A user should be able to either through talk or text ask questions about a particular picture input. Is the blue block on top of the orange block? Watson can say "No" or "Yes" as appropriate and even elaborate with "No, the blue block is in the persons hand."
This type of querying can span all input and output types. For example text in "Is Paris in Germany?", text out "No, Paris is in France." Can even elaborate with a visual presentation of a map of Europe.
NOTICE TO EU RESIDENTS: per EU Data Protection Policy, if you wish to remove your personal information from the IBM ideas portal, please login to the ideas portal using your previously registered information then change your email to "email@example.com" and first name to "anonymous" and last name to "anonymous". This will ensure that IBM will not send any emails to you about all idea submissions