Stock, reorder, suppliers.
Most small operations track stock in a spreadsheet until the day a bestseller hits zero and nobody noticed. The fix the software industry sells you is a full inventory suite with per-user logins, a mobile app you didn't ask for, and a monthly bill that assumes you run a warehouse. If you just need to see what's low and update a count, that's overkill you rent forever. This blueprint builds the lean version, a dashboard that tells you what to reorder and gets out of the way.
An inventory dashboard built around one table: SKU, quantity, reorder point, and supplier for every item. On top of that, a low-stock alert view surfaces anything at or below its reorder point, so what you care about most is one click away. Filtering and sorting let you slice the list by supplier or hunt down a specific SKU, and a simple form updates quantities without a spreadsheet round-trip.
You watch it come together in the task workspace: the agent scaffolds the project, wires the table and the alert logic, starts the dev server, and confirms it renders before handing you a live preview. The code lands on a branch in your repository with a pull request ready.
The first version is a base you steer with plain follow-up messages:
Each follow-up wakes the same repository and the agent continues on its own code.
Where does my stock data live? In your app, in your repository, under your account. No third-party inventory service sits between you and your numbers.
Can more than one person use it? Ask the agent to add logins and it will; the starter version assumes a single operator so it works the moment it's built.
Can it handle multiple locations? Yes, tell the agent you stock in more than one place and it adds a location column and filter to match.