Awin AI features
Awin AI features in Bonfire Terminal bring local-first automation to affiliate marketing. Connected through the Awin API, Claude, GPT, or Gemini summarize performance, flag reversals, and surface your best-converting programs, while an offline Llama model can handle private, on-device reasoning, all running on your own device.
What Bonfire can do in Awin
Real actions from the Awin API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| List accounts | Accounts | GET /accounts |
| List transactions | Transactions | GET /publishers/{publisherId}/transactions/ |
| List joined programmes | Programmes | GET /publishers/{publisherId}/programmes |
| Get programme details | Programmes | GET /publishers/{publisherId}/programmedetails |
| Aggregate by advertiser | Reports | GET /publishers/{publisherId}/reports/aggregated/publisher |
| Aggregate by creative | Reports | GET /publishers/{publisherId}/reports/aggregated/creative |
| List commission groups | Commission groups | GET /publishers/{publisherId}/commissiongroups |
Awin 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
Awin — questions
Can Bonfire automate Awin?
Yes. Bonfire runs on your machine, holds your Awin credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the Awin API to run the actions you ask for in chat.
Does my Awin 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.