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.
Select future or past or range for ambiguous sys-date and sys-time
Currently the system entities for date and time make a guess to fill in portions of the date and time that are not mentioned by the user.
"Monday" could be in the future or in the past.
"4/5" could be this year, last year or next ye...
Ability to make an API to see all the data that is present in the Improve Tab of a Skills. To see all of the Total Conversation data for the past 30 days, the number of times an intent being called, the number of active users, etc.
Airport codes(eg: ATL for Atlanta, NYC for New York, BLR for Bangalore) to extract location from user utterances. Typing codes are faster than typing the entire location for a user and it will also be easier to identify the departure & arrival...
Allow calling Watson AI APIs in-process rather than as a remote API call
A frequent ask is to allow calling the Watson AI APIs in the same process. For example, if you have a spark or pandas dataframe containing a news story per row, if would be great if each row could be mapped to a local Watson AI function call rathe...
In mathematics, the standard way to refer to the numeric output representative of certainty of a classification algorithm is as a "score." The name of this in the json structure returned by Watson Assistant currently is "confidence". However, this...
For every dialog node, user will be able to add status labels with color code to the node for their own references.
Example of labels: draft (red), in review (orange), reviewed (cyan), final (green), etc
Watson Conversations offers not only the API but also quite a complete interface that can be used by logging in Bluemix.
In many projects, when business and experts train the system, they use the Bluemix interface. It is more or less intuitive an...
Enable automatic transfer of a string of nodes from one skill to another
HI team, Could you please help in finding a solution for a way in transferring a string of nodes or folders with nodes from 1 skill to another in WA without having to do this manually, in just 1 click? It is a loss of time to manually copy those n...
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...
Do not place IBM confidential, company confidential, or personal information into any field.