Final Year Project · AI / EdTech
APIA
An AI tutor that guides first-year students using the Socratic method: instead of giving the answer, it asks the right questions to help them solve it themselves.
Runs entirely on local school servers. No student data ever leaves the campus.
The Problem
When students copy-paste code from ChatGPT instead of working through the problem, they skip the part where actual learning happens. They get the assignment done but never build the intuition.
"We found that using AI assistance led to a statistically significant decrease in mastery. [...] Participants in the AI group scored 17% lower than those who coded by hand."
The Solution
APIA acts as a Socratic tutor. It doesn't give answers. It guides students with questions and hints, forcing them to think critically while still getting 24/7 personalized support.
My Role
As Technical Lead, I benchmarked open-weight LLMs (we selected Qwen-Coder) and designed the local, GDPR-compliant infrastructure so everything runs on school hardware without any data leaving the network.
How it works
A RAG pipeline that reads official course PDFs, so the LLM can reference specific class concepts when guiding students.
Fast Inference
vLLM with 4-bit quantization. One server handles multiple students at the same time with minimal latency.
100% Private
Everything runs on the school's network. No student code or personal data ever touches an external server.
Context-Aware
Docling OCR reads actual course materials. The AI references the exact exercises students are working on.
Results
Presented in February 2026. Selected by the school for a pilot program in 2026-2027.
Pilot next year
Will be used in introductory programming labs
Self-contained deployment
Packaged so the school IT team can install it without us