Skip to content
1st Place

Ashkan + U Jin

Evaluating NYC development sites requires assembling data from 10+ disconnected sources, creating costly bottlenecks for acquisitions teams screening dozens of parcels.

Code Video Cerebral Valley

Core trick

Agents pull zoning, capacity, and regulatory records from 10+ NYC sources and merge them into one source-cited site briefing.

Tags

productivityagents

Description

Evaluating NYC development sites requires assembling data from 10+ disconnected sources, creating costly bottlenecks for acquisitions teams screening dozens of parcels. Using agentic zoning analysis and multi-source data aggregation coupled with agentic vision analysis, our platform enables acquisitions teams to evaluate NYC development sites in minutes, eliminating consultant bottlenecks and accelerating deal flow.
ashkanrdn/DueIntelligence★ 31 forksTypeScriptCreated Mar 21, 2026 · last push Jul 31, 2026

README excerpt

# Due Intelligence

### Agentic, multi-source due diligence for NYC development sites

**First place out of 62 teams — Vercel x Google DeepMind “Zero to Agent” Hackathon NYC.** Built by [Ashkan Radnia](https://github.com/ashkanrdn) and [U Jin Seah](https://github.com/ujseah), with the event hosted in partnership with Cerebral Valley.

Due Intelligence turns an NYC address into a source-grounded site briefing. It brings zoning, development capacity, regulatory constraints, market context, and visual site conditions into one workflow so acquisitions teams can screen parcels in minutes instead of assembling the same facts across disconnected portals.

<p align="center">
  <a href="https://www.youtube.com/watch?v=nN-HnoBNNy8">
    <img src="https://i.ytimg.com/vi/nN-HnoBNNy8/hqdefault.jpg" alt="Watch the Due Intelligence product demo" width="720" />
  </a>
</p>

<p align="center">
  <strong><a href="https://www.youtube.com/watch?v=nN-HnoBNNy8">Watch the product demo →</a></strong>
</p>

## What it does

- **Screens a parcel from one address.** NYC GeoSearch resolves the property, then the app pulls lot, zoning, flood, geometry, and incentive data in parallel.
- **Keeps facts separate from AI judgment.** FAR, buildable area, development scenarios, and constraint scoring are calculated deterministically before Gemini interprets the result.
- **Adds visual site intelligence.** Gemini analyzes Street View and satellite imagery for existing conditions, lot coverage, shadows, neighborh

Team