selecting a model for your AI agent

You can choose the foundation model for your AI agent directly within the agent builder UI. This feature provides greater control and flexibility in customizing your AI agent's capabilities. To learn more, see Choosing a foundation model.

Connecting to a content repository on a custom service

You can now connect to a content repository on a custom service, allowing you to use your existing custom service instances, whether hosted on the server side or client side. This enhances your capabilities by integrating your search functionality with a server to deliver search results.

This feature provides you with greater flexibility and customization options for integrating your custom services with watsonx Orchestrate, enabling access to and use of content from your preferred repositories.

For more information, see Connecting to a content repository on a custom service.

New prebuilt agents are available

watsonx Orchestrate now offers the following prebuilt agents.

Procurement

• Sourcing and contracts (Coupa)

• Supplier management (SAP Ariba)

• Invoice management (Coupa)

• Catalog search and supplier search (Coupa)

HR

• Learning and development (Oracle HCM)

Productivity

• Issue and bug tracking (Jira)

• Project and resource management (Adobe Workfront)

• Storage and collaborate file (Google Drive)

• Communication and messaging management (Slack)

• Account information (Salesforce)

For more information on the newly introduced prebuilt agents, see List of prebuilt agents.

Preview - Connecting to channels

Preview

You can now connect your agents to communication channels such as WhatsApp (through Twilio) and Microsoft Teams, making it easier for your team to interact with agents directly from the tools they already use.

For more information, see Connecting to channels.

Preview - Configuring voice

Preview

You can now enable voice interactions, allowing for verbal communication with users. On watsonx Orchestrate, you can configure voices that are powered by IBM Watson Speech to Text and Text to Speech services.

Key benefits include:

• Creating voice configurations

• Managing voice configurations

• Enabling voice modality

With this feature, you can create more dynamic and human-like interactions, making your agents more engaging and accessible. For more information, see Configuring a voice (Preview).

Other enhancements and changes

The following table details the enhancements that are delivered in the current release corresponding to the user role:

IBM® watsonx Orchestrate® API updates

See the updates in the IBM watsonx Orchestrate API for this release.

Documentation updates

See the updates in the watsonx Orchestrate documentation and other contents for this release.

New sections

• The Connecting to Microsoft Teams and Connecting to WhatsApp with Twilio sections was added to provide detailed steps on how to connect to the respective apps.

• The Evaluating an agents performance section explains how to use the performance monitoring tool to track message volume, latency, and failure rates.

• The Configuring a voice (Preview) section describes how to set up voice capabilities for agents by using IBM Watson Speech services.

• The Managing connections section details how to create and manage secure connections between external applications and watsonx Orchestrate.

• The Connecting to a custom service repository section was added to provide details on how to connect an agent to a custom service repository.

• The Importing tools from an MCP server were added give detailed information about how to connect to MCP servers and import external tools into your agent.

• The Choosing an agent style section provides information about agent styles, and how to set up agent style for your agent.

• The Agent creation specifications section gives you a high-level understanding of the fundamental components that form an AI agent.

• The Adding external A2A agents using ADK section provides information about adding external A2A agents as collaborators.

• The Connecting to apps section provides detailed information about how to connect to each application using the UI.

Updated sections

• The Known issues and limitations content was restructured to separate known issues for skill-based and agentic experiences.

• The Technology preview label was removed from features that are now generally available in this release.

• The Known issues and limitations topic now has the following entry:

  • Importing watsonx Assistants

  • Document upload fails

  • Repetitive responses by model Llama 3.2 70B Instruct

  • Llama 3.2 70B Instruct model context length

  • Chat with documents is not supported in voice (Preview)

  • Embedded chat disappears

New data center available on AWS

AWS

The AWS data center is now expanded to include the following region:

Mumbai

IBM watsonx Orchestrate data center now expands to Mumbai, enhancing global accessibility, performance, and adherence to local data sovereignty regulations. This expansion guarantees a scalable and dependable infrastructure, customized to cater to the specific requirements of users, while fostering business growth and providing an exceptional user experience throughout the region.

For more information, see Outbound IP addresses.

Support for new plans on IBM Cloud

Introducing the Premium plan

IBM watsonx Orchestrate introduced the Premium plan, by complementing the Essentials and Standard plans. This plan is designed for enterprises and requires advanced features and higher resource allocations. See what you get with the Premium plan:

• 1 million skill runs per month

• 50,000 monthly active users (MAUs)

• Data isolation capabilities: The data isolation feature allows organizations to create virtual data boundaries within a multi-tenant environment, ensuring enhanced data security and compliance.

• Also, you get everything included in the Standard plan, which includes automations for workflows, AI decisions, document processing, and access to Skill Studio and Agent Builder.

For more information, see IBM watsonx Orchestrate on IBM Cloud Premium.

New plans for the agentic experience

IBM watsonx Orchestrate is introducing 6 new plans by allowing customers to fully use the agentic experience. This includes:

• IBM watsonx Orchestrate on IBM Cloud Essentials Agentic monthly active users

• IBM watsonx Orchestrate on IBM Cloud Standard Agentic monthly active users

• IBM watsonx Orchestrate on IBM Cloud Premium Agentic monthly active users

• IBM watsonx Orchestrate on IBM Cloud Essentials Agentic Messages

• IBM watsonx Orchestrate on IBM Cloud Standard Agentic Messages

• IBM watsonx Orchestrate on IBM Cloud Premium Agentic Messages

• IBM watsonx Orchestrate on IBM Cloud Trial

These plans depend on two usage models:

Agentic Monthly Active Users (MAUs): Tracks the number of unique monthly active users interacting with the AI agents.

Agentic Messages: Measures the volume of messages exchanged with AI agent.

Each agentic plan also includes access to the Agent builder that provides a low-code, self-service experience to build AI assistants and custom agents. These options allow you to choose the best one that suits your business needs.

For more information, see Licenses and entitlements for watsonx Orchestrate on IBM Cloud.

Customizing with Add-on options

To further customize your experience, watsonx Orchestrate on IBM Cloud offers additional services:

• IBM watsonx Orchestrate on IBM Cloud Add-on Skill Runs

• IBM watsonx Orchestrate on IBM Cloud Add-on monthly active users

• IBM watsonx Orchestrate on IBM Cloud Class Inference

• IBM watsonx Orchestrate Add-on Voice monthly active users

• IBM watsonx Orchestrate Add-on Voice Minutes

• IBM watsonx Orchestrate Add-on Messages

• IBM watsonx Orchestrate Add-on Documents

• IBM watsonx Orchestrate Add-on Domain Agents

• Non-IBM products Add-on Domain Agents

For a detailed comparison of the new plans and to determine which edition best suits your organization's needs, see Licenses and entitlements for watsonx Orchestrate on IBM Cloud.

Data isolation for enhanced security

watsonx Orchestrate on IBM Cloud now supports data isolation, a key feature for organizations with strict security and compliance requirements, including HIPAA.

With data isolation, each customer gets a dedicated data storage instance, ensuring their information is fully separated from other tenants. This feature helps protect sensitive data and gives you greater control over access and usage.

Data isolation is available with the Premium plan on IBM Cloud.

This enhancement strengthens data security and helps your businesses meet regulatory standards. For more information, see Data isolation on IBM watsonx Orchestrate.

Other enhancements and changes

The following table details the fixes that are delivered in the current release corresponding to the user role:

Documentation updates

See the updates in the watsonx Orchestrate documentation and other contents for this release.

New sections

• The Data isolation on IBM watsonx Orchestrate section explains how watsonx Orchestrate isolates data on IBM Cloud.

Capturing user feedback

I Technology preview

You can now provide feedback on agent responses by using Like and Dislike buttons. This new feature makes it easier to evaluate and enhance agent performance based on real user input. The builder can view feedbacks that were submitted by users and use the feedback to gather insights and continuously improve the agent experience. This feature includes:

• Like or Dislike buttons to let users quickly rate responses.

• Options to select feedback reasons and add optional comments.

Feedback is stored with each message, including the selected reasons and an extra description, when it is provided. For more information, see Capturing user feedback.

Support for agentic plans on AWS

IBM has introduced a new tiered structure for watsonx Orchestrate on AWS, comprising three distinct editions:

IBM watsonx Orchestrate Agentic Essential:

Designed for small teams or those starting with AI automation. You get 600 Resource Units (RUs) and support for up to 40,000 Monthly Active Users (MAUs). It includes access to Skill Studio, where you can build and deploy AI-powered workflows, decision services, and document processing.

IBM watsonx Orchestrate Agentic Standard:

Suitable for growing businesses, with this plan you get 6,000 RUs per month. It includes everything in Agentic Essentials, and more capacity to scale your digital workforce.

IBM watsonx Orchestrate Agentic Premium:

Tailored for enterprises requiring advanced capabilities and higher resource allocations. This plan provides you with 7,500 RUs monthly, and everything in Agentic Standard plan.

This expansion provides businesses with more tailored options to match their specific requirements.

Customizing with Add-on options

To further customize your experience, subscribe to optional add-ons, which includes:

IBM watsonx Orchestrate Add-on Documents:

It is an optional subscription for Essentials, Standard and Premium editions that provides additional document entitlements in packs of 1,000.

IBM watsonx Orchestrate Add-on Domain Agents:

It is an optional subscription for Essentials, Standard and Premium editions that provides you with prebuilt, ready to use domain agents.

These add-ons provide the flexibility to scale and adapt the platform to your business needs.

The introduction of the Premium plan and the enhanced resource allocations ensure a seamless provisioning and a consistent functionality across all components, allowing customers to fully use the agentic experience. For a detailed comparison of the new plans and to determine which edition best suits your organization's needs, visit the Licenses and entitlements for watsonx Orchestrate on Amazon Web Services.

IBM® watsonx Orchestrate® API updates

See the updates in the IBM watsonx Orchestrate API for this release.

Capturing user feedback API

You can now provide feedback on agent responses by using "Like" and "Dislike" icons. The parameter message_state stores the feedback details for a specific message in the thread. For more information, see Update a message.

Other enhancements and changes

The following table details the fixes that are delivered in the current release corresponding to the user role:

Documentation updates

See the updates in the watsonx Orchestrate documentation and other contents for this release.

New sections

• The Capturing user feedback ratings section was added to provide detailed information on the feedback collection for agent responses in chat.

Updated sections

• The On-premises offering section was updated to add information about how to use different endpoint URLs depending on the resource, which include methods from the IBM watsonx Orchestrate API and AI assistant builder API.

• The Licenses and entitlements for watsonx Orchestrate section is updated to include the new agentic plans available on AWS.

• The Known issues and limitations topic now has the following entry:

  • An error while running tools

Building flows from Agent builder

Technology preview

You can now create flows from the Agent builder. These flows help you to design agents to complete tasks.

Creating flows from the Agent builder enables you to visually connect tools and define logic in the Tool builder screen. You can add tools, set conditional branches with Python expressions, and define inputs and outputs without writing any code.

It is a faster and more intuitive way to create tools for agents, which adds more flexibility to the way the agents work. For detailed steps to create flows, see Creating flows.

Prebuilt agents for team messaging and collaboration

Technology preview

IBM watsonx Orchestrate now includes a new set of prebuilt agents designed to streamline communication and collaboration in Microsoft Teams.

The Team Messaging and collaboration is the manager agent, which intelligently routes your requests to the most relevant supporting agents. These agents handle a wide range of Microsoft Teams tasks, which helps to automate everyday collaboration activities. To learn more, see Productivity agents

Connecting prebuilt agents to third-party apps

Technology preview

You can connect prebuilt agents to external applications using CLI commands from the Agent Development Kit. This integration process makes it easier to establish interactions between agents and third-party applications.

After you configure the connection, the agents can perform their tasks more efficiently, as they can leverage the functionalities of the external applications directly. For more information on how to connect prebuilt agents to SAP Successfactors and Workday, see Connecting to apps.

Using document classifiers in Skill studio (Beta)

You can now use an AI-powered document classifier to identify specific document types, such as invoices or contracts, and automatically classify uploaded documents. For more information, see Creating document classifiers.

Language support for document extractors in Skill studio

You can now set the language of documents when configuring a document extractor. Available options are English, French, or English with handwriting.

The English with handwriting allows you to extract a mix of typed text and handwritten text from your documents in English. This feature helps you efficiently process documents that require manual input, such as insurance policies or purchase orders.

Agent name and Avatar now visible in chat

You can now see the agent's name and avatar when using AI agent chat, preview, or embedded chat. This update makes it easier to identify the agent you are interacting with, ensuring a more personalized experience, even when switching between agents.

Other enhancements and changes

The following table details the fixes that are delivered in the current release corresponding to the user role:

Documentation updates

See the updates in the watsonx Orchestrate documentation and other contents for this release.

New sections

• The Team messaging and collaboration agent and its associated agents are added to the productivity agents list.

• The Getting started with the watsonx Orchestrate section provides detailed information on how to start using agents on watsonx Orchestrate.

Updated section

• The documentation topics were updated to emphasize the agentic experience.

• The Monitoring skills and Prebuilt charts section now include a deprecated label.

• The Switching from agentic experience to skills experience content is updated to rearrange the steps for switching to the skill based experience.

• The Known issues and limitations topic now has the following entry:

  • Authentication on watsonx Orchestrate API with IP address restriction

  • Enhancing an existing skill

Single sign-on for skills authentication

IBM watsonx Orchestrate introduces Single Sign-On (SSO) to enhance user authentication within the embedded chat experience. With SSO, users can seamlessly interact with third-party applications without needing to log in repeatedly.

Admins and builders can now configure SSO by integrating their applications with an Identity Provider (IdP), such as Microsoft Entra ID. After the SSO is configured, users can access applications effortlessly through embedded chat.

This update simplifies the authentication process, improves security, and enhances the user experience. For more information, see Single sign-on authentication for apps.

Other enhancements and changes

The following table details the enhancements that are delivered in the current release corresponding to the user role:

The following table details the fixes that are delivered in the current release corresponding to the user role:

IBM® watsonx Orchestrate® API updates

See the updates in the IBM watsonx Orchestrate API for this release.

API for agent based chat experience

Technology preview

The Agent Chat API (Technology preview) is introduced for the new experience of IBM watsonx Orchestrate. This API enables interactions with an agent-based chat system, allowing you to send messages, receive responses, and manage chat sessions seamlessly.

New sections

• Generating an IAM Access Token by using an API key section is added to provide information on how to generate an IBM Cloud Identity and Access Management (IAM) token by using your IAM API key.

Documentation updates

See the updates in the watsonx Orchestrate documentation and other contents for this release.

New sections

• The Single sign-on authentication for apps section provides detailed instructions on how builders configure SSO authentication for third-party applications.

• The Storing the data section explains where files and documents that are uploaded as Knowledge in the Agent builder are stored.

• The Configuring custom filters for Elasticsearch section guides users on using custom filters as an advanced setting in their agents.

• The Configuring query body for Elasticsearch section explains how to structure a query body for complex searches that require combining multiple search criteria.

Updated section

• The Authenticating users in the AI chat section was updated to add details about the format in which the user ID obtained from the subject claim is stored.

• The Activity tracking events for IBM watsonx Orchestrate on IBM Cloud section was updated to include events for tenants, threads, messages, tools, orchestrate runs, external chat agents, and connections.

• Removed the user role labels from the documentation.

• The Apps and skills availability per managed instances page was updated with the latest list of available apps for each deployment.

• The Supported foundation models section was updated to remove withdrawn foundation models.

• The Supported languages and [Configuring and changing the platform languages].\(../../chat/platform_languages.md) were updated to add a note to specify that the settings for changing the platform language are available only in the agentic experience.

• The Known issues and limitations topic now has the following entry:

  • Inconsistent transfer between multi-agent collaborators

Unlocking business productivity with AI agents and agent builder

Technology preview For builder or Writer For admin or Manager

IBM watsonx Orchestrate unveils AI agents, a feature that lets you build and manage agents tailored to your business needs. This feature is available in technology preview for a limited set of customers.

AI agents are processes that perform actions on behalf of users, either on a regular schedule or without user intervention. Powered by large language models (LLMs), these agents can operate with minimal supervision, handling tasks ranging from simple actions to complex multistep processes.

In IBM watsonx Orchestrate, agents can:

• Use tools to accomplish complex tasks, integrating with other systems

• Collaborate with other agents and tools to extend the agent capabilities and automate tasks.

• Take advantage of contextual knowledge grounded on your business needs

• Follow defined behavior tailored to your quality standards

Building agents by using IBM watsonx Orchestrate ADK

Builder or Writer

Agent development kit (ADK) is now available for IBM watsonx Orchestrate. The ADK enables you to build, deploy, and integrate agents within watsonx Orchestrate. You can use watsonx Orchestrate ADK to integrate with other agent frameworks, build tools and for multi-agent collaboration.

Key highlights:

• Agents creation: The ADK provides a Python library and command line tools to develop agents. With the ADK, you can import, create, remove, and list agents.

• Tools integration: Easily integrate existing tools or create new ones to enhance your agent capabilities.

• Cross-framework integration: The ADK supports integrating agents and tools built on other frameworks.

To explore how to create and customize agents and tools, and to learn more about the full capabilities of the ADK, refer to IBM watsonx Orchestrate ADK documentation.

Explore IBM watsonx Orchestrate with a 30-day trial on IBM Cloud

You can now try watsonx Orchestrate with a 30-day free trial on IBM Cloud. During the trial period, you get access to all the features available in the Standard plan.

For more information on how to initiate the trial access, see Trial access on IBM Cloud.

New data centers available on IBM Cloud

The IBM Cloud data centers are now expanded to include the following regions:

Sydney

IBM watsonx Orchestrate data center now expands to Sydney. With this new data center, watsonx Orchestrate offers secure and compliant data storage solutions for Australian users.

For more information, see Outbound IP addresses.

Tokyo

IBM watsonx Orchestrate data center now expands to Tokyo. With this new data center, watsonx Orchestrate offers secure and compliant data storage solutions for users in Japan.

For more information, see Outbound IP addresses.

Secure connectivity with TLS tunnel

You can now create a secure connection between IBM watsonx Orchestrate on IBM Cloud and your third-party Cloud or on-prem services by using a TLS tunnel. Set it up by using the Satellite connector. After configuring the TLS tunnel, you can use external apps and skills within watsonx Orchestrate and keep your data protected. For more information, see Configuring TLS tunnel.

Usability improvements in document extractors

Builder or Writer

You can optimize your document extractor by selecting the data type when you edit a field. Available data types are string, number and date.

In the document preview, you can also search the document for specific occurrences, for example, when you need to find text to provide as example to the LLM to understand the output. It saves you time especially if you are searching through long documents. For more information, see Creating document extractors.

Inspection of results from conversational search

Builder or Writer

Now you can inspect the results of a conversational search from the search inspector, improving the troubleshooting of potential inaccurate search results. When assistants use conversational search to answer to user prompts, they consider only a subset of the results to generate the response.

Improvements on error messages from conversational search results

User or WO User

Error messages in conversational search now include the following updates:

• Clearer error notifications

When a conversational search fails, the assistant now shows a detailed message explaining the issue.

• Specific error types

Messages indicate whether the problem is a timeout, retrieval error or connection issue with watsonx.ai.

This feature improves transparency, making it easier to quickly understand and resolve search errors.

IBM® watsonx Orchestrate® API updates

Builder or Writer

See the updates in the IBM watsonx Orchestrate API for this release.

Updated sections

• Register an external agent section is updated to include the provider type salesforce. You can now integrate Salesforce agents built in Agentforce with watsonx Orchestrate.

• Register AI Assistant instances API is updated to add descriptions for properties: api_key, crn and authorization_url.

• The IBM watsonx Orchestrate API known issues and limitations topic now has the following entry:

  • Skills and skill sets

    • The Get all scheduled events from Calendly skill does not return any output

Other enhancements and changes

The following table details the enhancements that are delivered in the current release corresponding to the user role:

The following table details the fixes that are delivered in the current release corresponding to the user role:

Documentation updates

See the updates in the watsonx Orchestrate documentation and other contents for this release.

New sections

• Learn about the new experience is added to provide detailed information about the new agentic experience in watsonx Orchestrate. This section contains information about:

  • Discovering the Catalog

  • Prebuilt agents for HR, Procurement, Productivity and Sales

  • Tools reference

  • Building agents with agent builder

• Managing settings in watsonx Orchestrate is added to provide information about all the settings options in one place.

• Connecting watsonx Employee Support agents to Slack section is added to provide the steps on how to connect IBM watsonx Employee Support agents to Slack. This feature enables you to quickly use the capabilities of AI agents built-in for HR use cases right from your Slack workspace.

Updated sections

The Troubleshooting section is now updated to add a solution for "Trouble logging in issue".

• The Known issues and limitations topic now has the following entry:

  • Prebuilt apps and skills

    • Error connecting to a skill

  • watsonx Orchestrate new experience

    • Non-secured embed chat

    • LLM in agents

    • External agents

    • Agent tools

New data centers available on IBM Cloud

The IBM Cloud data center is now expanded to include the following region:

Frankfurt

IBM watsonx Orchestrate data center now expands to Frankfurt. With this new data center, watsonx Orchestrate offers secure and compliant data storage solutions for user data in accordance with European data protection laws.

For more information, see Outbound IP addresses.

New data center available on AWS

Administrator Builder AWS

The AWS data center is now expanded to include the following region:

Singapore

IBM watsonx Orchestrate data center now expands to Singapore. With this new data center, watsonx Orchestrate offers secure and compliant data storage solutions for Asia-Pacific users.

For more information, see Outbound IP addresses.

Use agents from watsonx.ai

Administrator or Manager

You can now integrate agents that are built in watsonx.ai with watsonx Orchestrate by using the API! These agents can run tasks seamlessly by using the parameters and tools you specify in the agent's settings.

By integrating these agents, you can enhance automation and streamline workflows more efficiently. For detailed instructions, see Registering a watsonx.ai Agent Lab agent with watsonx Orchestrate.

Simplify app connections with preconfigured client credentials

Administrator or Manager Builder or Writer

Builders can now configure the connection details for prebuilt apps, such as Client ID and Client Secret directly when setting up the app's endpoints in a tenant.

This enhancement removes the need for Users to manually enter credentials, making connections faster and more intuitive.

With Client ID and secret preconfigured, Users can click the Connect App button to establish a connection effortlessly. When only the Client secret is preconfigured, users only need to enter their Client ID, further simplifying the setup.

This update enhances security, reduces setup errors, and improves the overall user experience. For more information, see Configuring endpoints per watsonx Orchestrate tenant.

The following GIF demonstrates how preconfiguring client credentials simplifies the app connection process. Here, the builder sets up the client credentials for the Workday HCM app, allowing users to connect without entering the Client ID and secret.

Document extractor skills are now generally available in Skill studio

Builder or Writer

Document extractor skills, which were previously in beta, are now generally available in the Skill studio. You can easily publish and use them in your workflows to extract the data you need in your business operations.

Here’s what else you can do with this update:

• Publish document extractors to the skill catalog.

• Use Document extractor skills in chat for quick access.

• Share updates with other collaborators.

• Set Document extractor skills as public or private.

• Edit the skill display name and operation ID.

• Delete Document extractor skills when you no longer need them.

To learn more, see Creating document extractors and Configuring document processors.

Enhance security with audio recording in phone integration

You can now use audio recording with the Genesys Audio Connector in Phone Integration! This feature helps you to record a caller’s verbal confirmation to verify identity, provide consent, or authorize actions.

With the new record feature, you can capture the caller’s utterance and play it back for confirmation. Set up an audio webhook to save the recording and configure a record response in your conversation flow. You can customize prompts, add a beep before recording, and let callers confirm their input by pressing a key.

This update enhances security, ensure compliance, and provides a reliable way to capture verbal communications. To learn more, see Recording a caller's utterance.

Enhance security with IP access control

The Administrators can now define which IP addresses can have access and which are restricted to IBM watsonx Orchestrate on IBM Cloud. This gives the Administrators control over the network that can access the application. For more information, see Allowing specific IP addresses.

AI agents now support Japanese in chat

User or WO User

IBM watsonx Orchestrate now supports Japanese language in AI agent chat. This enables Japanese users to effectively use watsonx Orchestrate AI capabilities in their native language, making interactions smoother and more intuitive. For more information, see Supported languages.

UIAgent Integration with AI Assistant Chat

UIAgent is a no-code UI automation feature designed to enable business users to create and execute web-based user interface (UI) automations without requiring any coding expertise.

With UIAgent, you can write automations for small, specialized use cases without relying on IT support, allowing you and your team to streamline repetitive tasks and boost productivity.

Users can create automations by using either screen demonstrations or natural language in a browser extension.

The automations can either be run directly from the extension or can be published to IBM watsonx Orchestrate and executed through an AI-powered Assistant embedded on the web app, providing a more intuitive, flexible, and accessible way to run the automations through a conversational interface.

The UIAgent is now in limited availability through watsonx Orchestrate. If you are interested, enroll by using the "UIAgent integration with IBM watsonx Orchestrate" form.

IBM® watsonx Orchestrate® API updates

See the updates in the IBM watsonx Orchestrate API for this release.

Register an external agent

You can now register an agent built in watsonx.ai Agent lab with watsonx Orchestrate by specifying the property provider as wx.ai in the requestBody. For more information, see Register an external agent.

Enable Base LLM response

In IBM watsonx Orchestrate, you can enable and disable the responses from an LLM by using the API. The is_base_llm_enabled property is set to True to allow LLM responses for a specific tenant. For more information, see Update Orchestrate settings.

Updated sections

• The watsonx Orchestrate API is now updated to mention the operations that are now available for on-premises offering. The available operations display the On-premises tag at the top of the document. For more information, see watsonx Orchestrate API.

• The IBM watsonx Orchestrate API known issues and limitations topic now has the following entry:

  • IBM watsonx Orchestrate API

    • Authentication on watsonx Orchestrate API with IP address restriction

Other enhancements and changes

The following table details the enhancements that are delivered in the current release corresponding to the user role:

The following table details the fixes that are delivered in the current release corresponding to the user role:

Documentation updates

See the updates in the watsonx Orchestrate documentation and other contents for this release.

New sections

• Defining an audio webhook section includes the procedure to add a webhook to store an audio.

• Regional availability of IBM watsonx Orchestrate section is added to provide information about the service availability by regions for IBM watsonx Orchestrate SaaS.

• Allowing specific IP addressessection is added to provide information on how to allow specific IP addresses to access watsonx Orchestrate on IBM Cloud.

• Adding actions from web-based automation flowssection is added to provide the steps on how to enroll to the UIAgent feature. The feature is in limited availability.

Updated sections

• The Configuring prebuilt appssection is now updated to add information on how the Builders can configure Client ID and Client secret of prebuilt applications.

• The Known issues and limitations topic now has the following entry:

  • Enhancing skills

    • Enhance the skill content in other languages

  • Skill-based actions

    • IBM watsonx.ai skills fail to run

Configuring webhook authentication

watsonx Assistant now supports webhook authentication to verify that the pre-message webhook and post-message webhook requests are legitimate, come from the expected source, and ensure the authenticity and integrity of the data. For more information, see Webhook authentication.

Other enhancements and changes

The following table details the fixes that are delivered in the current release corresponding to the user role:

Documentation updates

See the updates in the watsonx Orchestrate documentation and other contents for this release.

Updated sections

• The Administering section is now updated with a new structure for better organization and easier access to content.

• The Managing skills in the AI chat section is updated to improve clarity on adding skills.

• The Elasticsearch search integration set up documentation is updated to include details on advanced search capabilities for semantic text fields.

• The Known issues and limitations topic now has the following entry:

  • Building projects

    • Calling skills from interactions

  • Skill-based actions

    • Using form skills in the AI assistant builder

Changes in the navigation menu

IBM watsonx Orchestrate has made updates in the main menu, aiming to improve the UI usability.

New additions

• Skill sets tab is now available in the main menu. You can click the Skill sets tab to manage skills and connections.

Updates

• The Manage team tab is now moved under Administer for a structured layout. You can click the Manage team tab to manage users.

• The Usage tab under Manage team is removed.

Enabling a builder to manage skill connections

The users with the builder role can now manage the connections of the Team skills, skill sets from AI assistants, and the Orchestrate Agent Skillset. They can now configure an application credential as either Team credentials or Member credentials. Also, they can set connection parameters, such as client ID, client secret, as the required parameters for app integration. Builders can now connect to an app or configure the app connection either from the Skill catalog page or through the chat.

Support for more languages in conversational search

User or WO User

You can use Conversational search in languages other than English. The new supported languages include French, Spanish, German, and Brazilian Portuguese. To do this, switch from the default Granite model to another model. You can test the results to ensure that they meet your expectations. The accuracy of the responses depends on the selected model.

Configuring data retention time for AI chat

Administrator or Manager

You can set the data retention period for chat threads in AI chat as per your requirement. It is possible to retain the data for a minimum of 30 days to a maximum of 365 days. This feature provides you the flexibility to manage your data as per the requirements.

For more information, see Data retention policies of AI chat.

Other enhancements and changes

The following table details the enhancements that are delivered in the current release corresponding to the user role:

The following table details the fixes that are delivered in the current release corresponding to the user role:

IBM® watsonx Orchestrate® API updates

See the updates in the IBM watsonx Orchestrate API for this release.

• List message threads API is now updated to add the sample response for the request with limit and offset query parameters.

• Get Welcome content API is now updated to add new responses and descriptions. The property isDefaultMessage is added to indicate if the default content for the welcome message and description is used instead of customized message.

• Register AI Assistant instances and Update AI Assistant instance APIs are now updated to add descriptions for the config parameters in the request body.

• Register an external agent and related operations were updated to include the enable_cot parameter. It enables agents within IBM watsonx Orchestrate to show the reasoning into the AI's decision-making process in the AI chat. Agents within watsonx Orchestrate generate the trace of tool calls and their responses as a form of a chain of thought (COT).

• The IBM watsonx Orchestrate API known issues and limitations topic now has the following entry:

  • Using skills

    • AI Assistant instance operations work only with IBM Cloud AI assistants

Documentation updates

See the updates in the watsonx Orchestrate documentation and other contents for this release.

New sections

• Configuring data retention time for AI chat section is now added to describe how to configure the data retention time.

• Managing agents in the AI chat section is added to provide information about how to add an agent, edit an existing agent, or disconnect an agent that is no longer needed.

• Configuring a web chat language section is added to provide information about how to handle hard coded texts in web chat.

• Release notes for IBM watsonx Orchestrate for On-premises section is added to provide information about the latest updates to IBM watsonx Orchestrate for On-premises.

Updated sections

• Documentation is now rearranged for more usabilities. You can view all the content that is related to prebuilt applications in the Exploring the catalog section.

• Connecting to apps is now updated with the prerequisites that are required to connect to an application and information on how to configure the connection.

• Managing app connections section is now updated to document the navigation (main menu) changes.

• Installing IBM watsonx Orchestrate On-premises section is now updated to add separate procedures for installing IBM watsonx Orchestrate on IBM Cloud Pak for Data and IBM Software Hub.

• Connecting to apps content is now updated to mention that the users with the builder role can now manage the app connections.

• Updating skills from OpenAPI specifications section is updated to add a note on how to change the endpoint of a prebuilt app or an imported app.

• Outbound IP addresses section is now updated with IP addresses for Toronto region.

• The Enhancing skills with OpenAPI specification properties section is now renamed to Configuring inputs and outputs types for your skills and it includes the configuration of all input and output types that watsonx Orchestrate supports.

• The Troubleshooting topic now has the following entry:

  • No results with Elasticsearch

Testing limits update

Administrator or Manager Builder or Writer

There are no longer limits to the number of tests, but there is still a limit of 250 messages per test. For more information, see Testing limits for the set of data.

IBM Cloud data center expansion

The IBM Cloud data center is now expanded to include the following region:

London

IBM watsonx Orchestrate data center now expands to London DC. With this new data center, watsonx Orchestrate offers secure and compliant data storage solutions for user data in accordance with European data protection laws.

Documentation updates

See the updates in the watsonx Orchestrate documentation and other contents for this release.

Labels

The app pages in the documentation now display all the deployment label tags that they support.

The labels in the watsonx Orchestrate documentation are now updated with designated colors for deployments and personas.

New sections

• The Deprecated or withdrawn models section is added to provide information about the foundation models that are deprecated or withdrawn from support.

• Configuring a web chat language section is added to give information about the hard coded web chat texts.

• Added skill-ids for the followings apps:

  • Adobe Workfront

  • Cognos

  • FreshService

  • IBM Process Mining

  • Salesforce Chatter

  • Salesloft

  • Seismic

  • Webex

  • Workday HCM

  • Zoho Recruit

  • ZoomInfo

Updated sections

• Combining skills into skill flows section is now updated to add more information about workflows and skill flows and how to use them.

• Activity tracking events for IBM watsonx Orchestrate are now updated to add information about how to view the watsonx Orchestrate logs in the account.

• The Known issues and limitations topic now has the following entries:

  • Building AI assistants

    • Custom-built actions

  • Skill-based actions

    • Duplicate skills are created

  • Building skills

    • OpenAPI builder

  • AI chat

    • Embedded AI chat does not work with security that is enabled

  • Skill catalog

    • The IBM Process Mining app does not appear in the Skill catalog

IBM Cloud data center expansion

The IBM Cloud data center is now expanded to include the following region:

Toronto

IBM watsonx Orchestrate data center now expands to Toronto DC. With this new data center, watsonx Orchestrate offers improved performance, low-latency access, and data sovereignty for users in Canada and North America.

Stopping the streaming of responses for AI assistants

User

When a response is streaming in the chat of AI assistants, you can see a Stop icon in the chat. Click the Stop icon to stop streaming the response. You can use this feature to continue with your chat experience without waiting for the response to finish.

AI agent available on IBM Cloud

The AI agent is now available on IBM Cloud! Use agents, AI assistants, and skills in the AI chat to assist and augment your team's capabilities with advanced language models, by providing valuable insights and support to help your team achieve their goals.

Explore the features available:

• Adding AI assistants to the AI chat

• Managing skills

• Embedding the AI chat in a page

• Enabling web chat security

• Encrypting sensitive data in web chat

• Authenticating users in web chat

• Customizing the starter prompts

• Switching the chat experience

Support for new foundation models

Administrator or Manager Builder or Writer

IBM watsonx Orchestrate now supports the following foundation models:

• llama-3-2-11b-vision-instruct

• llama-3-2-90b-vision-instruct

• llama-3-3-70b-instruct

For more information, see Supported foundation models.

Enhanced UI experience for AI agent settings

The AI agent settings page is made more intuitive by simplifying the UI configuration. Instead of using YAMLs, now you have dedicated input fields to configure the base LLM and its parameters. You can specify the format to generate an output response in the System prompt tab.

For more information, see Configuring the model of the AI agentand Setting the system prompt.

Support for handwritten text extraction in IBM Document Processing

User or WO User

You can now perform handwriting recognition in English for the Extract Text skill of the IBM Document Processing app. When you set the language parameter to en_hw, the skill uses a handwriting recognition model that is specialized for English.

The handwritten text extraction improves the accuracy for detecting and extracting handwritten text compared to the standard OCR approach. For best results, use this option especially if your documents contain a significant amount of handwritten text.

For more information, see Skill name: Extract text.

IBM® watsonx Orchestrate® API updates

See the updates in the IBM watsonx Orchestrate API for this release.