FlameGuard AI™ - Prevention is Better Than Cure

Inspired by LA fires, FlameGuard AI™ helps homeowners and buyers detect external fire risks and get AI-driven protection strategies—because some homes survive when others don’t. Prevention matters!

Comment 1

🔥 Inspiration

The devastating LA wildfires were more than a tragic event — they were a turning point. While watching homes burn to the ground, I saw a story about one house that miraculously survived. That story stuck with me.

What protected that home? It wasn’t luck. It was planning — fire-resistant materials, defensible space, and design choices made long before disaster struck. This realization — combined with the rising difficulty of securing home insurance — inspired us to build FlameGuard AI™.

We wanted to create a tool that empowers homeowners to take fire risk prevention into their own hands — not just react after it’s too late.

🧠 What it does

FlameGuard AI™ helps homeowners, buyers, and property professionals detect and act on external fire vulnerabilities like wildfires or neighboring structure fires. It’s more than a scan — it’s a personalized research assistant for your home.

Key Features:

  • 📸 Upload a home photo
  • 👁️ Analyze visible fire risks via OpenAI Vision API
  • 📚 Trigger deep research using the Perplexity Sonar API
  • 📄 Get a detailed, AI-generated report with:
    • Risk summary
    • Prevention strategies
    • Regional best practices
  • 🛠️ Optional contractor referrals for mitigation
  • 💬 Claude (MCP) chatbot integration for conversational analysis
  • 🧾 GDPR-compliant data controls

Whether you’re protecting your home, buying a new one, or just want peace of mind — FlameGuard AI™ turns a photo into a plan.

⚙️ How we built it

FlameGuard AI™ is powered by a modern GenAI stack and built to scale.

  • Frontend: Lightweight HTML dashboard with user account control, photo upload, and report access
  • Backend: Python (Flask) with RESTful APIs
  • Database: PostgreSQL (local) with Azure SQL-ready schema
  • Containerization: Dockerized for flexible local or cloud deployment
  • Cloud-ready: Built for Azure App Service with dedicated database support

🔍 Deep Research with Perplexity Sonar API

The real innovation is how we use the Perplexity Sonar API:

  1. After analyzing the uploaded image, we identify specific vulnerabilities (e.g., flammable roof, dry brush nearby).
  2. For each risk, we generate a custom research plan — covering severity, mitigation strategies, and localized insights.
  3. We run iterative agentic-style calls to Perplexity Sonar — treating it like a research assistant gathering the best available information.
  4. The research is aggregated, organized, and formatted into an actionable HTML report — complete with citations, links, and visual guidance.

This kind of structured, trustworthy, AI-powered research would not be possible without Perplexity.

🚧 Challenges we ran into

  • 🔁 Designing multi-step research prompts for Perplexity Sonar that maintain context across multiple fire vulnerabilities
  • 🏠 Building robust image analysis prompts that generalize across diverse home types, lighting, and angles
  • ⏳ Coordinating asynchronous flows between user input, vision analysis, deep research, and report generation
  • ❌ One major challenge: we attempted to automatically retrieve contractor email addresses via Perplexity API to pre-fill outreach requests — with user consent, we wanted to connect homeowners directly to local professionals and even submit quote requests on their behalf.
    • While the idea worked conceptually, the email results from Perplexity were not reliably accurate or complete.
    • For now, we've disabled this feature in the UI, but it's a high-priority enhancement for our roadmap.
    • Future plan: we'll integrate a dedicated MCP server for contractors, allowing us to directly submit quote requests from homeowners in a structured, secure workflow.
  • ⚖️ Balancing speed and depth: AI-generated insights must feel fast, but research quality takes time — designing a UX that handles that tension gracefully was not easy.

🏆 Accomplishments that we're proud of

  • Successfully used OpenAI Vision + Perplexity Sonar API together in a meaningful, real-world workflow
  • Built a functioning MCP server that integrates seamlessly with Claude for desktop users
  • Created a product that is genuinely useful for homeowners today — not just a demo
  • Kept the experience simple, affordable, and scalable from the ground up
  • Made structured deep research feel accessible and trustworthy

📚 What we learned

  • The Perplexity Sonar API is incredibly powerful when used agentically — not just for answers, but for reasoning.
  • Combining multimodal AI (image + research) opens up powerful decision-support tools.
  • Users want actionable insights, not just data — pairing research with guidance makes all the difference.
  • Trust and clarity are key: our design had to communicate complex information simply and helpfully.

💳 Admin Credit System

To help manage resource usage and scale responsibly, we built a credit-based system for users. This allows us to give out free trial credits, support premium usage tiers, and track consumption transparently.

What the Credit System Does:

  • 🧾 Tracks credits per user (free and purchased)
  • ➕ Admins can grant credits
  • ➖ Admins can revoke credits safely (no negative balances)
  • 🔄 Usage is logged with full transaction history
  • 👁️ Credits update in real-time within the admin panel

Admin Panel Features:

  • View current user balances
  • Grant or subtract credits via secure modals
  • Automatically updates the user interface after each action
  • View recent credit transaction history

Credit Transaction Types:

  • admin_grant: credits added by admin
  • usage: credits used by the user for assessments
  • admin_revoke: manual deduction by admins
  • initial_free: signup bonus for new users

Backend Highlights:

  • 🔐 Safe SQL logic with balance checks
  • 📦 Modular logic in credit_utils.py
  • 🧠 Clean REST APIs for credit updates
  • 📝 Full logging of every transaction

We designed this credit system to be simple for admins, transparent for users, and ready for future billing integration.

📊 Market Opportunity (U.S.)

  • 🏠 Home Services & Improvement Market: ~$740B TAM
    Covers home maintenance, upgrades, and safety systems
    Sources: Verified Market Research, GlobeNewswire

  • 🔥 Wildfire & Fire Risk Mitigation: $8.6B → $19.9B
    Rising demand due to climate change & insurance premiums
    Source: Verified Market Research

  • 🧾 Home Inspection Market: ~$4B annually
    Home inspections are required for ~90% of real estate sales
    Source: IBISWorld

  • 💸 Estimated SAM: $100–$150B
    Focused on wildfire-prone homeowners, real estate firms, insurers, and contractors
    (California, Colorado, Oregon, etc.)

  • 🚀 Huge gap in end-to-end solutions that go beyond assessment to action
    FlameGuard AI fills this gap by identifying risks and connecting to local pros

🚀 What's next for FlameGuard AI™ - Prevention is Better Than Cure

We're just getting started.

Next Steps:

  • 🌐 Deploy to Azure App Services with production-ready database
  • 📱 Launch mobile version with location-based scanning
  • 🏡 Partner with home inspection services and homeowners associations
  • 💬 Enhance Claude/MCP integration with voice-activated AI reporting
  • 💸 Introduce B2B plans for real estate firms and home safety consultants
  • 🛡️ Expand database of local contractor networks and regional fire codes

🙏 Thank You

Big thanks to DevPost and Perplexity for making this hackathon possible. Without the Perplexity Sonar API, this level of structured, trusted, AI-driven research would simply not be possible.

We’re proud to stand with homeowners — not just to raise awareness, but to enable action.

FlameGuard AI™ – Because some homes survive when others don’t.

Built With

Share this project:

Updates