With implicit confirmation, the UI repeats a critical component of the user’s statement into its response, so that it’s clear what was understood.
Why is this implicit confirmation? It is because the user immediately knows that the question was correctly understood.
Suppose the bot says:
That would be an answer to the question, but it would be hard for the user to know for certain if the question was completely understood. By implicitly confirming what it understood, the bot makes it much easier for the user to trust it.
Dynamically generating implicit confirmation is hard because it would fall under the category of Natural Language Generation. But if you have a list of static questions, their implicit confirmations can be hardcoded and would be easier to implement.
The important thing is to check if the user is asking a question which can be answered with a single word or a single phrase. If so, instead of just blurting out the word or phrase, your bot should preface it with the appropriate context so that the user can implicitly confirm that their question was understood.
Check your text responses. Do you have any one word or one phrase replies?