AWS Elemental MediaConvert AI skills
MediaConvert AI skills let Bonfire's local-first agents call the AWS transcoding API to queue conversions, monitor jobs, and manage output settings, all orchestrated on your hardware so your video pipeline gains automation without a separate cloud control layer.
What Bonfire can do in AWS Elemental MediaConvert
Real actions from the AWS Elemental MediaConvert API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| Associate Certificate | certificates | POST /2017-08-29/certificates |
| Cancel Job | jobs | DELETE /2017-08-29/jobs/{id} |
| Get Job | jobs | GET /2017-08-29/jobs/{id} |
| Create Job Template | jobTemplates | POST /2017-08-29/jobTemplates |
| List Job Templates | jobTemplates | GET /2017-08-29/jobTemplates |
| Create Preset | presets | POST /2017-08-29/presets |
| List Presets | presets | GET /2017-08-29/presets |
| Create Queue | queues | POST /2017-08-29/queues |
AWS Elemental MediaConvert 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
AWS Elemental MediaConvert — questions
Can Bonfire automate AWS Elemental MediaConvert?
Yes. Bonfire runs on your machine, holds your AWS Elemental MediaConvert credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the AWS Elemental MediaConvert API to run the actions you ask for in chat.
Does my AWS Elemental MediaConvert 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.