{"slug": "ecoques-turn-screen-time-into-outside-time", "title": "EcoQues-turn Screen Time Into Outside Time", "summary": "A developer built EcoQuest, an AI-powered outdoor habit-building web app that uses Google's open-weight Gemma 4 model (gemma-4-26b-a4b-it) to turn user-selected time, environment, mood, and difficulty into structured, personalized outdoor quests. The app sends preferences to a server-side /api/generate-quest endpoint, which prompts Gemma 4 to return structured quest JSON with a title, duration, environment, difficulty, description, steps, and an optional bonus challenge, while progress such as outdoor minutes, XP, streaks, and field notes is stored locally in the browser via localStorage. The project is an MVP submitted to the Hacktoberfest Open-Source AI Challenge's Best Use of Gemma category.", "body_md": "*This is a submission for the [Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass](https://dev.to/challenges/hacktoberfest-week1-2026-10-05)*\n\n**EcoQuest** is an AI-powered outdoor habit-building web app designed to help people turn screen time into real-world exploration.\n\nInstead of simply telling people to \"spend less time on their phones,\" EcoQuest gives them something specific to do outside.\n\nUsers choose:\n\nEcoQuest then uses **Google Gemma 4** to generate a personalized outdoor quest.\n\nFor example, a user might choose:\n\n20 minutes · Park · Curious · Easy\n\nand receive a quest such as **The Tree Detective**, with simple observation and exploration steps they can complete outdoors.\n\nThe experience then continues with:\n\n**Choose → Generate → Explore → Complete → Earn XP → Build a Streak → Journal**\n\nThe app tracks outdoor minutes, completed quests, XP, nature streaks, and personal field notes locally in the browser.\n\nEcoQuest is built around a simple idea:\n\n**The goal isn't to spend more time on another app. It's to spend less time on screens and more time in the real world.**\n\n**Live Demo:** [https://ecoquest-txcy.onrender.com/](https://ecoquest-txcy.onrender.com/)\n\nThe live application demonstrates the complete experience:\n\n**GitHub:** [https://github.com/pnkj006/EcoQuest](https://github.com/pnkj006/EcoQuest)\n\nThe project is built as a small, focused MVP with the AI generation layer separated from the frontend.\n\nEcoQuest is built with:\n\nThe core architecture is:\n\n```\nReact Frontend\n      ↓\n/api/generate-quest\n      ↓\nNode.js Server\n      ↓\nGemma 4\n      ↓\nStructured Quest JSON\n      ↓\nPersonalized Outdoor Quest\n```\n\nThe user preferences are sent to a server-side API endpoint. The server asks Gemma 4 to generate a structured quest containing the title, duration, environment, difficulty, description, steps, and optional bonus challenge.\n\nI used **Gemma 4 (`gemma-4-26b-a4b-it`)** because the quest-generation task is short, structured, and highly adaptable to user preferences.\n\nThe model is instructed to create realistic and safe outdoor activities without requiring special equipment. It also avoids dangerous activities, unsafe road crossings, approaching wildlife, disturbing plants or animals, and entering restricted/private areas.\n\nThe rest of the application is intentionally lightweight. User progress is stored locally using `localStorage`, so the MVP does not require authentication or a database.\n\nFor EcoQuest, the AI model isn't just an additional feature. It is the component responsible for turning a user's mood, available time, and surroundings into an actionable outdoor experience.\n\nUsing an open-weight model such as Gemma gives the project a path beyond a single closed AI provider.\n\nBecause Gemma is an open-weight model, the quest-generation layer can potentially be adapted, fine-tuned, evaluated, or eventually self-hosted as the project grows.\n\nThat matters for a project like EcoQuest because the goal is not simply to generate text. The long-term goal is to create an AI system that understands different environments and creates useful, safe, context-aware experiences while keeping the underlying technology more open and adaptable.\n\nFor this MVP, Gemma made it possible to experiment with that idea without building a large recommendation system or manually creating hundreds of quests.\n\nI built EcoQuest with an AI-assisted development workflow and used Antigravity throughout the project for implementation, testing, debugging, and iteration.\n\nThe development process included:\n\nEcoQuest is entering the **Best Use of Gemma** category.\n\nGemma 4 is used as the core AI engine for personalized outdoor quest generation. The model directly transforms the user's selected time, environment, mood, and difficulty into structured quests that drive the main product experience.\n\nEcoQuest is currently an MVP, but there are several directions I would like to explore:\n\nFor now, the most important thing is simple:\n\n**Close the laptop. Go outside. Complete a quest.**", "url": "https://wpnews.pro/news/ecoques-turn-screen-time-into-outside-time", "canonical_source": "https://dev.to/pnkj_mty_4ec833d844e216ec/-ecoques-turn-screen-time-into-outside-time-4422", "published_at": "2026-10-07 11:39:50+00:00", "updated_at": "2026-10-07 11:47:24.651844+00:00", "lang": "en", "topics": ["generative-ai", "large-language-models", "ai-products", "ai-tools"], "entities": ["EcoQuest", "Google", "Gemma 4", "gemma-4-26b-a4b-it", "Hacktoberfest Open-Source AI Challenge", "Antigravity", "React", "Node.js"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/ecoques-turn-screen-time-into-outside-time", "markdown": "https://wpnews.pro/news/ecoques-turn-screen-time-into-outside-time.md", "text": "https://wpnews.pro/news/ecoques-turn-screen-time-into-outside-time.txt", "jsonld": "https://wpnews.pro/news/ecoques-turn-screen-time-into-outside-time.jsonld"}}