Multi-Modal AI for Education Hackathon @ Snowflake | Beta Fund × Epic

🛑 Learning was never text-only. Kids read out loud, scribble on worksheets, point at diagrams, and think with their hands. Now AI can hear, see, and watch too. SVAI Arrival Guide .pdf Multi-Modal AI for Education A text box only catches what a student types. A great teacher notices much more: the pause before a hard word, the crossed-out step in a math problem, the moment a class goes quiet. Multi-modal AI can finally pick up those signals. Voice, handwriting, images, and video can all become part of how we teach. The hard part isn't the demo. It's building tools that teachers and families actually trust, and showing that students really learned more. That takes clear learning outcomes, not just a clever model. Join Beta Fund and co-host Epic at Snowflake's Silicon Valley AI Hub in Menlo Park for a full day of building multi-modal learning tools. The day includes a panel with voices from Epic, Khan Academy, and Dex on where AI education is headed, plus demos in front of the room. Build tutors that listen. Build tools that see the work. Build learning you can measure. ⚠️ Approval required. About 120 builders. You need an approved registration to get in: no walk-ins, no +1s. Bring your laptop. 🛠️ Join our Discord for credits, team formation, and support: https://discord.gg/cswGFwFumn · 2-4 builders per team Format One-day, build-first hackathon in Menlo Park 2-4 builders per team Every project uses at least two modalities: text plus voice/audio, images/handwriting, or video Working demo required (3-minute demos) Use public, synthetic, or consented data only. No real student records. Hosts & Co-host 💡 Beta Fund｜Silicon Valley fund backing AI founders from inception to seed. Invests $200K–$3M and is built on the Beta community of 500+ startups and 300,000+ founders. 💡 Beta University｜Runs an 8-week pre-acceleration program that helps early-stage founders build VC-ready companies with proven know-how from Silicon Valley. Apply now! 📚 Epic｜Co-host. The leading digital library for kids 12 and under, with 40,000+ books, audiobooks, and learning videos from 250+ publishers, used by teachers and families. Epic also co-hosted our AI + Education Hackathon at Stanford in September. Venue Sponsor 📍 Snowflake Silicon Valley AI Hub｜Our venue for the day, Snowflake's AI hub in Menlo Park. Thank you to Snowflake for hosting us. 📅 Agenda 9:00 AM Check-in & Breakfast 10:00 – 10:20 AM Opening remarks and kickoff 10:20 – 11:00 AM 🎤 Panel: What Multi-Modal AI Changes in Learning, with speakers from Epic, Khan Academy, and Dex Panelists include Julia Horowitz, Head of Content at Epic 11:00 AM Build 12:00 PM Lunch 1:00 PM Build 4:00 PM Hard submission deadline 4:00 – 4:50 PM Demos (2 min limit) 4:50 – 5:00 PM 🏆 Audience voting and award ceremony Judges Charis Liang, Product Manager & UX Lead at Epic Focus Tracks 🎙️ Track 1 · Voice & Audio Tutors Tutors that listen as well as talk. Hear a student read or think out loud, catch exactly where they get stuck, and respond like a patient coach. Ideas: a read-aloud fluency coach that hears which words a kid stumbles on · a think-aloud math tutor that spots the misconception in a spoken explanation · a speaking partner for language learners · voice-first learning for students with dyslexia or low vision ✍️ Track 2 · Vision, Handwriting & Documents Learning happens on paper. Build AI that reads handwritten work, worksheets, diagrams, and textbook pages, and gives feedback on the steps, not just the final answer. Ideas: snap a photo of handwritten math and get step-by-step feedback · grade a stack of scanned worksheets and group the common mistakes · turn a picture-book or textbook page into an interactive lesson · understand a student's science diagram or lab sketch 🎥 Track 3 · Video & Classroom Understanding Video holds a lot of what happens in teaching and learning. Turn lectures, demonstrations, and classroom moments into feedback for students and teachers. Ideas: turn a lecture video into chapters, a study guide, and a quiz · give teachers feedback on talk time and questioning from a classroom recording · watch a student's experiment or presentation and coach them on it · a video explainer that adapts to what the learner already knows 📡 Track 4 · Real-Time Multi-Modal Tutors & Agents Tutors that work live, like sitting next to a great teacher. Combine live video, voice, and screen or camera input so the AI sees what the student is doing and helps in the moment. Ideas: a tutor on a live video call that watches a student work a problem and nudges at the right time · a screen-aware coding or homework coach · a phone-camera lab assistant for hands-on science · an AR or camera guide that teaches by pointing at real objects 📖 Track 5 · Multi-Modal Storytelling Stories are how kids learn to read, imagine, and remember. Build AI that blends voice, images, and video into stories that teach, react to the reader, and let kids create their own. Ideas: turn a child's drawing and voice recording into an illustrated, narrated story · an interactive read-along that reacts to how the reader is doing · turn a history or science lesson into a narrated illustrated or video story · kids co-creating a story by voice, with images generated as they talk · multilingual narration that reads the same story in a child's home language 🃏 Wildcard (Open Category) Any multi-modal idea that doesn't fit the tracks above. If it solves a real problem in learning and shows a measurable learning outcome, build it.

Approved registration required. No walk-ins. No +1s. Address shown to approved guests. Hosted by Beta Fund · Co-hosted with Epic · Venue sponsor: Snowflake Silicon Valley AI Hub · Beta University Events