Project case study
US Fund Advisor
A production business-funding platform that combines AI analysis with account flows, financial data, payments, communications, document generation, external APIs, and multi-service infrastructure inside one end-to-end application.
Engineering case study by Jonas Viray, Full Stack Developer & AI Automation Engineer
Overview
US Fund Advisor is a multi-service production application where AI analysis sits inside a broader funding workflow. The system combines Next.js and React interfaces with Supabase, Node.js and Express services, OpenAI, Plaid, Stripe, Twilio Voice, Google APIs, AWS S3, Mailgun, PDF tooling, and containerized deployment infrastructure. The engineering scope includes user and business-data flows, validation, account and funding journeys, external integrations, reporting, document generation, communications, and production operations around the AI layer.
engineering summary
Problem → Architecture → Contribution → Result
- Problem
- Business owners needed a simpler way to understand potential funding options without navigating a fragmented process across financial data, lenders, account systems, calculations, and follow-up communication.
- Architecture
- The platform combines Next.js, React, TypeScript, Supabase, Node.js and Express with OpenAI, Plaid, Stripe, Twilio Voice, Google APIs, AWS S3, Mailgun, PDF tooling, and production infrastructure including Docker, Nginx, Traefik, and PM2.
- Contribution
- Worked across the production application stack that surrounds the AI analysis flow, including frontend journeys, backend services, validation, external APIs, account and funding workflows, reporting, document generation, and deployment infrastructure.
- Result
- AI analysis operates as one part of a broader funding application instead of a standalone demo, allowing users to move from business information and financial context toward funding guidance inside the same product experience.
AI / integration engineering notes
- The OpenAI API is part of a broader application stack that also connects funding data, account flows, Plaid, Twilio Voice, Supabase, Google APIs, and backend services.
- AI analysis is embedded into a structured business-funding journey that collects user and company information and turns it into actionable funding guidance.
- The surrounding engineering includes validation, external API integration, reporting and PDF tooling, backend services, and deployment infrastructure so the AI feature operates inside a production application rather than in isolation.
Related service: Backend APIs & Durable Workflow Engineering
Observed product surface
- Free AI analysis flow: answer a few questions to get a funding report
- Loan calculator page
- Sign in / sign up user accounts
- Funding types for established businesses: lines of credit, asset-based, equipment, revenue-based
- Newsletter / free financial course signup and blog knowledge hub
- Trustpilot and Google review links
Public product areas
- Home
- Loans
- Resources / Knowledge Hub
- Loan Calculator
- About Us
- Contact Us
- FAQ
Intended audience · Established U.S. businesses seeking capital (featured tier: companies with $50K+/month revenue)
Planning a system with similar complexity?
Send the requirements, current stack, and constraints. I'll outline how I would structure the system, where the main risks are, and what an implementation path could look like.
More projects
Cynergists AI
An agentic CRM where one AI, Cynessa, runs lead generation, follow-up, booking, campaigns, calls, and websites. It sits on a multi-tenant CRM with approval-gated actions, multi-provider LLM routing, real-time voice, and usage-based billing.
Active Management AI
A production backend for an AI-powered property management platform, using durable workflow orchestration to execute long-running processes across delinquency, maintenance, tenant communication, and compliance-sensitive operations.
Atimonan Laundry Shop
A full booking and service-operations application covering customer scheduling, order status, payments, notifications, and staff administration, backed by Express, Supabase, Redis, and production deployment on Vercel.