Cognitively stimulating experiences are fundamental to supporting the welfare of zoo-housed animals. Puzzle-feeders are often initially engaging, but require frequent human intervention and often lack adaptability to support animals’ sustained cognitive engagement. We developed a modular adaptive puzzle-feeder designed to support user agency, independence, and multisensory feedback. The system was deployed over four weeks with an Arctic fox (Vulpes lagopus) across progressive difficulty levels and piloted with two coatis (Nasua narica). Combining HCI and animal science methodologies, we assessed (1) multisensory engagement, (2) changes in behavioral diversity and habitat utilization, (3) adaptation to puzzle complexity, and (4) impact on human stakeholders. Results show strong sustained engagement (46.5% time-budget), increased behavioral diversity, habitat exploration, strategic problem-solving, and positive keeper and visitor reactions. This work highlights how technology can support animal welfare and visitor experience, and how mixed HCI and ethological methods enable holistic evaluation of enrichment and animal usership.