ATTOM AI Integration
ATTOM AI agents run inside Bonfire Terminal, a local-first app that drives the ATTOM property data API from AI on your own machine. Pull ownership, valuation, and parcel records, then deliver insights to Slack, Telegram, or Discord.
What Bonfire can do in ATTOM
Real actions from the ATTOM API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| Get property detail | Property | GET /propertyapi/v1.0.0/property/detail |
| Get expanded profile | Property | GET /propertyapi/v1.0.0/property/expandedprofile |
| List properties in area | Property | GET /propertyapi/v1.0.0/property/snapshot |
| Get sales history | Sales | GET /propertyapi/v1.0.0/saleshistory/detail |
| Get tax assessment | Assessment | GET /propertyapi/v1.0.0/assessment/detail |
| Get AVM value | Valuation | GET /propertyapi/v1.0.0/attomavm/detail |
| Get rental AVM | Valuation | GET /propertyapi/v1.0.0/valuation/rentalavm |
| Get school profile | Neighborhood | GET /v4/school/profile |
ATTOM 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
ATTOM — questions
Can Bonfire automate ATTOM?
Yes. Bonfire runs on your machine, holds your ATTOM credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the ATTOM API to run the actions you ask for in chat.
Does my ATTOM 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.