{
  "id": 12815109,
  "title": "I Asked AI a Question. Then It Told Me to Put My Phone Away.",
  "url": "https://urgent.news/2026/10/08/i-asked-ai-a-question-then-it-told-me-to-put-my-phone-away",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-08T07:20:44.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/techgendm/i-asked-ai-a-question-then-it-told-me-to-put-my-phone-away-5d7h"
  },
  "original_language": "en",
  "account": "This is a story about OpenField, an AI-powered application that turns your curiosity about a nearby location into a short, structured field study. Instead of keeping you on the screen, OpenField encourages users to step away and observe the real world firsthand. Here's the story in plain prose:\n\nWhat is OpenField?\nOpenField is an open-source AI tool designed to help users conduct short field studies about their surroundings. Unlike most AI applications that keep users on the screen, OpenField prompts users to observe the real world, record their findings, and let the AI analyze the evidence. The project was built during the Hacktoberfest Open-Source AI Challenge Week 1 and is licensed under the MIT License.\n\nHow does it work?\n1. The user asks a question about their surroundings, specifies a location, and sets a time budget (15, 30, 45, or 60 minutes).\n2. Gemma, a local AI model powered by Ollama, turns the user's question into a structured Field Protocol. This includes 4-6 steps, evidence requirements, time estimates, safety guidance, and an optional audio briefing script.\n3. The user leaves their phone behind and follows the Field Protocol, observing the real world, recording notes, counts, and photos.\n4. When they return, they input their observations into OpenField, which analyzes the evidence and generates a Field Report.\n5. The Field Report is divided into three parts: Observed (what was actually recorded), Inferred (reasonable conclusions based on the evidence), and Uncertain (what the evidence cannot support yet).\n\nTesting the workflow\nThe author tested the complete OpenField workflow by simulating a study to determine which side of their street stays shaded the longest during a specific time of day. By comparing the two sides at several points during a 30-minute window, the author recorded 5 observation notes, 4 shade observations, and 3 photos. Gemma then analyzed the evidence and concluded that the left side of the street appeared to remain shaded for longer during the tested period. However, the study was too short to establish a strong long-term pattern.",
  "summary": "This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built Most AI tools are designed to keep you talking to them. I wanted to build one that sends you away. OpenField turns a question about your surroundings into a short field study. You type something you are curious about, like \"Which side of my street stays shady the longest?\" , then add a place and a…",
  "key_points": [
    "OpenField is an open-source AI tool for short field studies of surroundings.",
    "Users ask questions, set time budgets, and follow AI-generated Field Protocol."
  ],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}