Luis Henrich-Bandis

Work

What I’ve built. More to come.

StudyPDF

An AI study platform that turns lectures, slides, and PDFs into flashcards, practice exams, mind maps, and structured study guides. Students upload, the AI extracts what matters, and what comes out is something they can actually study from at 2am the night before an exam.

studypdf.net ↗
85,000
Registered users
200+
Universities
150k+
Documents processed
$1.5k
MRR
600+
Daily active users
1
Engineer

How it works

One expensive extraction at upload time. A reasoning model reads the document and pulls out topics, and within each topic, the concepts that are discussed, applied, or explained, each tied back to the source page. Every downstream feature (flashcards, practice exams, mind maps, chat) is generated against that same tree, using embeddings of the relevant concept chunks for retrieval. The deep analysis runs once per document, not once per feature. Cost goes down, quality goes up.

StudyPDF architecture: a single expensive extraction feeds every downstream feature

Stack

  • TypeScript
  • Next.js
  • PostgreSQL
  • Pinecone
  • Anthropic API
  • OpenAI API
  • Cloudflare R2
  • Monorepo
  • Self-hosted
  • Claude Code

The rest of the infrastructure is boring on purpose. Boring tech is what runs alone.

My role

Solo. I built and run all of it. The AI pipeline, the backend, the database, storage, auth, the growth side, the support inbox. Between March and December 2025, Moritz Kindler was co-founder and ran the UI/UX and brand work. What you see in the product today is largely his visual identity. We ended things cleanly when the logistics stopped working, and I’ve been running it alone again since January 2026.

More projects below as I write them up.