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.
Add ability to turn off matching to intents, entities and context in strings
Currently, if Watson Assistant finds a #,@, $ in any string, it will replace the characters with an evaluation of the intent, entity or variable (respecitvely). This can be very difficult when there are strings passed back from an API that need to...
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.
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 (o...
Allow dialog tree's to be copied from one skill to another
Allow for either all or part of a dialog tree to be copied from one skill to another. Currently if you have logic implemented in one skill and want to reuse it in another skill you have to completely rebuild it. The ability to copy useful dialog t...
Watson Assistant New Experience needs JSON import/export function
The Watson Assistant New Experience is missing the JSON import/export function that the Classic Experience had. When switching between New and Classic experiences, the Assistant data is not migrated, therefore you cannot switch to the Classic expe...
The Watson Assistant New Experience needs a way to enable and disable an Assistant without having to delete and recreate it when needed. My business case is that I create Assistants for annual events. We only need the Assistant active during the e...
When changing Intent name, offer to change corresponding dialog nodes
When we change an intent name, then all the dialog nodes that use it have errors because the old intent name no longer exists. We suggest that when an intent name is changed, then the option is provided to also change where it is used in dialog.
Get Search skill(Discovery) responses/logs via Assistant api(logs or a new analytics api)
Right now, AssistantV1 logs provides dialog skill logs only. Even if we provide assistant id, we do not get the search skill(discovery responses) logs. It will be good, if Assistant V2 also provides logs api or an analytics api, that can return bo...
Enhancement request for using Watson Assistant with Tone analyzer
We are currently integrating Tone analyzer with our product.
We have a suggestion that from Watson Assistant Dialog flow, you can provide direct support to invoke Tone analyzer. Rather if Watson Assistant itself can have Tone analysis function...
Do not place IBM confidential, company confidential, or personal information into any field.