Owen Sakawa, the founder of Elloe AI, wants his platform to be the “immune system for AI” and the “antivirus for any AI agent.”
The idea, Sakawa said in an interview days before the TechCrunch Disrupt conference, where Elloe AI is a Top 20 finalist in the Startup Battlefield competition, is to add a layer to companies’ LLMs that checks for bias, hallucinations, errors, compliance issues, misinformation, and unsafe outputs.
“AI is evolving at a very fast pace, and it’s moving this fast without guard rails, without safety nets, without mechanism to prevent it from ever going off the rails,” Sakawa (pictured above) said.
Elloe AI is an API or an SDK, a module that sits on top of an AI model’s output layer, an “infrastructure on top of your LLM pipeline,” as Sakawa explained. “And it sits there basically fact-checking every single response.”
The startup’s system has its own layers, or “anchors,” as Sakawa put it.
The first anchor fact-checks the LLMs response against verifiable sources. Then, the second anchor checks if the output violates any regulations, such as the U.S. health privacy law HIPAA, the European far-reaching data protection and privacy law GDPR, or if it exposes some Personal Private Information (PII). The last anchor is an audit trail that shows how all the previous decisions were made and allows regulators or anyone auditing the system “to analyze the train of thought for that model from where it made the decision the source of that decision, the confidence score of all those decisions,” according to Sakawa.
To be clear, Sakawa said Elloe AI is not built on an LLM, because in his opinion, having LLMs checking other LLMs is just putting a “Band-Aid into another wound.” Elloe AI’s system does use AI techniques, though, such as machine learning. And there are humans in the loop: Elloe AI’s employees, who keep up with new regulations on data protection and user protection, Sakawa said.
If you want to learn more about Elloe AI — while also checking out dozens of other companies, hearing their pitches, and listening to guest speakers on four different stages — join us at Disrupt, October 27 to 29, in San Francisco. Learn more here.
