{"slug": "outsideflow-ai-spend-less-time-planning-and-more-time-outside", "title": "OutsideFlow AI: Spend Less Time Planning and More Time Outside", "summary": "A developer built OutsideFlow AI, a local, open-source outdoor activity planner that uses a locally running open-weight model (Gemma 3 1B via Ollama) to turn a user's available time, mood, and environment into a short structured outdoor plan. The React/Vite frontend and Node.js/Express backend prompt the model for JSON output, then push the user to put the phone away and go outside. The project was submitted to the Hacktoberfest 2026 Open-Source AI Challenge Week 1: Touch Grass.", "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\nI built **OutsideFlow AI**, a local AI-powered outdoor activity planner designed to do something slightly unusual for an AI application:\n\n**get people away from the screen.**\n\nA lot of apps are designed to increase engagement and keep users inside the application for as long as possible.\n\nOutsideFlow does the opposite.\n\nThe user opens the app, tells it how much free time they have, how they are feeling, and what kind of outdoor environment is available.\n\nFor example:\n\n```\nAvailable time: 30 minutes\nMood: Relax\nEnvironment: Neighborhood\n\nExtra preference:\nI want something quiet and I don't want to spend money.\n```\n\nOutsideFlow then uses a locally running open-weight AI model to create a short outdoor plan.\n\nA generated plan might look like this:\n\n```\n30-Minute Neighborhood Reset\n\n1. Walk outside without headphones — 10 min\n2. Notice three things you normally ignore — 7 min\n3. Sit somewhere quiet and observe your surroundings — 8 min\n4. Walk home at a comfortable pace — 5 min\n```\n\nThe user then clicks:\n\n```\nStart Outdoor Session\n```\n\nand the app displays one final message:\n\nPut your phone away and go 🌿\n\nThat is the main idea behind the project.\n\nThe screen should be the shortest part of the experience.\n\nOutsideFlow is for people who want to spend more time outdoors but sometimes get stuck deciding what to do.\n\nSomeone may only have 15 or 30 minutes available.\n\nThey may want to relax, exercise, explore, or do something social.\n\nInstead of spending another 20 minutes searching online for ideas, OutsideFlow creates a simple plan in seconds and encourages the user to leave the screen.\n\nHere is a short video showing OutsideFlow AI in action:\n\n**YouTube Demo:**\n\nThe demo shows:\n\nThe complete source code is available on GitHub:\n\n**GitHub Repository:**\n\nOutsideFlow AI is a local AI-powered outdoor activity planner built for the **Hacktoberfest 2026 Open-Source AI Challenge Week 1: Touch Grass**.\n\nThe goal is simple:\n\nSpend less time planning. Spend more time outside.\n\nOutsideFlow asks the user for a few preferences, generates a personalized outdoor plan using a locally running open-weight AI model, and then encourages the user to put the phone away and actually go outside.\n\nThis project was built for the Hacktoberfest 2026 theme:\n\n**Touch Grass**\n\nThe challenge asks participants to build something with open-source AI that gets people off the screen and into the real world.\n\nOutsideFlow is designed specifically around that idea.\n\nThe screen is only used for a short planning step.\n\nAfter the outdoor plan is generated, the user starts the session and is encouraged to:\n\nPeople often want to take…\n\nOutsideFlow is a small full-stack application built with:\n\nOutsideFlow follows a simple architecture:\n\n```\nUser Preferences\n       ↓\nReact Frontend\n       ↓\nNode.js / Express Backend\n       ↓\nOllama\n       ↓\nGemma 3 1B\n       ↓\nStructured Outdoor Plan\n       ↓\nReact Session Screen\n       ↓\nPut the phone away and go outside\n```\n\nThe frontend is built with React and Vite.\n\nThe user selects:\n\nThe frontend sends those values to the backend.\n\nThe backend is built with Node.js and Express.\n\nIt receives the user's preferences and creates a prompt for the AI model.\n\n```\n{\n  \"time\": \"30\",\n  \"mood\": \"Relax\",\n  \"environment\": \"Neighborhood\",\n  \"note\": \"I want something peaceful and I don't want to spend money.\"\n}\n```\n\nThe backend asks Gemma to return structured JSON.\n\nExample:\n\n```\n{\n  \"title\": \"30-Minute Quiet Neighborhood Reset\",\n  \"goal\": \"Relax outside with a calm and simple walking session.\",\n  \"activities\": [\n    {\n      \"step\": 1,\n      \"activity\": \"Walk slowly around your neighborhood without headphones\",\n      \"duration\": \"10 min\"\n    },\n    {\n      \"step\": 2,\n      \"activity\": \"Notice three plants or details you usually ignore\",\n      \"duration\": \"7 min\"\n    },\n    {\n      \"step\": 3,\n      \"activity\": \"Sit somewhere quiet and observe your surroundings\",\n      \"duration\": \"8 min\"\n    },\n    {\n      \"step\": 4,\n      \"activity\": \"Walk home at a comfortable pace\",\n      \"duration\": \"5 min\"\n    }\n  ]\n}\n```\n\nThe backend validates and normalizes the response before returning it to React.\n\nOutsideFlow uses:\n\n**Gemma 3 1B**\n\nrunning locally through:\n\n**Ollama**\n\nI chose a small model because this project does not need a huge cloud-based model.\n\nThe AI only needs to understand a few user preferences and generate a practical, structured outdoor plan.\n\nOne part I specifically added for the challenge theme was the outdoor session screen.\n\nAfter generating the plan, the user clicks:\n\n```\nStart Outdoor Session\n```\n\nThe normal planning UI disappears.\n\nThe session screen shows only the essential steps and tells the user:\n\nYour plan is ready. The rest happens outside.\n\nThat was important because I did not want to build an outdoor app that still required the user to stare at the screen throughout the whole experience.\n\nOpen innovation matters a lot for OutsideFlow because the AI is not simply an optional feature.\n\nIt is what makes the personalized planning possible.\n\nA hard-coded application could display a list of generic outdoor ideas.\n\nBut it would struggle to adapt naturally to combinations such as:\n\n```\n15 minutes + Exercise + Beach\n```\n\nor:\n\n```\n60 minutes + Explore + Park + no spending\n```\n\nUsing an open-weight model makes the application much more flexible.\n\nGemma runs locally on the user's machine through Ollama.\n\nThat means the core AI functionality does not need to send every request to a cloud AI service.\n\nA user's preferences can contain personal information.\n\n```\nI am feeling stressed today.\nI only have 20 minutes.\nI want somewhere quiet.\n```\n\nWith local inference, those preferences can remain on the user's own computer.\n\nOutsideFlow does not need a paid AI API every time someone generates a plan.\n\nOnce Gemma is installed locally, the user can generate plans without paying for each request.\n\nThe application is not permanently tied to one AI provider.\n\nBecause the AI layer runs through Ollama, another supported open-weight model could be tested or swapped in later.\n\nOnce Ollama and the model are installed, the core planning feature can run locally without depending on an external AI API.\n\nThat fits the idea behind OutsideFlow especially well.\n\nAn application that encourages people to go outside should not require constant cloud connectivity just to create a simple activity plan.\n\nThe challenge theme made me think differently about how AI applications are usually designed.\n\nMany AI products encourage users to stay inside the interface:\n\n```\nAsk another question\n↓\nGenerate another response\n↓\nKeep scrolling\n↓\nRepeat\n```\n\nOutsideFlow intentionally changes that pattern:\n\n```\nChoose preferences\n       ↓\nGenerate plan\n       ↓\nStart session\n       ↓\nPut phone away\n       ↓\nGo outside\n```\n\nThe AI is there to remove the planning friction, not become the activity itself.\n\nThat is the part of the project I like most.\n\nOutsideFlow was my second Hacktoberfest 2026 project using open-weight AI.\n\nMy first challenge project helped me learn how to run Gemma locally and connect it to a React and Node.js application.\n\nFor this challenge, I focused more on how AI can shape the actual product experience.\n\nI practiced:\n\nOne thing I found interesting is that AI does not always have to increase digital engagement.\n\nIt can also be used to help people leave the screen.\n\nI did not use a DevRelay agent session for this project.\n\nThe application uses a straightforward local AI architecture with Gemma running through Ollama.\n\nI am entering OutsideFlow AI in:\n\nGemma 3 1B is the core AI model responsible for creating the personalized outdoor activity plans.\n\nThe idea behind OutsideFlow is intentionally simple:\n\nUse the screen just long enough to decide what to do, then go do it.\n\nAI is often used to keep people inside digital experiences.\n\nFor this challenge, I wanted to try the opposite.\n\nOutsideFlow uses AI to remove the small amount of planning that can stop someone from taking a break, walking outside, exploring somewhere nearby, or simply getting some fresh air.\n\nThe app creates the plan.\n\nThe actual experience happens outside. 🌿", "url": "https://wpnews.pro/news/outsideflow-ai-spend-less-time-planning-and-more-time-outside", "canonical_source": "https://dev.to/nadunjayaweera/outsideflow-ai-spend-less-time-planning-and-more-time-outside-5211", "published_at": "2026-10-09 19:44:11+00:00", "updated_at": "2026-10-09 19:51:31.505350+00:00", "lang": "en", "topics": ["ai-products", "ai-tools", "generative-ai", "large-language-models", "developer-tools"], "entities": ["OutsideFlow AI", "Hacktoberfest", "Ollama", "Gemma 3 1B", "React", "Vite", "Node.js", "Express"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/outsideflow-ai-spend-less-time-planning-and-more-time-outside", "markdown": "https://wpnews.pro/news/outsideflow-ai-spend-less-time-planning-and-more-time-outside.md", "text": "https://wpnews.pro/news/outsideflow-ai-spend-less-time-planning-and-more-time-outside.txt", "jsonld": "https://wpnews.pro/news/outsideflow-ai-spend-less-time-planning-and-more-time-outside.jsonld"}}