DEV Community

S M Tahosin
S M Tahosin

Posted on

How I Built an AI Carbon Footprint Analyzer for Earth Day 2026

#ai #webdev #javascript #tutorial

For Earth Day 2026, I built EcoSense AI — an app that analyzes your carbon footprint in 60 seconds using AI.

The Idea

Most carbon calculators are boring forms with static math. I wanted something that feels quick, uses AI for nuanced analysis, and gives actionable tips.

Architecture 

User -> 4-Step Form -> /api/generate (Cloudflare Function)
                            |
                    Google Gemini 2.0 Flash
                            |
                    JSON: score, grade, tips, pledge
                            |
              /api/memory (Backboard) -> saves results
              Solana donation -> carbon offset
Enter fullscreen mode Exit fullscreen mode

The Prompt Engineering

Gemini returns structured JSON reliably if you're specific. Temperature 0.7 gives the best balance of variety and accuracy.

Persistent Memory with Backboard

Each assessment gets saved to a Backboard thread. Returning users see their progress over time.

Carbon Offsets via Solana

Solana is Proof of Stake — 99.9% less energy than Bitcoin. Perfect for an eco app.

Try It

ecosense-ai.pages.dev

GitHub logo x-tahosin / ecosense-ai

AI Carbon Footprint Analyzer - Google Gemini + Backboard + Solana | Earth Day 2026

🌍 EcoSense AI

AI-Powered Carbon Footprint Analyzer | Earth Day 2026

Live Demo Dev.to

Next.js Gemini Backboard Solana Cloudflare Tailwind

What It Does

Answer 4 quick questions about your daily habits and Google Gemini analyzes your carbon footprint in real-time:

  • Eco Score (0-100) with letter grade and SVG donut chart
  • Estimated annual CO2 compared to global average
  • Impact breakdown by category (transport, diet, energy, shopping)
  • 5 personalized tips to reduce your footprint
  • Earth Day pledge — copy and share on social media
  • Carbon offset — donate SOL via Solana to plant trees
  • Progress tracking — Backboard memory saves your assessments

Architecture

Browser → Static HTML/JS (Cloudflare Pages)
            ↓
         /api/generate → Cloudflare Function → Google Gemini API
         /api/memory   → Cloudflare Function → Backboard API
         
         API keys NEVER reach the browser.

Tech Stack

Technology Purpose
Next.js 16 Static export frontend
Google Gemini 2.0 Flash AI analysis engine
Backboard Persistent memory threads
Solana Carbon offset donations
Cloudflare Pages Hosting + serverless functions
…
View on GitHub

Happy Earth Day! What are you building for the planet?

Top comments (0)