This project is one of the Scrum projects with industry partners that were part of the AMOS Summer 2026 Projects. Below please find the video (you may also like the other videos) and the project summary which details the final result of the project. We run these projects every semester, so please be in touch if you would like to motivate one of your own!
Demo Video
Project Summary
| Project name | Ailixir Intelligence |
| Project mission | The mission of this project is to create an MVP that runs on mobile devices. Core functionality includes extracting structured information from uploaded documents, storing and organising it within a personal knowledge base, and enabling conversational querying using RAG with optional enrichment from external knowledge sources such as research papers. The system will demonstrate domain configurability using medical documents as the primary domain and finance as a secondary domain. |
| Industry partner | Andreas Zink |
| Team logo |
|
| Project summary | Every professional domain relies on documents, yet the knowledge they contain
remains fragmented, difficult to interpret, and inaccessible. Medical reports, invoices,
contracts, research papers, and many other document types accumulate over time,
scattering important information across hundreds of pages and multiple years. Users
must manually extract facts, connect them across documents, and interpret
domain-specific terminology, making informed decision-making slow, error-prone,
and often impossible. While general-purpose AI chatbots can answer questions about
individual documents, they struggle to maintain reliable context across large document
collections, frequently losing information or hallucinating when faced with long
histories.
Ailixir Intelligence addresses this challenge by transforming unstructured documents into connected, actionable knowledge. Users can upload or scan documents (e.g., medical reports, invoices, contracts), from which the system extracts domain-specific, meaningful data fields and organises them into a personalised, graph-based knowledge base. Rather than treating documents as isolated files, the platform links information across time and across documents, enabling users to understand trends, relationships, and historical context. An AI-powered chat interface allows users to ask precise, context-aware questions grounded in this structured knowledge base instead of raw document text. At its core, the platform is domain-agnostic and configurable, allowing new extraction schemas and knowledge models to be deployed across a wide range of professional use cases. |
| Project illustration |   |
| Team photo |
|
| Project repository | https://github.com/amosproj/amos2026ss03-ailixir-intelligence |
Discover more from Professorship for Open-Source Software
Subscribe to get the latest posts sent to your email.