SearchHack: Build the next layer of AI search

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.

Judges

• Investment Director, Micron Ventures

• Investment Lead, Llama Ventures

• Investor, Foothill Ventures

• Investment Lead, Sixty Degree Capital

• More to come!

Prizes

• 1st place: iPhone 18 Pro + $1500 Telem AI credits + 30,000 Tavily credits

• 2nd place: Apple Watch Series 12 + $800 Telem AI credits + 20,000 Tavily credits

• 3rd place: AirPods 5 + $300 Telem AI credits + 10,000 Tavily credits

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 tokens

• Knowledge 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.

Schedule

• 10:00 – Check-in

• 10:30 – Kickoff, rules, judging criteria, team formation

• 11:00 – Building starts (mentors around all day)

• 5:00 – Submissions due, demo prep

• 5:30 – Judging

• 6:30 – Final presentations

• 7:30 – Winners announced

• 8:00 – Wrap

Projects will be judged on innovation, technical execution, search intelligence, and impact.

Come build something!