Outside, briefly: a tiny offline AI coach for getting off the screen

Description and use

Outside, briefly creates concise outdoor activity plans from a single mood sentence using a local Naive Bayes classifier, enabling users to leave the screen quickly.

Problem

Many wellness apps encourage walking but keep users checking their phones, making the planning step long and intrusive.

Outcome

The app delivers a short, actionable outdoor mission with transparent decision logic, enabling users to reduce screen time during planning.

Workflow

• User enters a mood sentence and time availability
• Local Naive Bayes classifier tokenizes input and predicts mission type
• Interface displays matched words for transparency
• Mission steps are assembled and adjusted for time and accessibility
• Resulting mission card is shown and can be printed or saved
• User leaves the browser and follows the mission outdoors

Evidence

I built Outside, briefly, a small outdoor activity planner. You describe your mood in a sentence, choose how much time you have, and get a short mission that sends you outside.

Source

The AI core is a transparent, locally trained multinomial Naive Bayes classifier. Forty labeled example phrases in model.js teach it the four outing types.

Source

The app is plain HTML, CSS, and JavaScript with no build step or API key. A service worker caches its files after the first visit, allowing the same flow to work offline.

Source

I tested all four model intents and the 10-minute accessible mission in automated tests. I also used the live site in Chrome with a gardening prompt and confirmed that it produced the care mission.

Source