[alistproducer2]

It's already really easy to get fast, efficient access to large data sets. I don't see much value in that. It is not fast,efficient, and easy to transform natural language queries into computationally actionable ones.

I would find more value as a developer if, when given a natural language query, it returned a structured query. Then I could tweak the query to conform to whatever data retrieval API I wanted.

I don't think what I'm asking for has to be mutually exclusive with what they're currently offering. Give me the option to have houndify do some or all of the work for me.

[iamcasen]

I am one of the developers for houndify.com, so I can answer this question for you!

We actually have an api endpoint dedicated to doing this for you. At the moment we have a concept of "domains" where developers use a proprietary language to help Hound understand topics. Using our api, you could technically do this yourself, and add functionality that doesn't currently exist on the platform.

You could use the hotel domain and get back a ton of pre-formatted data, or you could just get back speech-to-text, or you could specify hooks you want to take action on. I'm not a developer on the actual voice api itself, so I'm not the most informed, but perhaps that answers your question?

[alistproducer2]

Q1: So a domain developer gets to determine what is returned to from the API for all calls matched to that domain?

Q2: As a domain developer, where does the query-able content reside?