Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

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

Description and use

Outside, briefly generates short outdoor missions without keeping the phone on screen, using a local Naive Bayes classifier.

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 without keeping the phone on screen, enabling users to take a quick break from the screen.

Workflow

  • User enters a sentence describing mood and time
  • Local tokenizer splits sentence into words
  • Naive Bayes classifier estimates mission type
  • Time and accessibility adjustments applied
  • Short mission card generated and displayed
  • User can print or save the card and exit the browser

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 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

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

  • Record date: 2026-10-06T19:55:46.939Z