FM
Fabian Muoghalu
Back to Case Studies
Full-Stack Application / AI IntegrationProfessional Client Work2025

Masin Advisory Group Platform

Full-stack business platform combining content, events, payments, and AI-powered customer support.

Source code is private due to client ownership.
Live Application

Technologies & Tools

Next.jsReactTypeScriptJavaScriptCloudflare D1CloudflareVercel AI SDKGrokCloudflare AI

Problem Statement

The client required multiple business and customer-facing capabilities to operate within a unified web platform. Instead of managing separate systems for content publishing, events, customer registration, payments, and support, the application needed to bring these workflows together into a single product.

Role & Contributions

Software Engineer. Worked across frontend development, server-side application development, database workflows, event management, payment workflows, AI integration, and Cloudflare infrastructure.

System Architecture & Design

Built as a full-stack Next.js application with server-side logic and Cloudflare D1 for database workflows. The AI support assistant uses the Vercel AI SDK with controlled tool calling (Grok / Cloudflare AI) to invoke predefined application functions for customer inquiries, booking workflows, and delivery-related information.

Key Engineering Decisions

  • 1.Unified Next.js Codebase: Consolidated content management, event booking, payment handling, and customer support into a single maintainable repository.
  • 2.Controlled AI Tool Calling: Integrated Vercel AI SDK with explicit backend tool definitions, ensuring the model invokes specific functions rather than manipulating data directly.
  • 3.Cloudflare Infrastructure: Leveraged Cloudflare D1 for relational database workflows, Cloudflare AI for model execution, and edge infrastructure for media and deployment.

Challenges Overcome

  • Designing robust event registration and seat reservation logic to prevent double bookings during concurrent checkout flows.
  • Enforcing strict boundaries between AI reasoning tools and sensitive payment confirmation pipelines.

Lessons Learned

  • Tool-calling architecture provides safe, predictable bridges between AI models and production business operations.
  • Combining serverless Next.js edge logic with Cloudflare D1 maximizes velocity and keeps operational complexity low.

Results & Impact

  • Successfully built and maintained a production client platform consolidating content publishing, event registration, payments, and AI customer support.
  • Automated customer inquiries and booking-related workflows via controlled AI tool invocation.