The SAI Update magazine (Nov 2025 , sia.be) selected two projects from our Human–AI Interaction (HAII) course for its Next Technology Generation special. Proud of our students Linsey Helsen and Xander Vervaecke who turned their Human-AI Interaction project ideas into concrete, useful systems.
1) A Multi-Agent Approach to Fact-Checking (, ) — Xander Vervaecke (UHasselt) Xander’s LieSpy.ai coordinates multiple LLMs (e.g., GPT, Gemini, Mistral) to verify claims, compare reasoning, and aggregate evidence into a transparent verdict. The interface exposes sources, trust scores, and model rationales, moving fact-checking beyond a single-model answer. Key ideas: multi-agent collaboration, cross-validation, explainability.
2) Playground Assistant: How AI Makes Youth Work Smarter (, ) (in Dutch: Speelplein Assistent: Hoe AI het jeugdwerk slimmer maakt) — Linsey Helsen (UHasselt) Linsey’s assistant supports youth-leaders with four modules: game generator, day structure, materials inventory, and a theme chatbot that can schedule activities directly in Google Calendar. Built with Gemini, LangGraph, and Streamlit; the core advantage is local context—knowing the actual materials on hand. Key ideas: task automation, context grounding, lightweight tool use.
Read the special issue: SAI Update — November 2025 from sia.be.