DoNotPay, the company that bills itself as “the world’s first robot lawyer,” is launching a new AI-powered chatbot that can help you negotiate bills and cancel subscriptions without having to deal with customer service.
In a demo of the tool posted by DoNotPay CEO Joshua Browder, the chatbot manages to get a discount on a Comcast internet bill through Xfinity’s live chat. Once it connects with a customer service representative, the bot asks for a better rate using account details provided by the customer. The chatbot cites problems with Xfinity’s services and threatens to take legal action, to which the representative responds by offering to take $10 off the customer’s monthly internet bill.
This tool builds upon the many neat services DoNotPay already offers, which mainly allows customers can generate and submit templates to various entities, helping them to file complaints, cancel subscriptions, fight parking tickets, and much more. It even uses machine learning to highlight the most important parts of a terms of service agreement and helps customers shield their photos from facial recognition searches. But this is the first time DoNotPay’s using an AI chatbot to interact with a representative in real time.
“For the past five years, we’ve mainly been using rules-based systems, and what I mean by that is templates,” Browder says in an interview with The Verge. “We’ve trained this AI to be like a robot lawyer for consumers, and I imagine that the disputes that we can handle have now gone up significantly because we can handle cases where you can respond rather than just sending one template.”
DoNotPay’s bot issues convincingly human-like answers throughout the entire interaction with Xfinity, save for a hiccup where the tool says “[insert email address]” instead of providing the customer’s actual email. Browder tells The Verge that DoNotPay will clean up some of its responses before it goes live — and make the bot sound less polite, as it’s pretty heavy on the “thank-yous.”
In this particular example, Browder notes that the AI “exaggerated the Internet outages, similar to how a customer would,” but that this isn’t something the chatbot will do once it becomes available to all users. “We won’t allow for exaggeration of facts in the final version,” Browder says. “But it will still be aggressive, citing laws and having an emotional appeal,” which is (sadly) more than I can say for myself whenever I chat with a customer service representative.
DoNotPay’s bot is built on top of OpenAI’s GPT-3 API, the underlying toolset used by OpenAI’s ChatGPT chatbot that tons of people have been playing around with to generate detailed (and sometimes nonsensical) responses. DoNotPay’s tool is made for a specific purpose, though, and Browder seems to view it as an opportunity to expand the number of tasks it can tackle, like chatting with a representative to cancel a customer’s subscription or negotiating a credit report.
If the chatbot doesn’t know an answer to a particular question, Browder says it won’t start making things up. “It will just stop in its tracks and ask the user for help” when it’s unsure, Browder explains. The company’s working on ways to alert users whenever this happens so that they don’t have to sit in front of their computer and monitor the tool. Browder tells The Verge that users could eventually respond to the AI’s questions over text message so that it can continue its “conversation.”
The tool will be open for testing in the next two weeks, and Browder says it will work with all companies in the US.