Multi Model Hackathon

Inside the event

Build what a single model cannot. The next generation of AI products will not come from picking one model. It will come from knowing which models, agents, and modalities to bring together for a real task, then making the system work. With the release of Jeff, it's more important than ever for different kinds of models, whether that's video, audio, image, or classifier, to work together. For SF Tech Week, BuilderBase, Women in AI, and AI Collective are bringing builders together at Frontier Tower for a full day of building, testing, and live demos. The challenge Build an AI product that becomes more useful because it combines more than one model, provider, agent, or modality. Use the right system for each job: reasoning, code, vision, voice, long context, fast inference, or whatever your product needs. Build something a real person would use. By the end of the day, show what it does, why one model would not have been enough, and what the combination unlocks. Who should join Engineers, AI practitioners, designers, and technical founders who want to build something real in a day. No prior hackathon experience required. Bring a laptop, a problem you care about, or the willingness to join a team and start building. Sponsors Anbaric Anbaric builds workflows that combine human steps, agentic steps and coded steps; we don't believe in a world where humans are replaced by AI, but, rather, the AI unlocks human time and creativity by automating boring admin that fills our days. Base44 Base44 is a no-code AI development platform that turns builders' ideas into fully functional apps and websites — no coding required. Prelint Your AI makes decisions. Prelint keeps every decision reviewed, recorded, and traceable. Every pull request gets a 20-second decision review. Swytchcode Legacy APIs and AI agents don't blend. Swytchcode gives agents the implementation knowledge these APIs never documented, then governs every action that runs. This event is part of #SFTechWeek.