Skip to Main Content
IBM Data and AI Ideas Portal for Customers

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 (

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 ( - Use this site to find out additional information and details about the IBM Ideas process and statuses.

IBM Unified Ideas Portal ( - Use this site to view all of your ideas, create new ideas for any IBM product, or search for ideas across all of IBM. - 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


Showing 166

Function calling feature in API

Function calling feature is not available in the sdk or REST API. Functions/tools calling features (Function calling is the ability to reliably connect LLMs to external tools to enable effective tool usage and interaction with external APIs.). The...
3 months ago in 6 Under review

Support MIG GPUs for foundation model serving

The documentation states that MIG is not supported for foundational model serving in watsonx. Our current infrastructure does not allow us to use GPU passthrough, as our internal infrastructure team relies on vGPU and MIG for availability and easy...
3 months ago in 0 Submitted

Provide a proper dashboard to view pipeline executions and status.

IBM Pipelines do not provide any pipeline monitoring similar to airflow. See
6 days ago in 0 Submitted

Watsonx Pipelines should provide higher level DSL for creating Pipelines programmatically

Currently Watsonx Pipelines provide an API for managing Pipelines as described under However that API seems very tied to the UI and the payload needed to c...
7 days ago in 0 Submitted

Support timeouts at the node level for Watsonx Pipelines

Currently Watsonx Pipelines doesn't support timeouts so we can cap each task/job. This is important given long-running batch pipelines where we typically want to make have a cap in case something goes wrong otherwise we run the risk of resource wa...
7 days ago in 0 Submitted

Support retries at the node level in Watsonx Pipelines

Currently Watsonx Pipelines do not support interacting at the node level for restarting tasks in case of failures and require rerunning the entire pipeline job. This makes it complicated to use for complex pipelines where any given task could fail...
7 days ago in 0 Submitted

Cloud Pak for Data - Watson Pipelines - Add Undostack as a drop down list

Currently in a Watson Pipeline if you want to undo 5 Steps, then you have to 1: know how many steps to go back 2: click on the undo button n times As discussed with the dev team, this should be improved to offer an arrow-down next to the undo/redo...
5 months ago in 1 Submitted

Marking a project as sensitive on Default Git integration

One big restriction of CP4D git integration for KB Bank is that the customer need to set Sensitive to projects by their security policy but it’s not available with Default Git integration. As the option is available with Deprecated Git integration...
6 months ago in 0 Under review

multi-language LLMs - availability in Europe

For many customers (not only public) it is needed to have availability of multi-language LLMs (i.e. llama 2) in european data centers to address GDPR requirements
10 months ago in 0 Under review

Improve issue of PII getting leaked in the Granite 8B Japanese model

The clients have noticed PII getting leaked in the Granite 8B Japanese model. This is a massive Red flag and must be dealt with properly before can be deployed live(scheduled in early September).We did a quick search and found the infor...
21 days ago in 1 Submitted