{
  "id": 607415,
  "title": "Sorting potatoes with AI",
  "url": "https://urgent.news/2026/08/11/sorting-potatoes-with-ai",
  "topic": "ai",
  "section": "AI",
  "published": "2026-08-11T22:00:07.000Z",
  "source": {
    "name": "Phys.org",
    "slug": "phys-org",
    "url": "https://phys.org/news/2026-08-potatoes-ai.html"
  },
  "original_language": "en",
  "account": "Karevo, a startup founded by Benedikt Keßler, has developed an AI-powered optical recognition system for sorting potatoes. The technology can process up to 10 tons of potatoes per hour with 95% accuracy, identifying damage, foreign objects, and seven defect types. Keßler, who grew up on a potato farm, knew the challenges of manual sorting firsthand. His project began as a master's thesis at the Technical University of Munich, where he collaborated with co-founders Johannes von Wittke and Felix Beck. The system's modular, compact design makes it affordable and easy to maintain for small farms, a common issue with existing sorting machines. The AI model was trained on over 100,000 images to adapt to various conditions and potato types.",
  "summary": "Karevo's AI-powered optical recognition system can sort up to 10 tons of potatoes per hour with 95% accuracy. The founder's journey took him from a potato farm to the Technical University of Munich (TUM) and ultimately to his own startup.",
  "key_points": [],
  "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."
}