Denticon AI Integration
Denticon AI agents use your dental practice data as context, with Bonfire running on your own machine. These agents reference schedules, patients, and treatment records to inform the AI rather than acting as Denticon's backend, keeping patient data on-device.
What Bonfire can do in Denticon
Real actions from the Denticon API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| List all patients | Patients | POST /v2/api/Patient/AllPatients |
| Get patient detail | Patients | POST /v2/api/Patient/GetPatientDetail |
| Get appointments | Appointments | POST /v2/api/Patient/GetAppointments |
| Get changed appointments | Appointments | POST /v2/api/Patient/DeltaAppointment |
| Get patient ledger | Ledger | POST /v2/api/Patient/GetPatientLedger |
| List responsible parties | Responsible Parties | POST /v2/api/Patient/AllRespParties |
| Get account balance | Financial | GET /v2/api/Patient/GetAccountBalance |
| Initial batch download | Sync | GET /v2/api/Patient/InitialBatchDownload |
Denticon agents in action
On your machine, not a SaaS
Bonfire Terminal
- Your keys & data stay on your device
- Perpetual license — no per-seat SaaS fee
- Any connected model — Claude, GPT, Gemini or Grok
- Offline Llama for local, private reasoning
- Driven from chat you already use
Cloud AI middleman
- Keys & data pass through a third-party server
- Recurring subscription, usage caps
- Model locked to the vendor
- Yet another dashboard to log into
Denticon — questions
Can Bonfire automate Denticon?
Yes. Bonfire runs on your machine, holds your Denticon credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the Denticon API to run the actions you ask for in chat.
Does my Denticon data go to the cloud?
Bonfire runs on your desktop and keeps your keys local — it isn't a SaaS holding your data. Only the specific request you approve is sent to your chosen AI model.
Which AI models can I use?
Any connected model — Claude, GPT, Gemini or Grok. A fully offline Llama model runs locally for private reasoning but can't reach live APIs.