Mitchell 1 AI Integration
Mitchell 1 AI agents are driven by Bonfire Terminal, the local-first desktop app running AI on your machine. Using your Mitchell 1 context and credentials, agents help you look up procedures, draft estimates, and organize work orders for your auto shop, from Slack or Telegram.
What Bonfire can do in Mitchell 1
Real actions from the Mitchell 1 API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| Get jobs | RepairOrder | GET /api/2.2/RepairOrder/JobService.svc/Jobs |
| Get vehicles | RepairOrder | GET /api/2.2/RepairOrder/JobService.svc/Vehicles |
| Get vehicle detail | RepairOrder | GET /api/2.2/RepairOrder/VehicleService.svc/Vehicles |
| Get customer | RepairOrder | GET /api/2.2/RepairOrder/CustomerService.svc |
| Get claim | RepairOrder | GET /api/2.2/RepairOrder/ClaimService.svc |
| Get estimate | Opportunity | GET /api/2.2/Opportunity/OpportunityService.svc |
| Get shop | Shop | GET /api/2.2/Shop/ShopService.svc |
| List partner shops | Partner | POST /Partner/PartnerAdminService.svc |
Mitchell 1 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
Mitchell 1 — questions
Can Bonfire automate Mitchell 1?
Yes. Bonfire runs on your machine, holds your Mitchell 1 credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the Mitchell 1 API to run the actions you ask for in chat.
Does my Mitchell 1 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.