Salesforce AI assistant
The Salesforce AI assistant from Bonfire Terminal runs locally on your Mac or PC, drawing on your CRM credentials and context to help manage accounts and deals from your favorite chat app. Your AI, your machine, your control over sensitive customer records.
What Bonfire can do in Salesforce
Real actions from the Salesforce API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| Create a record | Records | POST /services/data/v60.0/sobjects/{sObject} |
| Get a record | Records | GET /services/data/v60.0/sobjects/{sObject}/{id} |
| Update a record | Records | PATCH /services/data/v60.0/sobjects/{sObject}/{id} |
| Delete a record | Records | DELETE /services/data/v60.0/sobjects/{sObject}/{id} |
| Run a SOQL query | Query | GET /services/data/v60.0/query?q={soql} |
| Run a SOSL search | Search | GET /services/data/v60.0/search?q={sosl} |
| Describe an object | Metadata | GET /services/data/v60.0/sobjects/{sObject}/describe |
| Create multiple records | Composite | POST /services/data/v60.0/composite/sobjects |
Salesforce 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
Salesforce — questions
Can Bonfire automate Salesforce?
Yes. Bonfire runs on your machine, holds your Salesforce credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the Salesforce API to run the actions you ask for in chat.
Does my Salesforce 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.