AS-Flow AI β Next-Gen Productivity with Contextual AI
This is a submission for the AI Challenge for Cross-Platform Apps β AI Acceleration.
What I Built
I built AS-Flow AI, a premium cross-platform productivity application designed to help users enter deep work states instantly.
It solves the problem of fragmented focus by combining:
Context-Aware Focus Modes
Ultra-realistic immersive environments (Rain, Beach, Fire, Space) that boost concentration.AI-Driven Planning
An intelligent assistant that builds schedules based on user energy levels.Seamless Cross-Platform Experience
Works on desktop and mobile web with an app-like feel.
Tech Stack
- Core: Next.js 14 (App Router), React, TypeScript
- Styling: Tailwind CSS + Glassmorphism UI
- AI: Contextual AI Agents (Claude) + Local Logic
- State: React Context + Persistent Storage
Demo
π Live Application
https://github.com/AsamaeS/AS-Flow-AI
Screenshots
Test Credentials
Email: asmae@focusflow.ai
Password: demo123
AI Tooling in Action
Building AS-Flow AI using Claude (Antigravity) accelerated development massively.
β‘ 10Γ Faster Feature Implementation
Example request:
"Add a Fire focus mode with crackling audio and a realistic flame animation."
The AI Agent:
- Parsed the project structure (
src/data/focus-modes.ts) - Added the new mode
- Retrieved a royalty-free audio source
- Generated UI code
β±οΈ Time taken: 3 minutes
Without AI: ~1 hour.
π Zero-Shot Bug Fixing
Critical error fixed by the AI:
useLanguage must be used within LanguageProvider
The AI:
- Analyzed the entire component tree
- Detected the provider wrapping issue in
layout.tsx - Implemented a hydration-safe fix with
suppressHydrationWarning
β±οΈ Time saved: 2β3 hours

Using App MCP and Uno Platform MCP
Even though AS-Flow AI uses Next.js, the project followed App MCP philosophy.
π§ App Context Awareness
The AI Agent knew:
- The tech stack (Tailwind, Lucide)
- The folder structure (
src/app/dashboard/...) - How to place new files correctly
- How to apply rebranding to βAS-Flow AIβ across 10+ files
π οΈ AI-Guided Architecture
The AI acted like an architect:
- Recommended extracting
FocusModeCardas a reusable component - Ensured
use clientboundaries for the Audio Player - Created a Clean Service Layer for persistent storage
This approach mirrors the guidance of Uno Platform MCP β AI that understands the full app context.
Cross-Platform Reach
AS-Flow AI runs everywhere:
- π» Desktop β 4-column optimized dashboard
- π± Mobile β Single-column responsive layout
- π Web β Works instantly in any browser
- π Auto Theme β Detects OS dark/light mode
Development Experience
Surprise #1 β Real Pair Programmer
It felt like working with a senior engineer.
For example:
I said βFix the sidebar paddingβ.
It edited the correct file (Sidebar.tsx) and the correct class (p-4).
Surprise #2 β Continuous Momentum
AI handled:
- Boilerplate
- Types
- i18n dictionaries
- Layout issues
- Hydration warnings
This allowed me to focus on design and user experience.
Outcome
I built a production-ready, multi-language, dark-mode productivity platform in under 2 days β normally a multi-week project.








Top comments (4)
Great use but you didn't use the prerequisites - uno platform mcps
Exactly what's the point then? π€
Great use of Ai Tools
thank you for your comment