{"slug": "touchless-ai-ai-that-wants-you-to-stop-using-it", "title": "TouchLess AI 🌱 — AI That Wants You to Stop Using It", "summary": "A developer built TouchLess AI, an open-source outdoor mission generator that uses Google's Gemma 3 4B model via Ollama to turn screen time into real-world activity. Users pick their available time, environment, goal and difficulty, and the model produces a personalized offline mission; a deliberately minimal \"Phone-Away Mode\" then encourages them to put the phone down, with a second Gemma call generating a grounding response to a post-activity reflection. The stack is Next.js, React, TypeScript and Tailwind on the frontend with Python, FastAPI and Pydantic on the backend, storing everything in browser localStorage with no authentication, database or user tracking.", "body_md": "🌱 What is TouchLess AI?\n\nTouchLess AI is an AI-powered outdoor mission generator that uses Google Gemma 3 to turn screen time into real-world activity.\n\nInstead of giving you another reason to stay on your screen, it generates a personalized mission that encourages you to leave it.\n\ngithub->[https://github.com/ashab683/touchless-AI](https://github.com/ashab683/touchless-AI)\n\nThe user chooses:\n\n⏱️ How much time they have\n\n🌳 Their environment\n\n🎯 Their goal\n\n⚡ Difficulty\n\nGemma then generates a personalized outdoor mission.\n\nAnd then comes the most important part:\n\nPut the phone away.\n\n💡 The Problem\n\nA lot of technology is designed around keeping us engaged for longer.\n\nMore notifications.\n\nMore scrolling.\n\nMore screen time.\n\nI wanted to explore the opposite idea:\n\nCan AI be useful while encouraging us to spend less time using technology?\n\nThat became TouchLess AI.\n\n🔄 How It Works\n\nThe experience is designed as a simple loop:\n\nChoose your preferences\n\n        ↓\n\nGemma generates an outdoor mission\n\n        ↓\n\nStart Phone-Away Mode\n\n        ↓\n\nPut your phone away\n\n        ↓\n\nGo outside\n\n        ↓\n\nComplete the mission\n\n        ↓\n\nWrite a short reflection\n\n        ↓\n\nGemma generates a grounding response\n\n        ↓\n\nSave the experience locally\n\nThe philosophy is simple:\n\nThe better TouchLess AI works, the sooner you should stop using it.\n\n🧠 Gemma at the Core\n\nGemma is at the core of the TouchLess AI experience.\n\nBefore going outside\n\nGemma receives the user's preferences and generates a structured outdoor mission.\n\nInstead of simply saying:\n\n\"Go for a walk.\"\n\nthe application can create a more specific activity based on the user's available time, environment, goal and difficulty.\n\n📸 Insert your actual mission screen showing the Gemma-generated mission here.\n\nThis is where the AI turns the user's preferences into an actionable offline activity.\n\nAfter coming back\n\nThe user writes a short reflection about what they noticed or experienced.\n\nGemma then generates a brief grounding response based on that reflection.\n\nSo AI is used at two important moments:\n\nBefore: Help me decide what to do.\n\nAfter: Help me reflect on what I experienced.\n\nThe middle part is intentionally human + offline.\n\n📵 Phone-Away Mode\n\nThis is one of the most important parts of TouchLess AI.\n\nOnce the mission starts, the interface becomes intentionally minimal.\n\n[IMAGE 3 — PHONE-AWAY MODE]\n\nIt includes:\n\n⏱️ A timer\n\n🌿 Minimal visual feedback\n\n📵 A reminder to put the phone away\n\n👀 An optional way to briefly check the mission\n\nThe feature is designed around one principle:\n\nThe application should become less interesting once the mission begins.\n\nThe goal isn't to keep you inside the app.\n\nThe goal is to get you out of it.\n\n🌳 The Real-World Activity\n\nThis is where TouchLess AI becomes different from a typical AI application.\n\nThe AI generates the mission.\n\nThen the user leaves the screen behind and actually completes it.\n\n📸 Insert your outdoor photo/video screenshot here.\n\nThis could be a photo of you completing the mission, a park/nature scene from the activity, or a frame from your demo video.\n\nThe important part is showing that the AI-generated task leads to something outside the screen.\n\n✍️ Reflection\n\nAfter completing the activity, the user comes back and records a short reflection.\n\nFor example:\n\n\"I noticed how quiet the park was once I stopped checking my phone.\"\n\nThe reflection becomes the input for the second AI interaction.\n\nGemma then responds with a short grounding reflection rather than trying to keep the user engaged in another conversation.\n\n🛠️ How I Built It\n\nFrontend\n\nNext.js\n\nReact\n\nTypeScript\n\nTailwind CSS\n\nBackend\n\nPython\n\nFastAPI\n\nPydantic\n\nAI\n\nGoogle Gemma 3 4B\n\nOllama for local inference\n\nStorage\n\nBrowser localStorage\n\nThe current application has:\n\nNo authentication\n\nNo database\n\nNo user tracking\n\nNo unnecessary data collection\n\nThe project is designed to keep the experience simple and local-first.\n\n🏗️ Architecture\n\nThe current local architecture looks like this:\n\n┌──────────────────────┐\n\n│   Next.js + React    │\n\n│      Frontend        │\n\n└──────────┬───────────┘\n\n           │\n\n           ▼\n\n┌──────────────────────┐\n\n│      FastAPI         │\n\n│       Backend        │\n\n└──────────┬───────────┘\n\n           │\n\n           ▼\n\n┌──────────────────────┐\n\n│       Ollama         │\n\n│   Local Inference    │\n\n└──────────┬───────────┘\n\n           │\n\n           ▼\n\n┌──────────────────────┐\n\n│      Gemma 3 4B      │\n\n└──────────────────────┘\n\nI used structured responses and validation so that the frontend receives predictable mission and reflection data from the AI service.\n\n🔓 Why Open Innovation?\n\nThe interesting question for me wasn't just:\n\n\"What can AI generate?\"\n\nIt was:\n\n\"What should we use AI for?\"\n\nOpen-weight models make it possible to experiment with AI in different directions and build applications around ideas that don't necessarily fit the usual engagement-driven model.\n\nTouchLess AI is my small experiment in that direction.\n\nInstead of using AI to keep someone on a screen longer, I'm using it to help them leave the screen.\n\n🎥 Demo\n\nThe demo follows the complete experience:\n\nConfigure\n\n   ↓\n\nGenerate with Gemma\n\n   ↓\n\nPhone-Away Mode\n\n   ↓\n\nGo Outside\n\n   ↓\n\nComplete Mission\n\n   ↓\n\nReflect\n\n   ↓\n\nGemma Response\n\n   ↓\n\nHistory\n\n[VIDEO / GIF — OPTIONAL]\n\n📹 Insert your 60–90 second demo video or GIF here if DEV supports your chosen format.\n\nThe demo should show the actual application rather than only the source code.\n\n💻 Source Code\n\nThe complete project is open source.\n\n🔗 GitHub:\n\n[https://github.com/ashab683/touchless-AI](https://github.com/ashab683/touchless-AI)\n\nThe repository contains the frontend, FastAPI backend, AI service layer, prompts, configuration and documentation.\n\n📚 What I Learned\n\nBuilding TouchLess AI helped me learn more about:\n\nIntegrating an open-weight AI model into a real application\n\nBuilding a FastAPI backend\n\nConnecting a Next.js frontend to an AI service\n\nWorking with structured AI responses\n\nValidating AI-generated data\n\nDesigning a local-first experience\n\nBuilding an interface where less interaction is actually better\n\nThinking about AI from a human-behavior perspective\n\nThe biggest lesson was probably this:\n\nGood AI doesn't always need to give you more to do. Sometimes it should help you do less on your screen.\n\n🚀 What's Next?\n\nSome improvements I'd like to explore:\n\n🌳 More diverse outdoor missions\n\n🧠 Better personalization\n\n♿ More accessibility improvements\n\n💾 More local-first functionality\n\n🤝 Community-contributed missions\n\n🤖 Additional open-model inference options\n\n📱 Better mobile/PWA experience\n\n📊 More ways to measure meaningful offline activity\n\n🌍 Final Thought\n\nWe already have plenty of technology competing for our attention.\n\nMaybe we also need technology that knows when to let us go.\n\nTouchLess AI is an experiment in exactly that. 🌱\n\nIf you had 30 minutes away from your phone, what outdoor mission would you want an AI to give you?", "url": "https://wpnews.pro/news/touchless-ai-ai-that-wants-you-to-stop-using-it", "canonical_source": "https://dev.to/mohd_ashab_6fe0c714df666b/touchless-ai-ai-that-wants-you-to-stop-using-it-4fg2", "published_at": "2026-10-07 21:30:13+00:00", "updated_at": "2026-10-07 21:47:00.315305+00:00", "lang": "en", "topics": ["ai-products", "generative-ai", "large-language-models", "ai-tools", "developer-tools"], "entities": ["TouchLess AI", "Google Gemma 3", "Ollama", "Next.js", "React", "FastAPI", "Pydantic", "GitHub"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/touchless-ai-ai-that-wants-you-to-stop-using-it", "markdown": "https://wpnews.pro/news/touchless-ai-ai-that-wants-you-to-stop-using-it.md", "text": "https://wpnews.pro/news/touchless-ai-ai-that-wants-you-to-stop-using-it.txt", "jsonld": "https://wpnews.pro/news/touchless-ai-ai-that-wants-you-to-stop-using-it.jsonld"}}