It will be great to provide an API allowing developers to interact with Cortana following this workflow:
1- Get command from Cortana.
2- Do some processes.
3- Get back to Cortana with response data (do not exit from Cortana UI).
4- Cortana responds the user.
Please vote if you're interested by this feature request.
In Windows 10 this scenario can be accomplished using voice commands. Cortana can activate your app in the background and display results on it’s surface.
For additional information please refer to MSDN https://msdn.microsoft.com/library/windows/apps/xaml/dn974230.aspx or watch Build 2015 video at https://channel9.msdn.com/events/Build/2015/3-716
Arun Singh commented
We announced this exact feature with Windows 10. Take a look at this Build talk https://channel9.msdn.com/events/Build/2015/3-716 about 39 minutes in. Apps can now provide an app service background task that can interact with Cortana. This allows Cortana UI to present data from the app in it's canvas.
This! Give devs access to Cortana Knowledge Database. As an example, MS decides that Cortana will know how to respond to a question about bus schedule in specific direction. As it is now, MS needs to feed Cortana with bus schedules for every city in the world - this is just not possible. So make API that will allow devs to feed Cortana with knowledge about bus schedules and let me choose witch service provider (read application from AppStore) I want to use. So there will be officaly provided applications from city governments or maybe a community provided applications in less popular locations.
A few of the best apps on the marketplace have options for reading things allowed. HERE Drive, for example, speaks instructions to help you navigate. Poki, an amazing Pocket client, reads saved news articles aloud to you.
Right now, it seems these apps either have to provide their own voice data. Instead, it'd be incredible if developers could use Cortana's voice for these situations.
Peter Wone commented
This is what I want, too. What currently exists is essentially sophisticated recognition and parsing followed by pass-through. It's one way. It's a very good start, but it treats Cortana as little more than a thin veneer over a normal app. If Microsoft wants this to be a category killer, this is my advice: treat Cortana as an AI framework. Apps should be able to function as domain knowledge providers. They may also have conventional UI; this is a separate matter. Use a VCD style file to specify weighted keywords to help Cortana assess service provider relevance. The "VCD" file should also specify a state machine definition for scripting conversations. There should also be a way to return an explicit spoken response. Implicit in the above is a need for developer tooling for preparing the state machine and the associated voice files.
Please add the German language to be faster than in a year . For this to feed into the development of new applications .
Mohamed Ouederni commented
Its about empowering Cortana with knowledge from apps without the need to say "Cortana, open app X do Y".
But by saying "Cortana do Y" directly.
I' don't get the idea! Is it a proxy?