Epic AI skills
Epic AI skills let Bonfire package clinical admin workflows, from summarizing charts to drafting referral letters using Epic context. Each skill runs on your own hardware, so protected health information never leaves the machine your practice already controls.
What Bonfire can do in Epic
Real actions from the Epic API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| Search patients | Patient | GET /api/FHIR/R4/Patient |
| Get patient | Patient | GET /api/FHIR/R4/Patient/{id} |
| Search appointments | Appointment | GET /api/FHIR/R4/Appointment |
| Get observations | Observation | GET /api/FHIR/R4/Observation |
| Get medications | MedicationRequest | GET /api/FHIR/R4/MedicationRequest |
| Get conditions | Condition | GET /api/FHIR/R4/Condition |
| Create document | DocumentReference | POST /api/FHIR/R4/DocumentReference |
Epic 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
Epic — questions
Can Bonfire automate Epic?
Yes. Bonfire runs on your machine, holds your Epic credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the Epic API to run the actions you ask for in chat.
Does my Epic 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.