Monday Sales CRM AI Integration
Monday Sales CRM AI agents draw on your pipeline as context, with Bonfire running locally on your machine. Rather than acting as your CRM's backend, these agents use Monday deal and contact data to inform the AI, keeping your sales information on-device and in your hands.
What Bonfire can do in Monday Sales CRM
Real actions from the Monday Sales CRM API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| Create an item | Items | POST /v2 (mutation create_item) |
| Update column values | Items | POST /v2 (mutation change_multiple_column_values) |
| Query items on a board | Items | POST /v2 (query items_page) |
| Create a board | Boards | POST /v2 (mutation create_board) |
| Query boards | Boards | POST /v2 (query boards) |
| Create a group | Groups | POST /v2 (mutation create_group) |
| Post an update | Updates | POST /v2 (mutation create_update) |
| Query users | Users | POST /v2 (query users) |
Monday Sales CRM 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
Monday Sales CRM — questions
Can Bonfire automate Monday Sales CRM?
Yes. Bonfire runs on your machine, holds your Monday Sales CRM credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the Monday Sales CRM API to run the actions you ask for in chat.
Does my Monday Sales CRM 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.