Skip to content

AI Research Assistant for Quiet Links

Case Study Summary

Client: Tim Gallati, Founder of Quiet Links
Website: quietlinks.com
Industry: Scientific Research & Knowledge Management

Impact Metrics:

  • Delivered a complete RAG system in 6 weeks
  • Saved client an estimated 1 year of solo development time
  • Enabled natural language queries across 200+ academic papers
  • Instant access to research insights previously buried in documents

Quiet Links needed to transform their static document database into an intelligent, searchable knowledge base that scientists could query in natural language.

Challenge

The client had a growing collection of academic papers and research documents but no way to efficiently search through them. Researchers were spending hours manually scanning PDFs to find relevant information. Tim Gallati, the founder, estimated that building this capability in-house would have taken him approximately one year working alone.

Our Approach

Working alongside Bob Belderbos (Frontend) and Tim Gallati, I designed and implemented the RAG (Retrieval-Augmented Generation) backend system. The solution involved:

  • Document ingestion and chunking pipeline for academic papers
  • Vector embeddings generation for semantic search
  • Integration with Weaviate vector database for efficient retrieval
  • Query processing system that returns contextually relevant answers
  • API endpoints for frontend integration

Results & Impact

  • 6-week delivery: From zero RAG functionality to production-ready system
  • 1 year saved: Client estimated this would have taken him a year to build alone
  • 200+ papers indexed: Full document corpus searchable via natural language
  • Instant answers: Researchers can now "interrogate" the knowledge base directly
  • Summarization: Complex research synthesized into digestible insights

Tech Stack

  • Python
  • Weaviate vector database
  • OpenAI APIs (embeddings & completion)
  • FastAPI for backend services
  • Document processing pipeline (PDF extraction, chunking)

Team & Timeline

  • Timeline: 6 weeks
  • Team Size: 3 people
  • My Role: AI/RAG Engineer (backend architecture, vector search, LLM integration)
  • Collaborators: Bob Belderbos (Frontend), Tim Gallati (Product Owner)

Client Testimonial

"This RAG implementation would have taken me a year to build on my own. Juanjo delivered it in 6 weeks."

— Tim Gallati, Founder of Quiet Links

  • Let's have a virtual coffee together!


    Want to see if we're a match? Let's have a chat and find out. Schedule a free 30-minute strategy session to discuss your AI challenges and explore how we can work together.

    Book Free Strategy Call