AI dental insurance verification checks a patient's cover before the appointment, prepares the claim from the clinical notes and chases rejections. A person in the practice approves every claim, and the system never chooses a code the notes do not support.
All Dental & Private Clinics →
In a US practice, a large part of the billing coordinator's day is eligibility and benefits: calling or checking portals to confirm what a plan covers before treatment, then preparing claims with CDT codes and attachments, then working the rejections. In the UK the paperwork is NHS dental claims and plan providers; in Spain, the mutuas and their own authorisation rules. The shape is the same everywhere: structured data scattered across portals, PDFs and phone calls.
Clinic billing automation is useful there, and risky in one specific way. Coding has to reflect what was done and documented. A system that nudges codes towards what pays better is a compliance problem, not an efficiency, so ours checks claims against the notes and flags gaps for a person; it does not optimise reimbursement.
patient and plan known
eligibility and benefits
notes and codes in the PMS
checked against the notes
then submitted
notes and codes disagree
Before the appointment, the system takes the patient and plan details from the practice management system, queries the insurer through electronic eligibility or its portal, and extracts the coverage that matters for the booked treatment: remaining maximum, frequency limits, waiting periods and co-insurance. The result is written to the patient record with the date it was checked. Anything it cannot confirm is left for a person to call about.
It can do most of the preparation, and it should not do the approving. Claims carry the practice's legal responsibility for what was billed, so a named person reviews and submits. The system drafts, checks the claim against the notes, gathers attachments and works the follow-up, which is where the time goes.
Yes, with different plumbing. In the UK it supports NHS claim preparation and dental plan administration; in Spain it handles the authorisation and billing steps the mutuas require. The approach is the same: read the practice's records, prepare the paperwork, flag gaps, and leave submission to a person.
What we built, what stage it is at, and a link to the live thing wherever there is one.
yourOS is an operating system with an AI at its heart. You talk to it like a person, out loud or typed. It makes your calls, plans your days and works on your projects with a crew of agents, on your own private server. Our own product, built from the first commit; the waitlist is open.
Website, backend and app assets for Sonora, a free AI sound-therapy app on iOS and Android published by Cognitive AI.
Brand, website, prototype, apps on five platforms, the AI backend and the algorithm-intelligence pipeline for Podswap, a social growth engine that runs without a human in the loop.
In closed beta: Roxy, a private AI assistant with permanent memory running on infrastructure the user owns. Brand, site, product, backend and conversational design.
Live at coherence.com: brand identity generated with AI agents we directed, the motion system and website for the group behind Sonora, AboutAI, WakeUp and MudShadows. Agent work remains in build.
Live at domainbooth.com for DomainBooth, a premium domain brokerage: a new animated mark, every page redesigned and rebuilt with designed mobile layouts, and a custom CMS for its sales record, featured names, press and enquiries.
Start with the insurers you deal with most and the claims that come back most often.
30-minute technical call · no deck