# Project export: ZoneZero

This document was generated by HackStack to give an AI agent context about a hackathon project. Sections are labeled with their provenance; content marked as truncated was cut to keep this document small.

## Project metadata

- Hackathon: TreeHacks 2026
- Tagline: Wildfire safety starts at home. We make it actionable. Zone Zero audits homes for wildfire compliance, shows homeowners how to fix risks with a personalized landscaping design.
- Devpost: https://devpost.com/software/zonezero
- GitHub: not linked
- Demo: https://v0-zone-zero-ai-ar.vercel.app/
- Video: https://www.youtube.com/embed/I4zW-v2duYA?enablejsapi=1&hl=en_US&rel=0&start=&version=3&wmode=transparent
- Team: contributor stats unavailable

## Devpost submission (written by the team)

### Inspiration

90% of homes in wildfires burn because of Zone 0 — the first 5 feet around your house. Up to 90% of homes ignite due to wind-blown embers landing in this critical zone. California's Board of Forestry is developing regulations requiring a 0–5 foot ember-resistant zone, but there's a problem: homeowners resist creating Zone 0 because they fear it will look ugly. Our team grew up in California and witnessed firsthand the devastation of wildfires. We spoke with CalFIRE Chief Jake Hess and learned that the #1 barrier to Zone 0 implementation isn't cost or effort — it's aesthetics. Homeowners imagine a “moat” of bare dirt or ugly gravel and simply don’t do it. Meanwhile, their homes remain vulnerable. We realized: what if we could make Zone 0 beautiful? Better yet — what if we could predict which beautiful design each homeowner would actually implement?

### What it does

Zone Zero AI helps homeowners understand wildfire compliance and receive personalized, realistic upgrade recommendations using public imagery and behavioral prediction. Address-Based Risk Scanner Homeowners enter their address We automatically retrieve property imagery using Google Street View and aerial mapping data AI analyzes visible features around the home foundation to identify fire risks: Wood mulch Combustible fencing Dry or dense vegetation Flammable decorative materials Wood mulch Combustible fencing Dry or dense vegetation Flammable decorative materials Users receive a clear LE-100 Zone 0 compliance assessment The system highlights where the home meets or fails defensible space standards Generates visual examples of safer and more attractive material replacements Behavioral Prediction Engine Users complete a 30-second style preference selection AI analyzes architectural style, neighborhood design patterns, and aesthetic preferences Predictive matching: “Homeowners with similar homes and preferences most often chose decomposed granite with a 73% completion rate.” Shows real before/after examples from visually similar homes that completed upgrades Recommends materials and landscaping changes homeowners are statistically most likely to adopt Insurance Integration Dashboard Generates compliance reports suitable for insurance verification Insurers can deploy scans to policyholders to encourage risk reduction Tracks implementation likelihood, compliance status, and projected loss reduction B2B SaaS model: insurers pay per compliance analysis and receive portfolio-level analytics

### How we built it

Frontend Experience React / Next.js responsive web interface Mobile-optimized inspection dashboard Before/after visual comparison modules Compliance scorecards aligned with LE-100 defensible space standards AI & Behavioral Prediction Google Gemini Flash 2.0 powers: Architectural style classification from property imagery Fire risk detection around foundations and landscaping Personalized Zone 0 design recommendations Implementation likelihood scoring based on homeowner behavior patterns Google Gemini Flash 2.0 powers: Architectural style classification from property imagery Fire risk detection around foundations and landscaping Personalized Zone 0 design recommendations Implementation likelihood scoring based on homeowner behavior patterns Custom behavioral model analyzing homeowner decision patterns Custom behavioral model analyzing homeowner decision patterns “Style twin” matching algorithm using visual similarity and geographic proximity “Style twin” matching algorithm using visual similarity and geographic proximity Computer vision pipeline to detect fire risks and combustible materials Computer vision pipeline to detect fire risks and combustible materials Deployment & Infrastructure Vercel deployment with edge functions for low-latency image analysis Serverless architecture for scalable compliance scanning CDN optimization for fast imagery loading PostgreSQL database for user profiles and implementation tracking Data & Analytics Insurance analytics dashboard with real-time compliance metrics Neighborhood aggregation for community-level wildfire risk scoring Privacy-preserving behavioral prediction (no personally identifiable information required) Implementation tracking using homeowner photo verification

### Challenges we ran into

Making Fire-Safe Look Beautiful Fire safety materials (gravel, metal, stone) can appear industrial. We addressed this by: Partnering with landscape designers to create style-specific palettes Curating visually appealing, fire-resistant material combinations Identifying “style twin” homes that demonstrate safe and attractive upgrades Educating users on fire-resistant plant options that maintain curb appeal

### Accomplishments we're proud of

Real-world validation CalFIRE Chief Jake Hess confirmed aesthetics are the #1 implementation barrier Real-world validation CalFIRE Chief Jake Hess confirmed aesthetics are the #1 implementation barrier Clear path to market Insurance companies benefit directly from reduced wildfire claims Clear path to market Insurance companies benefit directly from reduced wildfire claims Technical execution Built functional compliance scanning, behavioral prediction, and insurance analytics in 36 hours Technical execution Built functional compliance scanning, behavioral prediction, and insurance analytics in 36 hours Meaningful impact potential If deployed to 1M homes with a 73% implementation rate, we prevent 650K home ignitions and approximately $3.5B in wildfire losses Meaningful impact potential If deployed to 1M homes with a 73% implementation rate, we prevent 650K home ignitions and approximately $3.5B in wildfire losses Elegant user experience Made complex wildfire compliance understandable through simple address-based analysis and personalized recommendations Elegant user experience Made complex wildfire compliance understandable through simple address-based analysis and personalized recommendations

### What we learned

Behavior Change > Technology Psychological barriers matter more than technical ones Social proof strongly influences home improvement decisions Prediction increases homeowner confidence Neighborhood-level comparisons significantly increase adoption Insurance is the Fastest Go-To-Market Insurance providers already pay for inspections Compliance verification reduces claim payouts Regulatory mandates create urgency Enterprise distribution scales faster than direct consumer sales Network Effects Create Long-Term Advantage More users improve behavioral prediction accuracy More implementations increase social proof data Neighborhood compliance scoring encourages community participation Data compounds over time into a unique wildfire resilience dataset

### What's next

for Zone Zero AI Immediate Next Steps Pilot program with two insurance providers targeting 50K policyholders Launch pilot deployments in high wildfire-risk California communities Expand dataset to improve behavioral prediction performance Develop offline image analysis capabilities for limited connectivity areas 6-Month Roadmap Enterprise insurance partnerships across major California carriers Government distribution partnerships for high-risk communities Contractor marketplace connecting verified Zone 0 installers with homeowners Photo verification workflow for insurance compliance certification Long-Term Vision Expand resilience recommendations to flooding, earthquakes, and hurricanes Scale nationally across wildfire-prone states Develop a comprehensive climate adaptation recommendation platform Provide community-level resilience analytics for policymakers Business Model Evolution Year 1: Insurance verification scanning Year 2: Enterprise analytics subscription platform Year 3: Contractor marketplace revenue sharing Year 5: Multi-hazard climate adaptation platform Impact Metrics If deployed to 1M California homes: 650,000 homes protected from ignition $3.5 billion in wildfire losses prevented 85% reduction in ember-caused ignitions $280M annual revenue impact for insurance partners Behavioral Prediction Performance: 73% implementation rate 6.1× improvement over industry adoption baseline 87% confidence in design recommendation accuracy Zone Zero AI: Beautiful. Safe. Implemented.

## README (from the GitHub repository)

No README available.

## Detected evidence (automated analysis)

No repository was indexed for this project. Claimed technologies below could not be checked against code.
- Google Gemini (technology) — claimed on Devpost, not found in the code
- Vercel (technology) — claimed on Devpost, not found in the code

## Codebase structure

No repository index available.

## Key source files

No repository index available; no source files included.