QuickBooks AI features
QuickBooks AI features in Bonfire bring your accounting software into a chat interface you control. Bonfire holds your credentials locally and drives the QuickBooks API with Claude, GPT, or Gemini to review profit and loss, chase invoices, and summarize spending, with offline Llama available for private on-device reasoning.
What Bonfire can do in QuickBooks
Real actions from the QuickBooks API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| Create customer | Customers | POST /v3/company/{realmId}/customer |
| Create invoice | Invoices | POST /v3/company/{realmId}/invoice |
| Get invoice | Invoices | GET /v3/company/{realmId}/invoice/{invoiceId} |
| Create bill | Bills | POST /v3/company/{realmId}/bill |
| Record payment | Payments | POST /v3/company/{realmId}/payment |
| Create item | Items | POST /v3/company/{realmId}/item |
| Create account | Accounts | POST /v3/company/{realmId}/account |
| Query entities | Query | GET /v3/company/{realmId}/query |
QuickBooks 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
QuickBooks — questions
Can Bonfire automate QuickBooks?
Yes. Bonfire runs on your machine, holds your QuickBooks credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the QuickBooks API to run the actions you ask for in chat.
Does my QuickBooks 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.