A little over one year ago, SnapLogic Inc. introduced Iris as the first “self-driving” technology that automated enterprise data integration. The recommendation engine is designed to connect data flows and process application streams more efficiently. And now it’s getting smarter, too.

The company is working on a set of enhancements for Iris, still to be formerly announced, that will incorporate natural language processing in order to perform work across an entire data pipeline. This might include telling the system to filter all records logged in the previous week and place them into Amazon’s Redshift data warehouse, according to Greg Benson (pictured), chief scientist at SnapLogic and a University of San Francisco professor.

“We’re applying machine learning in order to speak or type what the intention is of what you’re looking for,” Benson said. “This is still very early on, but we have some exciting results.”

Benson spoke with Jeff Frick (@JeffFrick), host of theCUBE, SiliconANGLE Media’s mobile livestreaming studio, live from SnapLogic’s headquarters in San Mateo, California. They discussed the potential use of NLP for automated programming and how machine learning can help SnapLogic’s customers fill in the pieces of a complex data integration puzzle. (* Disclosure below.)

Automated programming may be next

SnapLogic’s use of NLP may also potentially be extended to the programming level. The company uses expressions, based on a subset of JavaScript, to perform various operations and manipulate data. The company is working on a way to verbally describe the expression needed and have a machine build it on the spot.

“One of our next goals is to use natural language to help you describe what you want those expressions to do and then generate those expressions for you,” Benson explained. “What we’re trying to do in our domain and in our space is to achieve automated programming. It’s very exciting.”

SnapLogic’s chief scientist likens the process of generating data integration support for the company’s clients to solving a puzzle. In this case, the customer can fit some of the pieces together and then rely on automation to do the rest.

“That puzzle-solving metaphor is where we’re moving with integration assistance so that you can fill in the pieces you know and then we help you work in any direction to make the puzzle complete,” Benson concluded.

Watch the complete video interview below, and be sure to check out more of SiliconANGLE’s and theCUBE’s coverage of the SnapLogic Innovation Day event. (* Disclosure: TheCUBE is a paid media partner for the SnapLogic Innovation Day event. Neither SnapLogic Inc., the event sponsor, nor other sponsors have editorial control over content on theCUBE or SiliconANGLE.)

Photo: SiliconANGLE