Interesting idea.

The slideshow on the front page changes too quickly once you get to the results pages. It is hard to see what is returned since it is only up there a few seconds.

How about providing a text box to allow the engine to be tested from the web. I know it is a mobile app, but before installing it I'd like to see if it produces useful results to something I might ask.

Thanks for pointing that out. A more interactive demo would certainly help. Also, the current webpage misses out the text-to-speech feature. I might work on that.

Thanks again! :)

Interesting. Your goals are similar to ours and your choice of name for the technology is also (too) similar. Are you using any of the concepts and ideas discussed at http://artificial-intuition.com and/or http://videos.syntience.com ?

Syntience Inc. is so far concentrating on understanding (written) text in any language but speech recognition is an obvious extension to any competent language understanding technology.

Clickable link: http://www.snolr.com

How does this compare to other question answering systems?

It's far more scalable in terms of technology. It uses intuition techniques and minimal NLP. So we can scale it to almost any language. Moreover, the system is not only limited to answer questions.

Also, it requires much less data. Usually Q/A systems have this thing called the query planner. We don't. It takes a single run through normal search results to get the answer. The speed to get, process and return answers is less than 500ms when the index is not hosted locally, so that includes the fetching lag.

The algo is completely online. No corpus, whatsoever.

These are just some examples of the fact that under the hood, it's completely different from the usual Q/A system.

How do you pronounce it?

snaw-ler.