[360Labs.ai]
{ 360Labs }Case Study
{ Our Products }· Live

AI-Native Real Estate Fund

Built for Bethun Bhowmik (ex-Oracle, ex-Amazon, ex-Ola). Discovers distressed properties (foreclosures, tax liens, probate, short sales) and land for data centers, solar farms, and wind farms. 4 AI agents handle scouting, underwriting, outreach, and deal structuring.

AI-Native Real Estate Fund
// overview

4 AI agents powering a Scout, Underwrite, Outreach, Deal Structure pipeline. 13-rule distress detection engine. XGBoost ML scoring (0-100% investment score). Claude underwriting agent generates Buy/Pass/Watch briefs. Claude deal structuring agent selects from a 9-strategy library. 3D Mapbox with Street View popups. Subscription tier gating across SFR, multifamily, commercial, and land.

// specs

Specifications

AI Agents4 agents: Scout, Underwrite, Outreach, Deal Structure
Detection13-rule distress detection engine with tier-1 definitive and tier-2 probabilistic signals
MLXGBoost ML scoring (0-100% investment score), Claude underwriting agent
StackNext.js, TypeScript, Supabase, Prisma, XGBoost, Claude API, Mapbox GL
// features

Features

  • 013 parallel data providers: ATTOM (8 API endpoints), RESO MLS (OData client), Probate (signal-based detection)
  • 0213-rule distress classification across 2 tiers
  • 03XGBoost on Flask for distress scoring (11 features)
  • 04Claude agents for underwriting briefs and deal structuring from 9-strategy library
  • 053D Mapbox with Street View popups
  • 06Subscription tier gating across SFR, multifamily, commercial, and land
// tech stack

Tech Stack

Next.jsTypeScriptSupabasePrismaXGBoostClaude APIMapbox GLPython

Interested
in AI-Native Real Estate Fund?

Let's discuss how this can work for you.

Get in Touch →
// end of case studyAI-Native Real Estate Fund