Skip to Main Content
IBM Data and AI Ideas Portal for Customers
Hide about this portal


This portal is to open public enhancement requests against products and services offered by the IBM Data & AI organization. To view all of your ideas submitted to IBM, create and manage groups of Ideas, or create an idea explicitly set to be either visible by all (public) or visible only to you and IBM (private), use the IBM Unified Ideas Portal (https://ideas.ibm.com).


Shape the future of IBM!

We invite you to shape the future of IBM, including product roadmaps, by submitting ideas that matter to you the most. Here's how it works:


Search existing ideas

Start by searching and reviewing ideas and requests to enhance a product or service. Take a look at ideas others have posted, and add a comment, vote, or subscribe to updates on them if they matter to you. If you can't find what you are looking for,


Post your ideas

Post ideas and requests to enhance a product or service. Take a look at ideas others have posted and upvote them if they matter to you,

  1. Post an idea

  2. Upvote ideas that matter most to you

  3. Get feedback from the IBM team to refine your idea


Specific links you will want to bookmark for future use

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.

IBM Employees should enter Ideas at https://ideas.ibm.com


ADD A NEW IDEA

All ideas

Showing 52

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...
1 day ago in IBM watsonx Orchestrate 0 Under review

Login support with both IBM ID and SSO for watsonx Orchestrate on AWS

By default, watsonx Orchestrate on AWS allows users to log in using their IBM ID. Additionally, Single Sign-On (SSO) login can be enabled upon request. However, once SSO login is enabled, logging in with an IBM ID is no longer possible. In custome...
7 days ago in IBM watsonx Orchestrate 0 Under review

Audio response embedded in wxa/wxo

wxA/ AI Assistant Builder has an audio response feature (see attached file), however when using this with a live phone conversation, there is some latency given that the audio file needs to be hosted outside of wxo/ wxa. IBM should host typing or ...
about 8 hours ago in IBM watsonx Orchestrate 0 Under review

Improve integration with MS Teams channel

As part of the deployment of an agent on teams channels, it should be implemented the following points: Provide visibility for the user that the agent is thinking. Currently the response takes one minute to be returned and no feedback for the us...
11 days ago in IBM watsonx Orchestrate 4 Under review

Granular and Actionable Error Logs

We encountered a scenario where a user had configured the Agent to connect to a tool that triggered a Python script. While the Agent was connected, it suddenly stopped responding and displayed the following error message: "I'm sorry, it seems I've...
16 days ago in IBM watsonx Orchestrate 0 Under review

Remove reasoning from Embed Chat

When deploying an agent as embed chat, it appears reasoning. This on an interface publicly available doesn't looks goods
15 days ago in IBM watsonx Orchestrate 0 Under review

3rd-party agent authentication/authorization

WxO has no mechanism to keep authentication smoothly with outside agents. It is applicable to both Talent & Finance use cases: Currently on Talent side we have the following issue: We build our agent using LangGraph & Langchain outside WxO...
4 months ago in IBM watsonx Orchestrate 1 Under review

Chat Utterance Display – Multiline Input Not Rendered Properly

Problem: When a user submits a message containing multiple lines (e.g., using line breaks), the echoed output (utterance) is not displayed as multiple lines. Current Behavior: The utterance appears in a constrained single-line view or a scrollable...
23 days ago in IBM watsonx Orchestrate 3 Under review

Remove startup prompt from embed chat

Remove startup prompt from embed chat
15 days ago in IBM watsonx Orchestrate 0 Under review

Adding AutoAI Models as Expert Tools by automatically generating OpenAPI specs

Enable seamless integration of IBM AutoAI-deployed models into watsonx Orchestrate agent flows as "expert tools" by automatically generating OpenAPI specifications during or after deployment. This would allow LLM-based agents to dynamically call p...
28 days ago in IBM watsonx Orchestrate 0 Under review