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.
As of now the intent recommendations work only within intents and so it is really hard to go to every intent and add examples, it will be really easy if we can upload the csv and it classifies the intent recommendation for every question. We shoul...
Provide whitelist of public IPs for public services
IBM Cloud does not provide any kind of whitelist for public-facing services. This prevents security-conscious people from hardening their firewalls by restricting outbound traffic to those whitelist IPs. I'm running into this issue now, where my s...
AFAIK, the expression language does not allow looping through data.
I a conversation, you often have the situation that multiple entities are recognized. You can easily create a response for one recognized entity. But you may want to loop through...
We sometimes have multiple people needing to add different features to the same dialog skill at the same time, or we'll need to branch for a feature addition but still need to maintain our production version of the skill. Currently we are reviewin...
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 quest...
The "Intent Eye" in Watson Assistant Try It Window should display the whole name of intents caught
The Eye shows 3 intents caught for the input text + confidence now. Yet, there's no way to display the whole intent names if those are longer. That causes problems when the intents are grouped by their names, for example. (Like: #CompanyName_FAQ_S...
View workspaces inside the instances in the Usage and Billing screen
Today, on the Usage and Billing screen, we can only see up to which instance is generating more cost. To view the workspaces inside them, you have to manually enter each one and check in the analytics tab
Leverage NLU Entity extraction from Watson Assistant
Through the GUI of WA in the Entity, we should be able to have access to native Watson NLU entity type and the ability to use custom model. I would extend the type of entities we have out of the box and leverage existing WKS models the customer co...
Do not place IBM confidential, company confidential, or personal information into any field.