Plato: A Multimodal Assistant for Your Next Great Meal

At the KXSB AI HackXelerator 2025, the project Plato won in the Multi-Model category for its innovative approach to integrating AI into cooking. Plato, developed by a team led by Peter Bodnar, is a multimodal cooking assistant that uses AI to suggest meals based on available ingredients, nutritional needs, and personal preferences through a conversational interface enriched with visuals and videos. The system, developed in just 20 days, employs a combination of Next.js, TypeScript, Python FastAPI, and various AI services to process natural language and image inputs, generating recipes along with supporting media. Despite facing technical challenges, the team successfully delivered a prototype that shows potential for integration into smart kitchen displays or recipe platforms. Moving forward, the team aims to refine the user experience and explore product market fit, with the hope that Plato could become a widely used kitchen companion, enhancing the cooking experience with AI.

Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.