IBM Data and AI Ideas Portal for Customers

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:

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

Help IBM prioritize your ideas and requests

The IBM team may need your help to refine the ideas so they may ask for more information or feedback. The product management team will then decide if they can begin working on your idea. If they can start during the next development cycle, they will put the idea on the priority list. Each team at IBM works on a different schedule, where some ideas can be implemented right away, others may be placed on a different schedule.

Receive notification on the decision

Some ideas can be implemented at IBM, while others may not fit within the development plans for the product. In either case, the team will let you know as soon as possible. In some cases, we may be able to find alternatives for ideas which cannot be implemented in a reasonable time.

Additional Information

To view our roadmaps:

Reminder: This is not the place to submit defects or support needs, please use normal support channel for these cases

IBM Employees:

The correct URL for entering your ideas is:

Status Future consideration
Workspace Watson Assistant
Created by Deleted user
Created on Sep 26, 2018

Allow for bulk testing of questions

During the construction or the improvement of a virtual assistant, we need to test its behavior thoroughly. It involves using a list of questions to check if the answers are consistent.

There's no native way in WA to import a large amount of question and get an output file containing all the answers (considering every dialog branches possible for every question).

This would be a usefull option.

  • Guest
    Nov 26, 2018

    A related idea is creating regression tests simply by saving Try It Out sessions - not only the utterances but everything else we'd want to check (intent, entities, context variables, nodes visited) in a future test run against an altered workspace OR test environment (ie new tokenizer). We don't currently log Try It Out sessions so we'd need a way for the customer to indicate at the start that this session is potentially one they want to save as a regression test or some other solution (always store temporarily until Cleared or Try it Out panel closed?). Would be great if when customers were reviewing results, they could easily decide a failure was just new and improved behavior and click a button to replace the old with the new.

    If it is not obvious already, I feel quite strongly that this feature is key to enabling customers to leverage dialog features AND for reducing the length of support calls since customers will be able to narrow down quickly what the new behavior they are seeing is.