Bloomberg Terminal AI agents
Bloomberg Terminal AI agents from Bonfire assist your financial workflow, using your Bloomberg context to summarize research, organize watchlists, and prep briefings. They run locally on your own machine, so market notes and analysis stay on your hardware.
What Bonfire can do in Bloomberg Terminal
Real actions from the Bloomberg Terminal API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| List catalogs | Catalogs | GET /eap/catalogs/ |
| Create security universe | Universes | POST /eap/catalogs/{account}/universes/ |
| Get universe | Universes | GET /eap/catalogs/{account}/universes/{universeId}/ |
| Create field list | Field Lists | POST /eap/catalogs/{account}/fieldLists/ |
| Submit data request | Requests | POST /eap/catalogs/{account}/requests/ |
| Get request | Requests | GET /eap/catalogs/{account}/requests/{requestId}/ |
| Download response | Responses | GET /eap/catalogs/{account}/content/responses/ |
| Create trigger | Triggers | POST /eap/catalogs/{account}/triggers/ |
Bloomberg Terminal 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
Bloomberg Terminal — questions
Can Bonfire automate Bloomberg Terminal?
Yes. Bonfire runs on your machine, holds your Bloomberg Terminal credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the Bloomberg Terminal API to run the actions you ask for in chat.
Does my Bloomberg Terminal 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.