Skip to content

Showcase FlameGuardAI - https://flameguardai.dlyog.com/ #21

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 14 commits into from
Aug 5, 2025
99 changes: 99 additions & 0 deletions docs/showcase/flameguardai.mdx
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This file is 550+ lines and tries to do both product storytelling and setup documentation. I'd strongly recommend cutting it down to just being a showcase for your project - what it is, what it does, how it works

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Agreed with above; still lots of cutting down that can be done! I would reccommend moving the Claude MCP config section and the Inspiration section to the ReadME of your own github repo. This page should be fairly short (<300 lines) and should only communicate the essentials. @tarunchy

@tarunchy

Original file line number Diff line number Diff line change
@@ -0,0 +1,99 @@
---
title: "FlameGuardAI"
description: "AI-powered wildfire prevention using OpenAI Vision + Perplexity Sonar API"
sidebar_position: 2
keywords: [FlameGuardAI, MCP, External Fire ,AI Home Safety, Home Inspection]
---

## 🧠 What it does

**FlameGuard AIβ„’** 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 β€” it's a personalized research assistant for your home.

### Demo

[![Watch Live video](https://img.youtube.com/vi/EI5yT7_aD6U/0.jpg)](https://www.youtube.com/watch?v=EI5yT7_aD6U)

### Try it out

- [FlameGuard AI](https://flameguardai.dlyog.com)
- [FlameGuard AI MCP](https://flameguardai-mcp.dlyog.com)
- [GitHub Repo](https://github.com/dlyog/fire-risk-assessor-drone-ai)

### Key Features:
- πŸ“Έ Upload a home photo
- πŸ‘οΈ Analyze visible fire risks via **OpenAI Vision API**
- πŸ“š Trigger deep research using the **Perplexity Sonar API**
- πŸ“„ Get a detailed, AI-generated report with:
- Risk summary
- Prevention strategies
- Regional best practices
- πŸ› οΈ Optional contractor referrals for mitigation
- πŸ’¬ 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 β€” **FlameGuard AIβ„’ turns a photo into a plan**.

## βš™οΈ How it works

### The FlameGuard AIβ„’ Process

1. **πŸ“Έ Upload**: User uploads a photo of their property
2. **πŸ‘οΈ AI Vision Analysis**: OpenAI Vision API identifies specific vulnerabilities (e.g., flammable roof, dry brush nearby)
3. **πŸ” Deep Research**: For each risk, we generate a **custom research plan** and run **iterative agentic-style calls** to Perplexity Sonar
4. **πŸ“„ Report Generation**: Research is **aggregated, organized, and formatted** into an actionable HTML report β€” complete with citations, links, and visual guidance
5. **πŸ“§ Delivery**: Detailed report sent via email with DIY solutions and professional recommendations

### πŸ” Deep Research with Perplexity Sonar API

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

- We treat it like a research assistant gathering the best available information
- Each vulnerability triggers multiple queries covering severity, mitigation strategies, and localized insights
- Results include regional fire codes, weather patterns, and local contractor availability

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

### Technical Stack

FlameGuard AIβ„’ 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
- **AI Integration**: OpenAI Vision API + Perplexity Sonar API
- **Cloud-ready**: Built for **Azure App Service** with Dockerized deployment

## πŸ† 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** β€” not just a demo
- Kept the experience simple, affordable, and scalable from the ground up
- Made structured deep research feel accessible and trustworthy

## πŸ“š What we learned

- The **Perplexity Sonar API** is incredibly powerful when used agentically β€” 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 β€” pairing research with guidance makes all the difference.
- Trust and clarity are key: our design had to communicate complex information simply and helpfully.

## πŸš€ What's next for FlameGuard AIβ„’ - Prevention is Better Than Cure

We're just getting started.

### Next Steps:
- 🌐 Deploy to **Azure App Services** with production-ready database
- πŸ“± Launch mobile version with location-based scanning
- 🏑 Partner with **home inspection services** and **homeowners associations**
- πŸ’¬ Enhance Claude/MCP integration with voice-activated AI reporting
- πŸ’Έ Introduce B2B plans for real estate firms and home safety consultants
- πŸ›‘οΈ Expand database of **local contractor networks** and regional fire codes

We're proud to stand with homeowners β€” not just to raise awareness, but to enable action.

**FlameGuard AIβ„’ – Because some homes survive when others don't.**

---

**Contact us to know more: [email protected]**