Problem: Many organizations still process invoices manually by reading PDF documents and entering key details (invoice number, vendor, amount, etc.) into systems. This process is slow, error-prone, and difficult to scale, and it also makes it harder to detect duplicate invoices or incorrect totals.

Solution: This project builds an automated invoice processing pipeline that converts uploaded invoice PDFs into structured data. It uses OCR to extract text, LLMs to identify invoice fields, validation checks to ensure correctness, and Kafka-based event streaming to manage the processing pipeline. The extracted data is stored in PostgreSQL and visualized through a dashboard, enabling faster, scalable, and more reliable invoice processing.

Very real problem. Manual invoice processing is still surprisingly common and becomes a huge bottleneck as companies scale. Automating extraction and validation with AI can save a lot of operational time and reduce errors significantly.

https://wired-stray-77779333.figma.site/

SaaS Dashboard UI Concept

This project presents a modern SaaS analytics dashboard designed for business intelligence and data monitoring. The interface focuses on clarity, usability, and efficient data visualization.

The dashboard provides a structured layout that allows users to quickly understand key metrics, monitor performance trends, and track recent activities within the platform.

Main features include: • Key performance metric cards (Revenue, Active Users, Signups, Conversion Rate) • Revenue analytics charts and user growth tracking • Recent activity feed for platform updates • Transaction table displaying payments and customer data • Clean sidebar navigation and top search interface

Tools used: Figma UI Design Product Design