Amazon Seller Central AI chatbot
Amazon Seller Central AI chatbot access lets you ask about orders or inventory by messaging Bonfire in Slack. Running on your machine, it uses your Seller Central context to respond conversationally, so marketplace data informs the AI while staying local.
What Bonfire can do in Amazon Seller Central
Real actions from the Amazon Seller Central API that a Bonfire agent can run on your behalf, on-device.
| Action | Resource | Method · Endpoint |
|---|---|---|
| List orders | Orders | GET /orders/v0/orders |
| Get order | Orders | GET /orders/v0/orders/{orderId} |
| List order items | Orders | GET /orders/v0/orders/{orderId}/orderItems |
| Search catalog items | Catalog | GET /catalog/2022-04-01/items |
| Create/update listing | Listings | PUT /listings/2021-08-01/items/{sellerId}/{sku} |
| Get inventory | Inventory | GET /fba/inventory/v1/summaries |
| Create report | Reports | POST /reports/2021-06-30/reports |
| Submit feed | Feeds | POST /feeds/2021-06-30/feeds |
Amazon Seller Central 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
Amazon Seller Central — questions
Can Bonfire automate Amazon Seller Central?
Yes. Bonfire runs on your machine, holds your Amazon Seller Central credentials locally, and a connected model (Claude, GPT, Gemini or Grok) drives the Amazon Seller Central API to run the actions you ask for in chat.
Does my Amazon Seller Central 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.