Shape the future of IBM watsonx Orchestrate

Start by searching and reviewing ideas others have posted, and add a comment (private if needed), vote, or subscribe to updates on them if they matter to you.

If you can't find what you are looking for, create a new idea:

  1. stick to one feature enhancement per idea

  2. add as much detail as possible, including use-case, examples & screenshots (put anything confidential in Hidden details field or a private comment)

  3. Explain business impact and timeline of project being affected

[For IBMers] Add customer/project name, details & timeline in Hidden details field or a private comment (only visible to you and the IBM product team).

This all helps to scope and prioritize your idea among many other good ones. Thank you for your feedback!

Specific links you will want to bookmark for future use
Learn more about IBM watsonx Orchestrate - Use this site to find out additional information and details about the product.
Welcome to the IBM Ideas Portal (https://www.ibm.com/ideas) - Use this site to find out additional information and details about the IBM Ideas process and statuses.
IBM Unified Ideas Portal (https://ideas.ibm.com) - Use this site to view all of your ideas, create new ideas for any IBM product, or search for ideas across all of IBM.
ideasibm@us.ibm.com - Use this email to suggest enhancements to the Ideas process or request help from IBM for submitting your Ideas.

ADD IDEA

All ideas

Showing 323 of 323

Expanding agent routing mechanisms

Feature Request: Expanding AI Agent Routing Mechanisms To enhance the flexibility and intelligence of AI agent orchestration, we propose adding support for multiple routing strategies. These should include semantic routing, rule-based routing for ...
7 months ago in  2 Under review

Provide a configuration option to hide individual input and output fields displayed during tool execution.

At present, all inputs and outputs from tool execution are displayed to the user without filtering. This can include sensitive information such as API keys or authentication credentials that should not be exposed. To address this, we request the f...
about 2 months ago in  1 Needs more information

Admin should have an option to block (disable) an LLM model available

The IA governance area is requesting that the admin should have an option to disable an LLM available in Orchestrate to attend cases where the governance area did not approve some model for security reason. Exemple: Lets suppose that AI gov team d...
4 months ago in  0 Future consideration

Publishing a new version from Skill studio should retain the "enhance skill" updates that are made in the skill

We are having issues when publishing new versions of skills. On our end, all the configs in "Enhance Skill" get removed after publishing any changes in the skill studio. This behavior was confirmed in more than one tenant. To avoid it we have to e...
7 months ago in  0 Not under consideration

Integration with Microsoft Copilot 385 , Office 365 , Sharepoint and Microsoft Team

This is very important, as follows: 1- most enterprises use Microsoft Applications in the Forefront and IBM Agentic AI for Enterprise in the Back End, 2- We can do the Digital transformation smoothly and keep the investment in Microsoft technologi...
about 2 months ago in  2 Functionality already exists

Asynchronous skill execution to be enabled from Assistant web chat to App connect

There is a use case where an API built using App Connect processes bulk records. As per the current design, the API handles records sequentially, which can result in significant delays when processing large volumes of data. This delay impacts the ...
11 months ago in  1 Not under consideration

Newer Model Support in Assistant Builder Features

Per the official documentation only four models can be used for the watsonx Orchestrate Assistant Builder features (e.g., Conversational Search Answer Generation, Conversational Search Query Rewrite, Conversational Skills, and Custom Action Inform...
about 2 months ago in  1 Under review

Create forms directly on the AI Agent

At the moment, AI Assistant works primarily in a Q&A style. However, in some use cases, such as when users need to input personal information for a credit card application, using a form provides a much better user experience. Currently, we are...
about 2 months ago in  0 Functionality already exists

Users other than the creator of the skill need to be able to enhance the skill

In a large operation, creation and maintenance of skills is performed by a team, not an individual and this requires that multiple users be able to enhance (edit) a skill. Currently, only the creator of the skill can enhance it. Authentication for...
6 months ago in  1 Not under consideration

Search for text snippets across an Action of an Assistant

In the dialog mode, its possible to perform a search for text snippets within the Nodes, which greatly facilitates in the customer's daily tasks when its needed to find specific information and direct it exactly to where the data is located. For e...
10 months ago in  0 Submitted

By clicking the "Post Comment" or "Add Idea" button, you are agreeing to the IBM Ideas Portal Terms of Use.
Do not include IBM confidential, company confidential, or personal information in any field.
Having problems accessing this portal? Describe the problems in an email to ideasibm@us.ibm.com.