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,
Post an idea
Upvote ideas that matter most to you
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.
Currently, if we have "seasonal" intents, we have to pull them out and save them somewhere. There is no way to turn them off at certain times of the year. It would be helpful to have an on/off switch for intents. Better yet would be a means to hav...
In order to support full CI/CD of our Watson assistant based product, we should have the full ability to deploy a version without any manual UI actions needed. Currently, the API does not support any version control.
As an editor i want to see which nodes are jumping to the node i'm working in
When working in complicated flows, where jump-to's are used to move the user laterally through a dialogue, we lose sight of which jump-to's are implemented.
When updating or deleting a node we need to know when we shouldnt just check/update th...
Export dialog as pretty table so that it can be printed, reviewed, and audited by a third party outside the tooling.
For every response, create a row that record the relevant information such as:
- which node do this response belong to (i.e. node ...
The API currently does not support handling of carriage character. While our UI does handle this, in cases where customers copy/paste data, we are unable to handle unless we build a custom handler to remove carriage characters. While we can implem...
Support for live editing of the dialog while working with multiple people
As a conversation developer it would be nice to have functionality that supports working with multiple developers on the same dialog from different computers, without having to have refresh the browser screen every time.
Watson discards changes in Dialogue nodes done during the training - Possibility of team coworking on the same skill in one moment would make development faster and smoother
1. If one person in the team is training the assistant (adding user examples to Intents, adding Entities, or making other changes) and the assistant is processing them ("Watson is training" stripe in the "Try it" window), then no other team member...
Ability to delete disabled nodes when turning off MCR
Currently, when you turn off MCR (Multiple Conditioned Response) it will disable the separate responses instead of deleting them. This means they are kept in the skill/module but won't be visible in the Watson Assistant UI (can be seen in the down...
Do not place IBM confidential, company confidential, or personal information into any field.