Toast AI assistant
Toast AI assistant built on Bonfire Terminal helps run your restaurant POS from chat. Local-first on your machine, it uses your Toast context to surface sales insights and daily prep while your store data stays firmly on-device.
What Bonfire can do in Toast
Real actions from the Toast API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| List orders | Orders | GET /orders/v2/orders |
| Create order | Orders | POST /orders/v2/orders |
| Get order | Orders | GET /orders/v2/orders/{guid} |
| Get menus | Menus | GET /menus/v2/menus |
| Get restaurant | Config | GET /config/v2/restaurants/{guid} |
| List dining options | Config | GET /config/v2/diningOptions |
| List employees | Labor | GET /labor/v1/employees |
| Get time entries | Labor | GET /labor/v1/timeEntries |
Toast 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
Toast — questions
Can Bonfire automate Toast?
Yes. Bonfire runs on your machine, holds your Toast credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the Toast API to run the actions you ask for in chat.
Does my Toast 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.