QuickBooks Online AI features
QuickBooks Online AI features come from Bonfire adding local reasoning over your books. On your own hardware it interprets accounting context to flag anomalies, summarize months, and draft reports, bringing on-device intelligence to your financial data.
What Bonfire can do in QuickBooks Online
Real actions from the QuickBooks Online 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 |
| Create item | Items | POST /v3/company/{realmId}/item |
| Create payment | Payments | POST /v3/company/{realmId}/payment |
| Create bill | Bills | POST /v3/company/{realmId}/bill |
| Create vendor | Vendors | POST /v3/company/{realmId}/vendor |
| Create estimate | Estimates | POST /v3/company/{realmId}/estimate |
| Run query | Query | GET /v3/company/{realmId}/query?query={sql} |
QuickBooks Online 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 Online — questions
Can Bonfire automate QuickBooks Online?
Yes. Bonfire runs on your machine, holds your QuickBooks Online credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the QuickBooks Online API to run the actions you ask for in chat.
Does my QuickBooks Online 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.