Quaterline-AI

Quarterline AI compares SEC filings to instantly show what changed, why it matters, and the exact evidence, so you don’t have to read hundreds of pages.

Comment

Inspiration: We were inspired by how long and difficult it is to read financial filings, which can span hundreds of pages. Most people only care about what actually changed, but existing tools focus on vague summaries instead of meaningful differences. This led us to build a solution that highlights key changes with clear evidence.

What it does: Quarterline AI compares a company’s latest SEC filing to its previous one and identifies the most important changes. It explains why those changes matter and provides direct quotes as evidence for transparency. The platform also includes financial visualizations and optional audio summaries for quick insights.

How we built it: We built Quarterline AI using a full-stack architecture with Next.js and React for the frontend and Express with TypeScript for the backend. We used SEC EDGAR APIs to fetch real financial data and Cheerio to extract key sections from filings. Gemini AI Structured Outputs enabled us to generate reliable, schema-based comparisons.

Challenges we ran into: One major challenge was working with SEC APIs, which have strict rate limits and no CORS support, requiring a backend proxy. Extracting clean, structured text from messy HTML filings was also difficult. Additionally, ensuring the AI produced consistent and factual outputs required careful schema design.

Accomplishments that we're proud of: We successfully built a fully functional end-to-end product within a short hackathon timeframe. Our system generates evidence-backed insights rather than generic summaries, making it more trustworthy. We’re also proud of creating a clean, intuitive UI that simplifies complex financial data.

What we learned: We learned how to work with real-world APIs and constraints like rate limiting and data inconsistencies. We also gained experience using structured AI outputs to improve reliability. Most importantly, we learned how to collaborate effectively and build a full-stack product under time pressure.

What's next for Quarterline AI: Next, we plan to add real-time alerts for major filing changes and portfolio tracking for multiple companies. We also want to enhance our analysis with deeper insights and improve the user interface. Long-term, we aim to scale Quarterline AI into a tool used by both individual investors and institutions.

Share this project:

Updates