On Lounge since Oct 2026
Matteo Vitali
Member #956DeveloperL2AI Engineer, Independent
AI Engineer building agentic AI & GenAI products end-to-end · Founder of AO Agents · MSc AI @ USI Lugano
How karma works. Everyone starts with 5. You get +1 each time another member upvotes one of your posts or comments (your own upvotes don't count), and lose it if they take the upvote back. Post what you're building, answer questions and help other members to earn more.
Achievements
Plugged In ×3Connected sources: GitHub, Hugging Face, LinkedIn, X, website.How: Connected 3 sources (GitHub, LinkedIn, X or a website) in Settings
Plugged In×3Featured
Shipper ×2Projects on your profile.How: Added 5 projects to their profile
Shipper×2
Pinned projects
LLMs struggle with clinical adoption because their reasoning lacks transparency. Real medical diagnosis integrates abductive, deductive, and inductive logic. To bridge this gap, we must evaluate LLMs against an epistemic baseline grounded in human reasoning and structured for reproducibility.
This repository contains a reproducibility study of the paper Flowing Through States: Neural ODE Regularization for Reinforcement Learning. The project is developed as the practical examination for the Advanced Topics in Machine Learning course, part of my Master’s Degree in Artificial Intelligence (AY 2025-2026).
Polymarket trading bot for 5/15 minutes crypto bet
Verifera is a verifiable document agent for your knowledge base. It answers questions over your own documents with source-grounded citations, quote verification, and exact passage highlighting. Swap domain packs to reuse it across corpora.
Stack
OpenAI Agents SDK
Qwen
Claude
Gemini
ChatGPT
LangGraph
Vercel
Claude Code
Google AI Studio
Codex
GitHub Copilot
DeepSeek
Gemma
About
AI Engineer building agentic AI & GenAI products end-to-end · Founder of AO Agents · MSc AI @ USI Lugano
Experience
AI Engineer | Agentic AI, LLMs | end-to-end builder | MSc AI · Founders Track @ USI