Forecast visualization.
Open a typical weather app and count the seconds before you see the forecast: a full-screen ad, a push-notification prompt, a "premium radar" upsell, and somewhere underneath it, the temperature. Meanwhile your location is quietly sold to a dozen data brokers. All you wanted was to know whether you need a jacket. This blueprint builds you a clean dashboard that pulls from an open weather API and shows the forecast with nothing layered on top: you describe it, the agent builds it, and it runs under your own account.
A weather dashboard that fetches live data from an open API and gets straight to the point: current conditions front and center, a 5-day forecast at a glance, and a background gradient that shifts with the weather, so a clear afternoon and a rainy morning feel different the moment the page loads. The fetch is handled cleanly, so it loads fast and degrades gracefully when the network is slow.
You watch it happen in the task workspace: the agent scaffolds the project, wires the API fetch, and confirms the forecast renders and the gradient reacts 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.
Do I need to know how to code? No. You describe the dashboard you want; the agent writes it, verifies it fetches and renders, and ships the code to your repository.
Which weather API does it use? An open one you can swap freely. The API key is yours, kept in your own environment, not routed through anyone else's servers.
Is my location tracked? No. The app asks the weather API for a forecast and nothing more; there is no broker between you and the sky.