How we built ThreatLedger — AI-powered NDR on AWS Aurora + Vercel in 72 hours

A team built ThreatLedger, an AI-powered Network Detection and Response dashboard, in 72 hours using AWS Aurora and Vercel. The tool turns raw security logs into actionable threat intelligence, aiming to provide affordable NDR for small businesses. It leverages Aurora with pgvector for semantic search across 21,742 IP reputation records and uses Prisma for type-safe queries.

This post was created for the purposes of entering the H0: Hack the Zero Stack Hackathon. H0Hackathon Small businesses face the same network threats as enterprises but can't afford $100K/year NDR tools. We built ThreatLedger to change that. ThreatLedger is a cloud-native Network Detection and Response dashboard that turns raw security logs into actionable threat intelligence using AI. Live demo: https://threatledger-app.vercel.app https://threatledger-app.vercel.app Aurora gave us a production-ready database from day one. We enabled pgvector for future semantic search across 21,742 IP reputation records. The Prisma + Aurora combination gave us type-safe queries with zero configuration overhead. Getting Prisma 7 working with Aurora on Vercel's serverless environment required configuring PrismaPg adapter with connection pooling and handling SSL correctly. Semantic similarity search using pgvector, MITRE ATT&CK mapping, and real-time log streaming. Built for the H0: Hack the Zero Stack Hackathon H0Hackathon