Applause, the Boston-based crowd-testing specialist has launched a new tool for AI-based software testing. The tool uses data collected from Applause’s global team of testers to train algorithms to learn quickly and test the output from those algorithms to ensure they are responding appropriately.
Companies will be able to use the tool to identify issues of quality or bias earlier in the development process, Applause said.
“Users want AI to be more natural, more human. Applause’s crowdsourced approach delivers what AI has been missing: a diverse and large collection of real human interactions prior to release,” said Kristin Simonini, VP of Product at Applause. “Not only will this improve AI experiences for consumers everywhere, the breadth of the community also has the potential to mitigate bias concerns and make AI more representative of the real world.”
Not only does its community of testers provide diverse training data sets to power algorithms, Applause said, it can also test the outputs of those algorithms to check for bias. If bias has crept into an algorithm at any stage, the community can identify it when testing the output, something that a smaller or less diverse group of testers might not be able to do.
Applause’s new solution operates across five types of AI engagements, the company said: voice, OCR (Optimized Character Recognition), image recognition, biometrics, and chatbots.
