About Relataly and Florian Follonier
Relataly is a practical AI blog. It shares hands-on, first-hand knowledge about applying machine learning, Python, and generative AI to real problems — from classic model building to today’s LLMs, RAG, and AI agents.
The site focuses on:
- Machine learning and data science — metrics, model evaluation, feature engineering, classification, clustering, and time-series forecasting in Python.
- Generative AI — the OpenAI API, prompt engineering, embeddings, and vector search.
- RAG and AI agents — grounding LLMs in your own data, and building agentic systems that use tools to act.
- Real-world enterprise AI use cases — how companies actually apply AI across finance, retail, healthcare, manufacturing, and more.
Everything here is meant to be practical: concrete tutorials, working code, and honest notes on what does and doesn’t work in production.
Florian Follonier, PhD
Zurich, Switzerland
I’m Florian, a Cloud Solution Architect at Microsoft based in Zurich. In 2020, I started this blog to build a comprehensive resource for anyone kick-starting a Python machine-learning project — a single place to find the concepts, code, and worked examples needed to get going, whether you’re a beginner or a professional.
The blog covers a wide range of topics, including supervised and unsupervised learning, deep learning, neural networks, data preprocessing, and, more recently, generative AI, retrieval-augmented generation, and AI agents. Alongside the tutorials, I build and share real projects.
One of those projects is AIUseCaseHub — a free, source-linked database of more than 3,000 real-world enterprise AI implementations, discovered and organized by a team of AI agents. Several articles here document how it was built.
I’m passionate about making AI more accessible. Feel free to explore the tutorials, and let me know if you have feedback or suggestions.
Note: Although I work for Microsoft, the articles on this blog represent my own personal opinion.
Philipp Peron
Munich, Germany
Philipp holds a Master’s degree in Electrical Engineering and Information Technology from the Technical University of Munich. He is passionate about machine learning, software development, and signal processing, and has contributed Python machine-learning tutorials to this blog — including several time-series forecasting tutorials that use neural networks.