ClimateIQ - AI Acceleration

Published: 1 day ago (December 8, 2025 at 02:34 AM EST)

2 min read

Source: Dev.to

Overview

ClimateIQ is a comprehensive climate‑intelligence platform that showcases how AI coding assistants can speed up the creation of complex, production‑quality cross‑platform applications.

APIs Used

API	Purpose
Google Gemini AI	Powers climate alerts, crop recommendations, eco‑tips, waste scanning
NASA FIRMS	Real‑time fire/thermal anomaly data
OpenWeather API	Temperature, air quality, precipitation data
NREL PVWatts	Solar potential calculations
Planet Labs	Vegetation health (NDVI) data
Storyblok CMS	Community content, events, learning modules

Challenge

Build a feature‑rich climate app that includes:

15+ tools
6 real‑time data layers
AI integrations
CMS‑powered content

All must run on multiple platforms from a single codebase.

Solution

Leverage AI coding assistants together with Uno Platform MCP for contextual, grounded guidance throughout development.

Repository & Demo

GitHub:
Live WebAssembly demo:

AI Tools Used

Tool	Role
Windsurf IDE (Claude)	Primary AI for code generation, debugging, architecture
Google Antigravity IDE (Gemini 3.0 Pro)	Rapid prototyping, API research (e.g., Mapbox vs. Mapsui)
Uno Platform MCP Server	Contextual guidance on XAML, cross‑platform compatibility, Material Design, navigation, platform‑specific adaptations

How AI Accelerated Development

Guidance Provided by Uno Platform MCP

XAML layout patterns & best practices
Cross‑platform compatibility considerations
Material Design integration with Uno Toolkit
Navigation patterns & state management
Platform‑specific adaptations

Example interaction

Me: How do I create a responsive card layout with shadows?  
MCP: Use ThemeShadow, Border styling, and responsive Grid layouts.

Productivity Gains

Component	Approx. Lines	AI‑generated %
XAML Pages	~3,000	~90 %
ViewModels	~2,500	~85 %
Services	~2,000	~80 %
Models	~500	~95 %

Specific Challenges & AI Solutions

Challenge	AI Solution
Emojis not rendering on Linux Skia renderer	Researched font fallback limitations; replaced emojis with styled text badges across 10+ pages
Multi‑step wizard for Solar Savings Calculator	Designed 4‑step wizard architecture, added progress tracking, integrated NREL API calls following Uno best practices
JSON deserialization failing in WebAssembly Release builds	Identified `JsonSerializerIsReflectionDisabled` error caused by .NET trimming; switched to manual `JsonDocument` parsing in 7 service files
Integration of 6 different APIs	Implemented error handling, rate‑limiting, response parsing, caching strategies for each API

Example Code

// AI‑generated NASA FIRMS integration
public async Task> GetFireDataAsync(double lat, double lon)
{
    // Proper error handling, CSV parsing, and data point mapping
    // (implementation omitted for brevity)
}

Design Consistency

Gradient headers on every page
Card‑based layouts with consistent spacing
Accessible color contrasts
Responsive breakpoints

Development Time Metrics

Phase	Traditional Estimate	With AI
Initial prototype	~2 weeks	~2 days
Full feature set	~2 months	~2 weeks
Bug fixes	Hours each	Minutes each
Cross‑platform testing	Days	Hours

Platform Support

Platform	Framework	Status
Windows	`net9.0-desktop`	✅ Working
Linux	`net9.0-desktop` (Skia)	✅ Working
macOS	`net9.0-desktop`	✅ Builds
WebAssembly	`net9.0-browserwasm`	✅ Working

Running the App

# Desktop (Linux/Windows/macOS)
dotnet run -f net9.0-desktop

# WebAssembly
dotnet run -f net9.0-browserwasm

Takeaways

AI + MCP = Grounded Intelligence – The Uno Platform MCP kept AI suggestions relevant and accurate.
Iterative Refinement – Quick feedback loops with AI accelerated learning and reduced rework.
Complex Apps Are Achievable – Tasks that would take months were completed in weeks.
Cross‑Platform Is Real – Write once, run everywhere truly works with Uno Platform.

Built with Uno Platform, .NET 9, Google Gemini AI, Windsurf AI Assistant, and a passion for climate action. 🌍