Automated LLM-based Prompt Engineering for Structured Data Processing

An interactive Jupyter Notebook demonstrating AI agent collaboration using CrewAI. This project explores how multiple AI agents can research, generate content, and automate workflows through task orchestration.

Master’s Thesis at TU Vienna, assessing state-of-the-art LLMs for automating BPO tasks. Features a custom Action Research-Based Compliance Testing (ARCT) framework, exploring LLM capabilities, context impact, and limitations in optimizing complex workflows.