Siri sibling Trapit launches as intelligent discovery engine for the web’s content

Say hello to Trapit. The latest offspring from CALO, the DARPA-commissioned artificial-intelligence project that gave birth to iPhone virtual assistant Siri, launches in public beta Tuesday as a personalized discovery engine for the web.

[aditude-amp id="flyingcarpet" targeting='{"env":"staging","page_type":"article","post_id":352684,"post_type":"story","post_chan":"none","tags":null,"ai":false,"category":"none","all_categories":"business,social,","session":"D"}']

The service offers web denizens a search-free, sit-back-and-relax way to stumble upon news articles, images, videos, recipes and other content on specific topics of interest. More than 10,000 participants have been using Trapit to find and “trap” content since the site’s private beta release in June.

“We’re revolutionizing the way people will access content on the web,” Trapit CEO and co-founder Gary Griffiths told VentureBeat. “This is the web following you.”

The word “revolutionary” gets thrown around with reckless abandon these days, but if Trapit is to the web what Siri is to the iPhone, as Griffiths promises, then perhaps it’s a fitting description.

Here’s how it works: You tell Trapit what you want to discover with a keyword or two. The intelligent discovery engine then goes to work and scans an archive of data collected over the past 30 days. In 10 seconds or less, Trapit will find and return up to 100 pieces of content related to your keywords.

You can save the results to a topic-based information stream, called a “trap.” After you hit save, the artificial engine continues to grab new content as it’s published to the web and adds it to the trap.

Pretty cool, right? Just don’t call it search. Trapit’s discovery process is much more sophisticated, co-founder Hank Nothhaft said. Griffiths and Nothhaft said that what Trapit is actually doing is taking your keyword and matching it against content with the same context, making associations at a level deeper than text.

You can, as would be expected, train Trapit to find better photos, videos and news articles for your trap. Hit the thumbs up and thumbs down buttons to steer Trapit in the right direction. And as you express your tastes, this handy assistant to the web’s most pertinent content will once again query its trove of data to find even better content for your trap.

“Trapit gets to know you. It gives you more and more of what you want and less of what you don’t like,” Griffiths said. “It’s not just pure search, it’s going out and creating that sense of delight.”

[aditude-amp id="medium1" targeting='{"env":"staging","page_type":"article","post_id":352684,"post_type":"story","post_chan":"none","tags":null,"ai":false,"category":"none","all_categories":"business,social,","session":"D"}']

Just how delightful it is remains to be seen. Trapit’s technology may share the same storied upbringing as Siri, but the Trapit service is missing the smack-you-over-the-head-with-it wow factor of its buzzed-about cousin on the iPhone 4S.

Trapit, founded in early 2010, has raised several million for its intelligent discovery engine. The startup landed $2 million in its first round of financing, and is said to be in the process of raising a second, more sizable round. The company plans to release mobile applications for iOS in early 2012.