Oracle MICROS Simphony AI chatbot
An Oracle MICROS Simphony AI chatbot from Bonfire Terminal answers from Telegram or Discord using your POS context. Ask about today's sales or a menu item with Claude, GPT, or offline Llama, all running privately on your own restaurant hardware.
What Bonfire can do in Oracle MICROS Simphony
Real actions from the Oracle MICROS Simphony API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| List checks | Checks | GET /api/v1/checks |
| Get check | Checks | GET /api/v1/checks/{checkRef} |
| Create check | Checks | POST /api/v1/checks |
| Add round to check | Checks | POST /api/v1/checks/{checkRef}/round |
| Calculate totals | Checks | POST /api/v1/checks/calculator |
| Get menu | Menus | GET /api/v1/menus/{menuId} |
| List tenders | Tenders | GET /api/v1/tenders/collection |
| List revenue centers | Revenue Centers | GET /api/v1/organizations/{orgShortName}/locations/{locRef}/revenueCenters |
Oracle MICROS Simphony 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
Oracle MICROS Simphony — questions
Can Bonfire automate Oracle MICROS Simphony?
Yes. Bonfire runs on your machine, holds your Oracle MICROS Simphony credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the Oracle MICROS Simphony API to run the actions you ask for in chat.
Does my Oracle MICROS Simphony 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.