BRIGHTCODE – Michał Żarnecki Portfolio

LLPhant – A comprehensive open source PHP Generative AI Framework – contribution with complete evaluation module

Posted on 30 August 2025  in projects

Implemented a collection of tools that represent different strategies for evaluating LLM responses in most popular PHP AI/LLM framework LLPhant.
Supported 10 different strategies for evaluating LLM responses:

Score evaluators:

• Criteria evaluator
• Embedding distance evaluator
• String comparison evaluator
• Trajectory evaluator

Output validation:

• JSON format validator
• XML format validator
• Fallback messages validator
• Regex pattern validator
• Token limit validator
• Word limit validator

Introduced A/B testing for different LLMs response comparison.
Added also guardrails which are lightweight, programmable checkpoints that sit between application and the LLM. After each model response they run an evaluator of your choice (e.g. JSON‐syntax checker, “no fallback” detector). Based on the result, either pass the answer through, retry the call, block it, or route it to a custom callback.

Framework repository: https://github.com/LLPhant/LLPhant
Evaluation module: https://github.com/LLPhant/LLPhant/tree/main/src/Evaluation

A/B testing, Criteria evaluation, embedding distance, GuardRails, LLM evaluation, PHP

[Top]

AI-supported company structure report generator

Posted on 17 July 2025  in projects

In this project I built a pipeline that transforms raw corporate‑registry filings into an interactive ownership‑tree dossier. This approach helps analyse even complex company structures and detect beneficial owners in multi‑level hierarchies. The application reconstructs every legal entity in a group, calculates the equity stake at each level, and flags individual shareholders who meet Germany’s ≥ 25 % “wirtschaftlich Berechtigter” threshold. A single PDF (example attached) contains the full tree, drill‑down tables, and a concise write‑up in both German and English.

Functional Overview

• Document acquisition – Scrapes excerpts, shareholder lists and capital‑table attachments; deduplicates, corrects, matches and standardises addresses, register numbers and legal forms.
• Graph‑builder – A Neo4j‑backed engine converts the filings into a directed equity graph. Direct and indirect holdings are aggregated with depth‑first traversal to produce the true economic ownership percentages.
• LLM reasoning chain – Specialised prompts guide LLM to parse unstructured shareholder related documents, providing structured shareholder information
• Visual presentation – D3 js library renders tree also handling cricular dependencies and output is captured by pupeteer service in order to generate final PDF with clickable deep‑links back to source documents.

[Top]

AI-based company credit rating and financial report generator

Posted on 18 June 2025  in projects

In this project I designed pipeline that converts raw financial statements and company data into a fully formatted credit-rating dossier. The application produces a narrative assessment, multi-year ratio analysis, yer-to-year comparison and a suite of visualisations each generated dynamically at runtime.

Functional Overview

• Data acquisition – The service ingests three years of balance-sheet, income-statement, and cash-flow data together with current market quotations.
• Analytical engine – A carefully curated Expert-Investor system prompt guides OpenAI o3 and Claude 3.7 sonet to draft commentary in German, embedding all referenced figures verbatim for improved traceability. Guard-rails prevent from wrong output formatting, validate and correct data if any issue is detected. Analysis consists multiple stages where output of single LLM with secialized prompt is passed to another LLM with different instructions and by such multi stage reasoning, complete, repeatable and high quality of expertise is achived.
• Credit scoring – Liquidity, solvency, and profitability ratios are computed and weighted to deliver an internal credit rating.
• Visual presentation – Matplotlib/Seaborn charts (trend lines, ratio heat maps) are embedded directly into the final PDF.

Business Value

Automated, audit-ready financial commentary shortens the traditional analyst workflow and enables decision-makers without a finance background to evaluate corporate health immediately.

>>> see sample report <<<

For more technical details and guidance how to approach such topic please refer also to my article “Building Financial Reports with FinGPT and Claude 3.7 Sonnet” (Medium, May 2025).

AI Agents, few-shot, FinGPT, GuardRails, langchain, LangGraph, matplotlib, xbrl

[Top]

System for detecting similar companies and competitors

Posted on 1 December 2024  in projects

System for identification of similar companies and competitors based on company description text, texts from company websites, coordinates, industry tags, revenue and size of employment.
System is based on relational database queries that include logistic regression model coefficient trained on large dataset related to German companies.

Logistic regression, PostgreSQL, text similarity

[Top]

System for official industry codes classification

Posted on 21 November 2024  in projects

Solution for multi-class classification of unstructured texts containing company descriptions categorized into over 1800 classes (WZ 2008), using Python libraries, large language models (LLMs) and the Retrieval Augmented Generation (RAG) technique.
This project was evolving since 2021 together with artificial inteligence solutions and initially approached using a Random Forest Classifier, to be later replaced with zero-shot transformer based solution and finally solved with a solution based on RAG and LLMs, yielding significantly improved results.
More details can be found in article

Classification, Llama3, LLM, NLP, Python

[Top]

AI chatbot for analysing companies source documents

Posted on 26 May 2024  in projects

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 uses vector database based on postgres pg_vector extension to store and access trade register documents.
Application is using large language model (LLM) Llama3 together with retrieval augmented generation (RAG) approach which allows to ask and get response to any question related company and managers history as well as financial condition and important changes.
Together with response also source documents are listed making this approach reliable business intelligence tool.

Responsibilities:

• build application prototype
• implement application code parts
• implement authentication mechanism
• specify and coordinate works related to building chatbot interactions
• specify and coordinate works related to sychronizing in real time source documents and make them accessible for LLM
• measure answers quality

langchain, Llama3, LLM, Python, PyTorch, RAG, Stremlit, Vector DB

[Top]

Named Entity Recognition system for parsing documents

Posted on 12 December 2023  in projects

The goal of this project was to prepare NER-based system parse information from semi-structured documents.

NER, Spacy

[Top]

Self-driving vehicle based on tensorflow CNN and RasberryPi

Posted on 26 January 2023  in projects

Responsibilities:
– prepare laboratories for students related to computing vision recognition and training autonomus vehicle using convolutional neural network and tensorflow library
– assemble vehicles using Raspberry Pi 4 Model B, motors and other parts
– configure environment for model training and run model on Raspbian OS
– implement module for object detection

CNN, Machine Learning, OpenCV, Python, tensorflow

[Top]

System to collect networking and finance data about German companies

Posted on 1 July 2020  in projects

Web application to collect networking and finance data about German companies.
companyhouse.de

Responsibilities:

• Implementing data mining tools and parsers using deterministic algorithms and deep learning models
• creating fast and efficient search engine
• carrying out integration with external platforms, APIs, web-services
• working with Selenium, automation of acceptance, integration, functional and unit tests, TDD
• conducting data analysis using Python, R
• server environment setup and configuration

AWS, Cassandra, Data mining, data science, DBMS, Docker, Jenkins, Machine Learning, MongoDb, Neo4j, Neural networks, Nginx, NLP, NumPy, Pandas, PHP, regular expression, ScikitLearn, Server administration, Spacy, text mining, TextBlob, Ubuntu, Yii2

[Top]

Search engine based on Elasticsearch

Posted on 1 November 2019  in projects

Pictures from companyhouse.de

Search engine based on Elasticsearch

Responsibilities:

• setup multi-node Elasticsearch server structure
• implementing efficient synchronization script
• configuring queries and score functions

Big Data, Elasticsearch, Kibana

[Top]