Adobe Premiere AI Integration
Adobe Premiere AI agents run on your own machine through Bonfire Terminal, using your project context to draft edit decisions, log rough cuts, and prep timelines. Because everything stays on-device, your footage and creative work never leave your workstation.
What Bonfire can do in Adobe Premiere
Real actions from the Adobe Premiere API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| Post Cq Actions | cq | POST /.cqactions.html |
| Post Config Adobe Granite Saml Authentication Handler | sling | POST /apps/system/config/com.adobe.granite.auth.saml.SamlAuthenticationHandler.config |
| Post Config Aem Password Reset | custom | POST /apps/system/config/com.shinesolutions.aem.passwordreset.Activator |
| Post Config Aem Health Check Servlet | custom | POST /apps/system/config/com.shinesolutions.healthcheck.hc.impl.ActiveBundleHealthCheck |
| Post Config Apache Felix Jetty Based Http Service | sling | POST /apps/system/config/org.apache.felix.http |
| Post Set Password | crx | POST /crx/explorer/ui/setpassword.jsp |
| Get Install Status | crx | GET /crx/packmgr/installstatus.jsp |
| Get Login Page | cq | GET /libs/granite/core/content/login.html |
Adobe Premiere 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
Adobe Premiere — questions
Can Bonfire automate Adobe Premiere?
Yes. Bonfire runs on your machine, holds your Adobe Premiere credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the Adobe Premiere API to run the actions you ask for in chat.
Does my Adobe Premiere 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.