Building InsightForge: An AI-Powered Business Intelligence Platform with Aurora PostgreSQL and Generative AI
H0Hackathon
Built for the Vercel + AWS Database Hackathon.
InsightForge helps small and medium-sized businesses transform raw sales, inventory, and customer data into actionable insights, forecasts, and AI-generated recommendations.
The Problem
Small and medium-sized businesses generate large amounts of data every day through sales, inventory management, and customer interactions. However, most SMBs cannot afford dedicated analysts or expensive business intelligence tools.
As a result, valuable business data often remains unused inside spreadsheets and CSV files.
I wanted to build a platform that could transform raw business data into actionable insights within minutes.
That idea became InsightForge.
What is InsightForge?
InsightForge is an AI-powered Business Intelligence and Decision Support Platform designed for SMBs.
Users can upload business datasets such as:
- Sales Data
- Inventory Data
- Customer Data
The platform automatically analyzes the data and generates:
- Business Health Scores
- Revenue Insights
- Inventory Analytics
- Customer Analytics
- Risk Detection
- Forecasting
- AI-Generated Executive Reports
The goal is simple:
Help small businesses make data-driven decisions without needing a dedicated analytics team.
The Challenge
One of the biggest challenges was handling different dataset structures.
Every business stores data differently.
For example:
- Revenue may appear as Revenue, Sales, Amount, or Total Value.
- Customer identifiers can have different column names.
- Inventory datasets vary significantly across industries.
To solve this problem, I built a dataset detection and column mapping system that automatically identifies dataset types and maps important business metrics.
This allows InsightForge to work with a wide variety of business datasets without requiring manual configuration.
Why Aurora PostgreSQL?
Database selection was one of the most important architectural decisions.
InsightForge manages highly related business entities, including:
- Users
- Uploaded datasets
- Business health scores
- Forecasts
- AI-generated reports
These relationships require:
- Relational consistency
- Structured querying
- Transactional integrity
- Historical data tracking
Aurora PostgreSQL was a natural fit because it allows InsightForge to maintain relationships between business records while supporting analytical workloads.
Rather than treating uploaded files as temporary inputs, Aurora enables the platform to build a historical business knowledge base that supports long-term trend analysis and forecasting.
Architecture
Frontend
- Next.js
- React
- Tailwind CSS
Backend
- Next.js API Routes
- Prisma ORM
Database
- Amazon Aurora PostgreSQL
AI Layer
- Google Gemini API
Deployment
- Vercel
Key Features
Intelligent Dataset Detection
The system automatically identifies whether uploaded data belongs to:
- Sales
- Inventory
- Customer datasets
Business Health Score
A composite score that evaluates:
- Revenue performance
- Inventory efficiency
- Customer readiness
- Forecast readiness
Forecasting and Risk Analysis
InsightForge identifies business risks and highlights areas requiring attention.
AI Executive Reports
Business leaders receive natural language summaries and recommendations generated from their data.
Lessons Learned
Building InsightForge taught me several important lessons:
- Data quality matters more than model complexity.
- Schema design significantly impacts analytics performance.
- Relational databases remain essential for business intelligence systems.
- AI becomes far more valuable when combined with structured business data.
Future Improvements
Future versions of InsightForge will include:
- Multi-user collaboration
- Real-time data synchronization
- Advanced forecasting models
- Industry-specific analytics templates
- Automated anomaly detection
Conclusion
InsightForge was built around a simple idea:
Businesses should not need a dedicated analytics team to understand their own data.
By combining Aurora PostgreSQL, Next.js, and Generative AI, InsightForge transforms disconnected business datasets into actionable insights, forecasts, and recommendations that help SMBs make better decisions.
Thanks for reading.
The complete source code is available on GitHub:
This is a Next.js project bootstrapped with create-next-app.
Getting Started
First, run the development server:
npm run dev
# or
yarn dev
# or
pnpm dev
# or
bun dev
Open http://localhost:3000 with your browser to see the result.
You can start editing the page by modifying app/page.tsx. The page auto-updates as you edit the file.
This project uses next/font to automatically optimize and load Geist, a new font family for Vercel.
Learn More
To learn more about Next.js, take a look at the following resources:
- Next.js Documentation - learn about Next.js features and API.
- Learn Next.js - an interactive Next.js tutorial.
You can check out the Next.js GitHub repository - your feedback and contributions are welcome!
Deploy on Vercel
The easiest way to deploy your Next.js app is to use the Vercel Platform from the creators of Next.js.
Check out our Next.js deployment documentation for more…
You can try the live application here:
