Anthrodontics Blog

I’m thrilled to finally pull back the curtain on something I’ve been quietly building for a while now. Richard and I have been working on the latest version of Anthrodontics, which is an intelligent, multi-media notebook designed for clinicians and dental professionals.

It’s a digital workspace for your clinical brain. Just like how dentists have to synthesise different sources of information, the notebook is a place where notes, images, scans, audio, and patient context all live together, and interoperate to deliver high quality medico legal documents and reports, custom patient education materials and many more.

Notebooks are composed of cells, which can represent all the unique pieces of information that we have to stitch together on a daily basis. Its flexibility means that we can create new cell types that suit your work, also it is easy to replicate, extend and give new context to existing workflows and processes.

We have opened up the Pilot Program because we want to hear your opinion / feedback how such solution could suit your day to day work as a dental practitioner the best.

This is a very novel technology, so we have also created a dedicated Guides section with walkthroughts tailored to different clinical workflows.

Want In?

If any of this sounds like something you’ve been waiting for, come check us out and grab one of the pilot spots before they’re gone. I’d love to have you in the first cohort helping us build the AI interfaces that dentistry deserves.

Join our Pilot Program today

At heart, I’m a builder. There’s nothing more satisfying than turning an idea in your head into something real on the screen. So I worked day and night on Anthrodontics, fully believing the old mantra: if you build it, they will come. But after launch, traction was slow. They didn’t come. After some honest soul-searching, I narrowed it down to three reasons.

The first was stealth mode. When I build, I become reclusive and live inside my head. That meant I wasn’t talking to users, wasn’t understanding their needs, and wasn’t iterating on real feedback. It felt productive, but it isolated me from the people I was building for.

The second was unclear product features. Anthrodontics is ambitious, with many moving parts: Anthrodontics Share (referral letter automation and secure file sharing), Anthrodontics Profile (Linktree-style social pages with embedded referral tools), and Anthrodontics Tungsten (the patient data store) — all underpinned by a dental large language model. But on launch, the homepage only showed a tutorial covering a subset of the features. Without clear communication, my pitch deck made me look as wild-eyed as Daniel Radcliffe on a good day.

The third was ambiguous pricing. The pricing page was an afterthought. Tiers weren’t differentiated, prices felt too high, and since billing wasn’t even live, users could technically have used the product free forever. The friction alone was enough to deter sign-ups.

So I went back to strategy basics. A good strategy has three parts: diagnosis, guiding policy, and coherent actions. My diagnosis was that users will use whatever software their workplace provides even if it sucks, dentists want information instantly available, and users only engage when there’s immediate clinical benefit. My guiding policy became: create a frictionless interface, gradually expose multiple functions, and do the hardest things first for maximum leverage.

The coherent action is an iceberg metaphor. At the tip is a voice and chat interface — users are already trained by Google and ChatGPT to start by typing, so we meet them there. Just below is registration and PMS integration, so patient information is instantly accessible. Deeper still are referrals and secure file sharing, replacing the WhatsApp habit clinicians currently rely on for confidential information. At the deepest level is Anthrodontics Profile, closing the loop on the patient journey.

The AI engine driving all of this is Delta — Dental Expertise Language Technology for Assistance. There are currently no answer engines built specifically for dentistry, and this is where we’ll stand apart. At launch, Delta will handle the basics: speech-to-text clinical notes, caries detection on radiographs, and more. But the exciting part is chains of thought for tailored treatment plans, and deep searches across literature, protocols, material guides, and CPD content — so clinicians are armed to the teeth with knowledge.

Our initial audience is threefold: new graduates juggling patient loads, theory, and the dream of getting home on time; dental students testing treatment plans and learning from reputable sources; and dental influencers, who can help drive awareness through sponsorships.

Pricing is also simpler now. Anthrodontics is free forever for dental students. Pro is $20/month for individual practitioners. Enterprise is $50/month plus $8/month per user for workplaces. We’ll also launch a referral program, and clinicians who contribute CPD content to Delta’s knowledge base will be paid whenever their work is cited — a Spotify-style model for dental expertise.

The biggest shift, though, is one of identity. Anthrodontics is pivoting from being a dental startup focused on AI to being an AI startup focused on dentistry. It’s a small change in wording, but a massive change in leverage — and I believe it’s the unlock that will let us outpace competitors and realise the full vision.

Software needs data to be effective. Ingesting and interpreting data is important, but the key is being able to store that data. Healthcare software needs to be able to store patient-related information. That database interface will always amalgamate into a patient management system (PMS). It is an inevitability. The only quesiton is whether your final user interface will look modern and minimalistic or like a pilot’s cockpit controls.

When I was developing my GenAI assisted referral program, I envisioned a software product suite that would be backed by a Patient Management System. I called it Tungsten, a tongue-in-cheek reference to the PMS I used in school. That PMS was called Titanium, and well, Tungsten is stronger than titanium.

My PMS version was designed to be primarily based on visits. Commerical PMS will have two sections, a list of treatment plans and a list of all the treatment items. Clinicians can create treatment plans and insert them into the treatment items list. The treatment details will show the overall dental history of the patient. There is no visual distinction of the item codes per visit, so clinicians would have to infer by grouping item codes by date. My version was attempting to eliminate that manual step by explicitly displaying the grouping.

It had some neat ideas, but ultimately failed to gain traction. However, it was a great learning experience. While I was committed to using Elixir/Phoenix LiveView, I was inexperienced so there was a learning curve.

I have recorded a video tutorial, which you can view below.

I was finishing up my Cone Beam Computed Tomography (CBCT) Observation rotation. The radiologist and I had just finished reviewing five cases together. Our conversation drifted to the use of AI in dentistry. We talked about how good these new models seemed to be at pattern recognition, and how naturally that capability mapped onto CBCT diagnosis and reporting. Could a model surface differential diagnoses from a DICOM volume? Could it draft the report a radiologist would otherwise spend an hour writing?

At the time, I was trying to start an indie iOS/macOS software business. I had a demo of my current project on my phone, and on a whim, I pulled it out and showed him.

He gave me a look of awe.

I want to be honest about how much that small moment mattered. I was a dental student showing a half-finished side project to a senior clinician. Instead of polite acknowledgement, I got genuine surprise. It was a look that said, you can actually build things. That look lodged itself somewhere in my brain. It was the spark. It made me feel like our conversation wasn’t just idle speculation. It was something I could, in principle, actually go build.

I left the office that day with a different idea of what my career might look like.

In the months that followed, I went deeper. The technical hill was steeper than I had hoped, but the more I learnt, the more convinced I became that there was real opportunity here for a company, and not just a side project.

By the time 2024 rolled around, I had started talking to every dentist who would listen. What did they hate about their workflow? Where did AI actually fit, and where was it a solution in search of a problem? I still wanted to pursue CBCT diagnosis, but the deeper I got, the more I saw the intermediary mountains: ethically acquiring training data, navigating regulatory approval, building clinician trust, and so on. None of these are reasons not to do it. They’re just reasons it can’t be your first move.

So I pivoted to something more tractable: a GenAI assisted dental referral program. I used this idea to apply to Y Combinator under the name Anthrodontics. While waiting for the results, I moved to Emerald, Queensland, to start my first job. Most new graduates take a metro job, ease in, and enjoy their evenings. I went bush, treated patients all day, and tried to build a startup at night.

In May 2025, I relocated to Sydney to pursue the idea more seriously. After a year of ruminating, attending dental AI seminars and conferences, and drawing on experience from the industry, I think I finally got it.

It’s been four years since I first started imagining this future, and it has been, by every honest measure, a rollercoaster. I’ve had quite possibly the most unconventional new grad experience of anyone in my cohort: moving twice in less than a year, moonlighting as a self-taught programmer,, trying to imagine what the future of dental AI will look like.

Would I do it again?

Probably not.

The romantic answer would be of course, in a heartbeat. But the truthful answer is that the cost has been real. Friendships lost, weekends evaporated, a clinical career that has taken a back seat to a startup that may or may not work. The look of awe from that radiologist set me on a path I didn’t fully understand the price of.

So here’s my parting advice, equal parts sincere and tongue-in-cheek: the next time someone gives you a look of awe and respect, ignore the call.

You probably won’t. I didn’t.

But at least you’ll have been warned.