An in-house AI agent cut Curative's doctor credentialing process from two to three months and $50 per doctor down to roughly 12 hours and 20 cents.

42:22from their school, checking like a database of of who's been sued by who, um, and then like rubber stamping. And that used to take us two to three months on average and cost about $50. We've now built in-house an agent that runs on on Claude that does this end to end. and it goes to the website, it verifies the license, it goes and reads the transcript, it puts it all together, it

42:44stamps it for approval. Um, and we're now averaging about 12 hours turnaround time for credentiing somebody. And it cost us about 20 cents. And so this is like a mind-numbing process that payers have to do, which is important. We want to know the doctors in our network, right, are are validly licensed to practice medicine. Um, but it's like historically has always been kind of terrible and payers have been bad at it,

43:08right? If you're a doctor and you join a network and it takes 3 months before you can see any patients. It's just bureaucracy, right? Like they don't Doctors hate that and it's not actually adding the value that it should be adding. It's just creating paperwork. >> How many people did you have in credentiing? >> That one wasn't that large. I think there was like five or six people. We

43:26had a few other departments that have shrunk more than that with the >> What other departments? We've seen a lot on the claims side, claims processing, right, is used to be a very manual process where claims comes in and people are like manually tweaking and editing it. Um, and also on the underwriting side, underwriting, you know, the process used to be uh a broker comes to us with a group, an employer that

43:49they're looking to insure and they ask for competitive bids from multiple different insurance companies. And what that means is basically sending us an email with a bunch of PDFs and spreadsheets attached of who are the employees, what current claims do they have, what's the current insurance look like. And you'd think that over time they would develop like a standardized format for how that should run, but no,

44:12every single one is like a different spreadsheet format, different PDF. And we tried to sort of solve that problem with software and build like universal importers and universal intake. And it like it kind of worked, but what we found works amazingly is literally to give the files to an agent, tell it to write Python to get these files into a standardized format because they're not very good at parsing files. But they're