DoorDash Drive AI features
DoorDash Drive AI features expand when Bonfire Terminal runs locally on your own device. Using connected models like Claude, GPT, or Grok, it coordinates dispatches and communications through the delivery API, while an offline Llama model handles private, on-device reasoning so your operational data stays under your control.
What Bonfire can do in DoorDash Drive
Real actions from the DoorDash Drive API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| Create delivery quote | Quotes | POST /drive/v2/quotes |
| Accept quote | Quotes | POST /drive/v2/quotes/{external_delivery_id}/accept |
| Create delivery | Deliveries | POST /drive/v2/deliveries |
| Get delivery status | Deliveries | GET /drive/v2/deliveries/{external_delivery_id} |
| Update delivery | Deliveries | PATCH /drive/v2/deliveries/{external_delivery_id} |
| Cancel delivery | Deliveries | PUT /drive/v2/deliveries/{external_delivery_id}/cancel |
| List businesses | Businesses | GET /drive/v2/businesses |
| Create store | Stores | POST /drive/v2/businesses/{external_business_id}/stores |
DoorDash Drive 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
DoorDash Drive — questions
Can Bonfire automate DoorDash Drive?
Yes. Bonfire runs on your machine, holds your DoorDash Drive credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the DoorDash Drive API to run the actions you ask for in chat.
Does my DoorDash Drive 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.