Connect AI to Billions of Legal Documents — Simon Eskildsen, turbopuffer & Jacob Lauritzen, Legora
Legora helps legal firms search through billions of legal documents.
One of their biggest problems was that fast searches suddenly became very slow—from 100 milliseconds to 20 seconds—because of how document chunks were distributed across thousands of storage locations. Projects that were no longer used ended up on the same storage locations as active projects, forcing every search to load massive amounts of unnecessary data. The solution was to make each project its own storage unit, so inactive projects could sit cheaply in cloud storage. It also solved a security requirement: banks and large firms need to encrypt and isolate each project's data completely separately, so they can delete everything instantly if they want to.
Vibekollen prepared this summary with AI from the original publication. The content belongs to AI Engineer.
More to read
Lumaril, which develops AI software for optimizing industrial production by connecting to existing control systems, raised a $66M Series A at a $400M valuation
Techmeme 3 h ago
DeepSeek open sources Super-Agent as a research prototype, a proactive coding agent it says can monitor group chats for coding issues and suggest solutions
Techmeme 4 h ago
Insurance software maker Guidewire agrees to acquire Hyperexponential, which makes AI-powered insurance underwriting and pricing software, for $1.7B in cash
Techmeme 4 h ago
One word for AI agents in 2027
Nate Herk 8 h ago