Ship It: The Operational Agent Hackathon with Snow Leopard AI
On Monday, February 2 (5:00PM - 10:00PM ET) join us for a high-energy hackathon for AI builders.
Build fast and show what’s possible when operational data isn’t the blocker.
Use SnowLeopard.ai to build functional AI agents with live data, no long setups, no tuning MCP servers, and no wasted cycles.
Demo real products, get expert feedback, and walk away with prizes!
Ready to accept the challenge? Join us!
Limited spaces available.
Who should join?
You can turn an idea into a prototype in hours.
You thrive in fast-paced, collaborative environments.
You want to explore new agent ideas and APIs
Get mentor feedback and connect with other builders.
What’s waiting for you?
🎁 Prizes
🛠️ Hands-on expert mentorship
⚙️ Integration support for APIs, workflows, and agent tools
🤝 Collaborative space designed for speed & real-time feedback
Requirements
Use SnowLeopard.ai APIs (plus any other AI tools you like)
Must use a SQLite database (bring your own or choose datasets onsite)
Bring Laptop + charger
Solo or teams up to 4
In-person demo required
Judges:
Deepti Srivastava is the founder and CEO of Snow Leopard AI, helping enterprises build production AI agents powered by live, accurate business data. With nearly 20 years in enterprise data platforms, she was the founding Product Lead for Google Spanner, Head of Product at Observable, and a distributed systems engineer at Oracle.
Ed Solovey is an Associate Professor of the Practice in Electrical and Computer Engineering at Boston University, where he teaches software engineering through a hands-on, collaborative approach that mirrors real-world development. He's worked as a software engineer at Google, Adobe, and Twitter (now X), and is a Founding Engineer at Digits, a fintech company focused on simplifying finance for small businesses.
Why Snow Leopard matters?
Snow Leopard lets agents retrieve live, high-fidelity data at query time, so decisions are made on real, up-to-date business information. It never stores or caches customer data; access is secure, scoped, and explicit. It generates native SQL in real time, avoiding the overhead and inaccuracy of vector/RAG pipelines. The system is fast, reliable, and hits ~95% accuracy out of the box, making it a strong foundation for production-grade agents.