Karevo's machines can sort up to ten tons of potatoes per hour. The AI-powered optical recognition system achieves 95 percent accuracy. The founder's journey took him from a potato farm to the Technical University of Munich (TUM) and ultimately to his own startup.
Karevo "Sorting potatoes is hard work-you stand at the sorting table for hours, checking every single potato while surrounded by noise and dust," says Benedikt Keßler, co-founder of the startup Karevo. He grew up on a potato farm and knows the challenges firsthand. While studying mechanical engineering at TUM, he therefore developed the idea for an automated sorting machine that uses a specially trained AI model.
AI trained with over 100,000 images
The model was trained using over 100,000 images and can identify damage to potatoes with 95 percent accuracy. The machine can detect foreign objects and seven types of defects, such as rot, cracks, and wireworms. A particular advantage is that it also works on unwashed potatoes.
"Other detection methods often reach their limits with unwashed potatoes because they can look very different depending on the region, soil type, or storage conditions," explains Benedikt Keßler. Thanks to the AI model, Karevo can quickly adapt the sorting process to the specific potatoes on the farm.
Designed for Small and Family-Run Farms
"Potato sorting machines are often too expensive, too large, or too complicated to maintain for small farms," says Benedikt Keßler, speaking from experience. That's why Karevo's machines are smaller and more affordable. They also feature a modular design, which makes maintenance easier and allows them to be integrated into existing systems. "I developed the machine that would have taken the back-breaking work off my hands at my parents' potato farm."
Prototypes built at TUM
Benedikt Keßler began working on the technology during his master's thesis at TUM. Together with his friend Johannes von Wittke, an engineering student at the East Bavarian University of Applied Sciences in Regensburg, he searched for additional co-founders. Through UnternehmerTUM, the Center for Innovation and Entrepreneurship at TUM, they found Felix Beck, who had completed his Executive MBA at TUM.
During the startup phase, they participated in the UnternehmerTUM Incubator and founded Karevo in 2024. In the beginning, they tinkered with the prototypes in the Makerspace, UnternehmerTUM's high-tech workshop. They have been successfully on the market since the fall of 2025.
Karevo Entrepreneurship
Entrepreneurship is part of our DNA. Discover the founding ecosystem of TUM, UnternehmerTUM, and the TUM Venture Labs with a wide range of entrepreneurship offerings - from startup consulting to entrepreneurship education.
Andreas Heddergott / TUM The innovation ecosystem centered around TUM is considered one of the most successful deep-tech hubs in Europe. Its particular strengths lie in its strong, diverse network and highly targeted support. Through initiatives and co-labs, startups collaborate with established companies, experts, investors, and government agencies to drive innovation. TUM and UnternehmerTUM, the Center for Innovation and Entrepreneurship , support startup teams with programs precisely tailored to the individual phases of the startup journey and the teams themselves. Across twelve technology fields, the TUM Venture Labs offer direct access to cutting-edge research, technical infrastructure, and market expertise. Each year, more than 100 companies are founded at TUM, and more than 1,000 startup teams are supported by UnternehmerTUM and the Venture Labs. UnternehmerTUM, which invests through its own venture capital fund, has been named Europe's best startup center three times by the Financial Times.
