CompanyHouse platform: LLM API Gateway for unified model access
I prepared an internal LLM API Gateway for CompanyHouse to unify the use of different language models across the company…
read_more()Hi, I'm Michał Żarnecki - a programmer, machine learning specialist, and educator. I build data-driven systems using Python and PHP, with a strong focus on natural language processing, LLM applications, AI agents, and modern web-based technologies. My work combines machine learning and software engineering to deliver practical solutions to real-world business problems. On this website, you can explore selected projects, technical work, and recent professional activity.
Course for Collegium da Vinci University: Advanced Artificial Intelligence
Course for Collegium da Vinci University: Advanced Artificial Intelligence I had the opportunity to prepare and deliver the Advanced Artificial…
read_more()
Lecture for University College of Professional Education in Wrocław: Time Series Analysis and Forecasting video lecture
I recently prepared and recorded a video lecture on time series analysis and forecasting for University College of Professional Education…
read_more()
CompanyHouse platform: MCP integration for AI-assisted development
In this project, I designed and introduced an MCP-based integration layer for the development team, connecting everyday engineering tools directly…
read_more()
Video Course on platform Videopoint.pl/Helion: Creating LLM Applications and AI Agents. Learn the LangChain and LangGraph Libraries
The course “Creating LLM Applications and AI Agents. Video Course. Learn the LangChain and LangGraph Libraries” is a practical guide…
read_more()
Open source framework: LLPhant – A comprehensive PHP Generative AI Framework – contribution with complete evaluation module
Implemented a collection of tools that represent different strategies for evaluating LLM responses in most popular PHP AI/LLM framework LLPhant.…
read_more()
CompanyHouse platform: AI-supported company structure report generator
In this project I built a pipeline that transforms raw corporate‑registry filings into an interactive ownership‑tree dossier. This approach helps…
read_more()
CompanyHouse platform: AI-based company credit rating and financial report generator
In this project I designed pipeline that converts raw financial statements and company data into a fully formatted credit-rating dossier.…
read_more()
ConFoo 2025 developer conference in Montreal, Canada
ConFoo 2025, held February 26-28 in Montreal, Canada. ConFoo.ca is a premier multi-technology conference for developers that brings together international…
read_more()
Python Summit 2024 at the Copernicus Science Center in Warsaw
During my talk I shared the journey of building a system that maps unstructured company descriptions to official industry codes…
read_more()
CompanyHouse platform: System for detecting similar companies and competitors
System for identification of similar companies and competitors based on company description text, texts from company websites, coordinates, industry tags,…
read_more()
CompanyHouse platform: System for official industry codes classification
Solution for multi-class classification of unstructured texts containing company descriptions categorized into over 1800 classes (WZ 2008), using Python libraries,…
read_more()
Data Science Summit 2024 at PGE National Stadium in Warsaw
Lecture: Classifying unstructured texts into 1800 categories!Problem: In this presentation, I will examine the development of a text classifier created…
read_more()
Course for Collegium da Vinci University: Generative AI in text Mining – laboratories at the Collegium da Vinci
The course familiarizes participants with aspects of generative artificial intelligence and the latest achievements in the field of natural language…
read_more()
PHPers Summit Conference 21.06.2024 Poznań
Lecture: Retrieval Augmented Generation – replace complex logic with a text modelAbstract: Have you ever encountered code with so many…
read_more()
CompanyHouse platform: AI chatbot for analysing companies source documents
https://chat.companyhouse.de/ AI-based chatbot for retrieving reliable, up to date and precise information about companies.Chatbot is based on streamlit framework and…
read_more()
CompanyHouse platform: Named Entity Recognition system for parsing documents
The goal of this project was to prepare NER-based system parse information from semi-structured documents.
read_more()
PHPCon Conference 17-18.11.2023 Zawiercie
ML with PHP – replace complex business logic with machine learning models Abstract: Have you ever encountered code with so…
read_more()
PHPers Summit Conference 27.05.2023 Poznań
Lecture: Exploring the viability of PHP for implementing artificial neural networks: A case study on autonomous vehicle control with CNN…
read_more()