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

Status Not under consideration
Workspace Cognos Analytics
Components AI/Smarts
Created by Guest
Created on Jun 8, 2023

Define AI Assistant 'Assumptions' or Defaults for when a user doesn't give context to a natural language query

When a user enters a natural language question, they may not give the full context to the question.

Our data warehouse fact tables have upto 20 dimension tables. When a user asks a question they would typically only supply a few dimensions in the context. For example "Show sales for TVs this year". This question only provides context for two dimensions - product and time. No context is given to all the other dimensions - sales method, sales person and so on. with simple measures and simple additive dimensions, assumming ALL when no context is given is usually ok. However this is rare in an enterprise data warehouse.

The data source modeller should be able to provide default context about the query if the user question is not explicit.

Another example "show the forecasted tv sales for this year". A business will typically have multiple forecasts. The user question has not specified which forecast they want to see. As no context has been given, the AI assistant will assume ALL forecasts which would sum all the forecasts!

As no context has been given to the forecast dimension, the data source modeller should be able to tell the AI to assume the latest forecast.

Another example "compare region 1 sales between 2023 and 2022".
If there was a reorganisation of the regions between the years, then the modeller should be able to tell the AI assistant that the assumption is a like for like answer (such as only showing open stores).

These assumptions would also help business authors. Again, if they create a report and are not explicit in the Forecast, the report will use the data model assumption of latest forecast.

Needed By Yesterday (Let's go already!)