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.
One of our team members asked for this. Here's their request:... I really miss the ability to export the JSON without having to go back to the skills page. There used to be an icon next to Try it that gave you that ability. I used that A LOT to ma...
Currently, Disambiguation has a fixed threshold of confidence between the top intent and other intents to trigger disambiguation. We would like to see this threshold be configurable so that disambiguation doesn't get triggered too often (or not a...
When using Watson Assistant search, we can find node names, but we can't find which nodes have a jump to a particular node. This would be helpful to know what nodes are jumping to a particular node.This could be implemented in one or the other (or...
Create UI/UX for Watson Assistant users to view, delete, and add counterexamples
Currently, via the web tooling, there is no way to view or delete counterexamples in the WA workspace. You may add them using the "Irrelevant" tag in the "try it out" panel, but after that the counterexample is not easily inspect-able.
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 have...
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...
Add a visualization to the "Try it out" expereince that shows the intent confidence threshould
Google Dialog Flow has a functionality for its developers that WA does not have: the json of the response is easily inspected in the tooling as "diagnostic info". Our premier customer sent me this email to complain:
> Hey Anna,
Currently Assistant supports only one skill , which in a real world scenario does not make sense.
There should be provision to add multiple skills to an assistant to be achieve more scalable conversations
Update cursor to provide more contrast in JSON editor
A few versions ago, we were able to see the cursor in the JSON editor within a dialog node, but now it's very difficult to see so it makes editing very difficult. Can the cursor be changed to provide more contrast so we can find it.
It would be great to have a built-in workspace versioning for managing changes in the workspace.
Today, we have to workaround that using a time-based download of the workspace json and `git push`ing it to be "safe".
Meanwhile this time-based sch...
Do not place IBM confidential, company confidential, or personal information into any field.