IBM Data Platform Ideas Portal for Customers


This portal is to open public enhancement requests against products and services offered by the IBM Data Platform 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

Clear

Ideas

    Enable tools to use member credentials through Microsoft Teams and the Orchestrate Agent API

    Requested enhancement Enable tools to use member credentials when an agent is accessed through external channels. IBM watsonx Orchestrate should identify the requesting user and run tool actions on behalf of that user, using the credentials and pe...
    6 days ago in IBM watsonx Orchestrate 0 Submitted

    Reduce thinking messages back to a single line

    In the latest release of watsonx Orchestrate, the thinking messages that are displayed while the agent is processing a user input have changed to be shown in sequence. Release reference: https://www.ibm.com/docs/en/watsonx/watson-orchestrate/base?...
    3 days ago in IBM watsonx Orchestrate 0 Submitted

    Create CCA MCP Server builder using workflows UI.

    Banco do Brasil (BdB) is one of the world's largest Watson Assistant users and is actively migrating their customer-facing virtual assistant to watsonx Orchestrate (wxO) using the Customer Care Agent (CCA) model. Building CCA solutions today requi...
    19 days ago in IBM watsonx Orchestrate 0 Submitted

    Intelligence freshness re-validation before action

    Problem: AI-derived assessments go stale as sources update, but the report keeps its authority hour after hour. Idea: Before any consequential action, Orchestrate re-validates AI-derived products against current sources. Shifted underlying data fl...
    less than a minute ago in IBM watsonx Orchestrate 0 Submitted

    Model-version pinning for evidentiary work products

    Problem: If you can't name the model, version, and configuration behind an assessment, you can't reproduce it, audit it, or defend it later. Idea: Every AI-assisted product records full lineage: model name and version, training cutoff, tool versio...
    less than a minute ago in IBM watsonx Orchestrate 0 Submitted

    Contradiction circuit breaker: quarantine on source conflict

    Problem: The chatbot's conclusion contradicted what primary sources actually said, but nothing stopped the report from circulating. Idea: When an agent's synthesis conflicts with a primary source it ingested, the product is automatically quarantin...
    1 minute ago in IBM watsonx Orchestrate 0 Submitted

    Standing AI red-team for analytic products

    Problem: The false report circulated unchallenged. No one was assigned to attack it — everyone assumed someone else had checked. Idea: A dedicated adversarial agent or workflow that stress-tests AI-generated assessments before circulation: weakest...
    1 minute ago in IBM watsonx Orchestrate 0 Submitted

    Click-through source tracing on every AI claim

    Problem: Nobody could see which "sources" supported the nuclear-cargo claim until minutes before the operation — the report didn't link claims to evidence. Idea: Every factual claim in an AI-generated product links back to the source documents beh...
    2 minutes ago in IBM watsonx Orchestrate 0 Submitted

    Two-human verification for AI-originated high-consequence actions

    Problem: One analyst, one chatbot, one report — and boarding teams were in the air. A single unverified AI product nearly started a war. Idea: Orchestrate enforces a policy: operational recommendations originating from AI analysis require two inde...
    2 minutes ago in IBM watsonx Orchestrate 0 Submitted

    Confidence intervals required on AI assessments

    Problem: The chatbot delivered its cargo conclusion as a flat fact. There was no "we're 40% sure" — so planners treated a guess as certainty. Idea: Any agent output framed as an assessment must carry a calibrated confidence range. Products below t...
    less than a minute ago in IBM watsonx Orchestrate 0 Submitted

    By clicking the "Post Comment" or "Submit Idea" button, you are agreeing to the IBM Ideas Portal Terms of Use.
    Do not place IBM confidential, company confidential, or personal information into any field.