The Animal Whisperer in the Spotlight

At the STEAM Challenge 2026, held under the motto “Innovation under Pressure”, six projects competed against each other on March 3, 2026, at Spirgarten Zurich. Among them were Autobike by Daniel Lagnaux and Mark Bezmalinovic from ETH Zurich, and Repair Scanner by Aron Bienge, a master carpenter. The evening was hosted by Sara Taubman-Hildebrand, while comedians Gülsha Adilji, Reena Krishnaraja, and Zukkihund provided additional entertainment with humorous interludes, interpreting the projects in their own way. More than 200 people filled the hall and remained in excellent spirits throughout the two-hour event. One of the projects presented was the Animal Whisperer, initiated by Prof. Dr. Oliver Bendel from the School of Business FHNW. His student at the time, Nick Zbinden, implemented the Cow Whisperer, Horse Whisperer, and Dog Whisperer on his behalf. A multimodal large language model (MLLM) was endowed with the desired capabilities using retrieval-augmented generation (RAG). The system first analyzes and evaluates the body language of cows, horses, or dogs as well as the overall situation. It then provides recommendations for how humans should behave when interacting with the animals. At Animal-Computer Interaction 2024 in Glasgow, Oliver Bendel and Nick Zbinden had already received an award for their paper “The Animal Whisperer Project: A GenAI App for Decoding Animal Body Language and Behavior”. In her interpretation, Gülsha Adilji also saw potential for dating – suggesting that the body language of men could be interpreted as well. Jury member Nathalie Klauser praised the Animal Whisperer Project for incorporating animals. In the end, BlueGreens by Sebastian Haymann took first place. The audience award went to Zurich pupils Nina Zvezdina and Poppy Alexander.