Menu

How we built a shopping agent
📰

How we built a shopping agent

DEV Community: typescript·Browsa·1 day ago
#jPMIsPB7
#devtotypescript#devto#dev#store#review
Long article (2068 words) — no AI summary yet.
Reading 0:00
15s threshold

Try it: npx open-shopping-agent web (no account needed). Code: github.com/browsa-io/open-shopping-agent

Open Shopping Agent (OSA) is an MIT-licensed agent that takes one request, like "usb-c hub with hdmi and a 6 ft hdmi cable under $60". It searches Amazon, Walmart, eBay, Best Buy, Target and Shopify stores, compares the offers and fills the carts. It can also place the order. That last step is the one that matters, and this post covers how we built it so it can't happen without you.

In short: the model never decides to pay. Approval is data, not a prompt. It names one store and one total in cents. Three separate places check it, and the last check reads the total from the store's page a moment before the click.

The model never holds the trigger

OSA reads pages with plain code first: one adapter file per store. An AI model takes over only when a page changed and the code failed. Either way, the store adapter only reads pages and clicks. The engine ranks offers, applies limits and asks for approval.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.