Welcome to SearchHack: Build the Next Layer of AI Search
AI has changed how people search, but most of what’s out there is still a search box with an LLM attached. We think the interesting work is a layer deeper, and we want to spend a day building it with you.
SearchHack is a one-day hackathon for engineers, researchers, and founders working on how information gets found, retrieved, routed, and remembered by AI systems.
Requirements
The problem
AI systems have too much information and not enough sense of what to do with it. Context gets fragmented, retrieval is expensive, personalization is weak, memory is limited, and routing across different sources is mostly guesswork. Keyword search doesn’t solve this, and neither does putting a chatbot on top of it.
What to build
Anything that makes AI search meaningfully better. Some directions we’d love to see:
- Retrieval that goes beyond keyword matching
- Long-context and memory systems
- Routing queries to the right engine, database, or tool
- Agents that plan, search, verify, and synthesize across sources
- Faster, cheaper retrieval with fewer wasted tokensKnowledge graphs and connecting scattered information
- Search that understands a user’s context and history
- Search across images, video, audio, and code
- New interfaces for working with information
You don’t have to stick to this list. If you have a better idea, build that.
Come build something!
Prizes
First Place
iPhone 18 Pro + $1500 Telem AI credits + 30,000 Tavily credits
Second Place
Apple Watch Series 12 + $800 Telem AI credits + 20,000 Tavily credits
Third Place
AirPods 5 + $300 Telem AI credits + 10,000 Tavily credits
Judges
Tian Yu
Micron Ventures
Mohan Zhang
Sixty Degree Capital
Ara Kyi
Sky9 Capital
Sophia Yu
Foothill Ventures
Kyle Qi
Llama Ventures
Paula Ramoneda
Plug and Play
Judging Criteria
-
Innovation
-
Technical Execution
-
Search Intelligence
-
Impact
Questions? Email the hackathon manager

