I Built an Outdoor Break for the Five Minutes You Already Have
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built A few people tried my first version of Out There and told me it assumed a park and gave them little reason to return the next day. On an ordinary weekday, a pause might fit into a work break, the path across campus, a safe stop during a commute, or a few minutes near home. I changed the app around…
This submission is for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass. The author built an app called Out There to help people find moments of pause in their day. They aimed to address the issue that their first version of the app assumed a park and did not encourage users to return. The app allows users to choose a time frame of five, ten, or fifteen minutes, specify a familiar setting, and indicate what they want to notice during that pause.
The app then generates a question for the user to answer and provides three short steps to follow during their pause. For example, the app might ask how shadows change during strong sunlight and suggest finding a shaded spot to observe. The app also includes a local seven-day rhythm feature, marking a save when a user reflects on their pause.
The app's view updates to show when a user has made room for a pause, but it does not erase previous days if a user misses one. The app does not require an exact location or an account, and it does not collect any personal information. Gemma, an open-weight language model, is used to generate the observation question and three steps based on the user's input.
The server checks the response shape and safety rules before sending the response to Gemma. The app sends mission preferences and optional context to Google's hosted Gemini API, which requires an internet connection. The app's goals are to encourage users to find moments of pause and reflection in their day, and to gather feedback on the effectiveness of the app's design.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.