Home / Integrations / Redox / AI features

Redox AI features

Redox AI features arrive with Bonfire Terminal, which connects to Redox healthcare data integration through its API. Device-resident AI agents surface interoperability metrics, troubleshoot connections, and summarize data exchange on demand while keeping PHI handling under your control.

Get Redox AI featuresHEALTHCARE DATA INTEGRATION · PUBLIC API ✓

AI featuresAI agents AI skills AI chatbot AI assistant

Block 1 · Capabilities

What Bonfire can do in Redox

Real actions from the Redox API that a Bonfire agent can run on your behalf, on-device.

Action	Resource	Method · Endpoint
Search patients	Patient	`POST /fhir/R4/{destination}/{environment}/Patient/_search`
Get patient	Patient	`GET /fhir/R4/{destination}/{environment}/Patient/{id}`
Search encounters	Encounter	`GET /fhir/R4/{destination}/{environment}/Encounter`
Search observations	Observation	`GET /fhir/R4/{destination}/{environment}/Observation`
Search documents	DocumentReference	`GET /fhir/R4/{destination}/{environment}/DocumentReference`
Search coverage	Coverage	`GET /fhir/R4/{destination}/{environment}/Coverage`

SOURCE: https://developer.redoxengine.com/ · spec-backed — no capability shown without a real endpoint.

Block 2 · Automation recipes

Redox agents in action

Telegram: a chat command → Bonfire → Redox → Search patients and replies with the result.

Slack: ask a question → Bonfire → Redox → Get patient posted back to the channel.

Scheduled: nightly → an agent checks Redox and flags anything that needs your attention.

Block 3 · Local-first vs cloud

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

Block 4 · FAQ

Redox — questions

Can Bonfire automate Redox?

Yes. Bonfire runs on your machine, holds your Redox credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the Redox API to run the actions you ask for in chat.

Does my Redox 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.

Explore

Redox overview Redox AI agents Redox AI skills Redox AI chatbot ShopifyE-commerce HubSpotCRM