
We’re excited to share that the recording of our colleague Max Schattauer’s presentation, "Improving Retrieval Q&A Contextualization Prompts," from the Prompt Engineering Conference 2024 is now available!
In his insightful session, Max tackled a critical challenge in chatbot and Q&A systems: ensuring retrieval queries effectively leverage conversation history. Simply relying on the latest user query often results in incomplete or inaccurate document retrieval. Max demonstrated how query contextualization can transform scattered conversation data into a cohesive and effective retrieval query.
Key points covered in the session:
The talk is packed with practical insights and actionable strategies for anyone working in AI, natural language processing, or chatbot development.
If your business is facing challenges in building smarter chatbots or improving retrieval systems, reach out to us. We’re here to help you design innovative solutions tailored to your needs.
📺 Watch the full recording below:
News

The proceedings from the "AI in Production" workshop at KI2025 have been published. Among the contributions is a paper by our team on the use of the Model Context Protocol (MCP) in industrial production environments.
News

Dominik Filipiak and Michael Banf are co-authors of a community paper on the 2025 Topological Deep Learning Challenge, published in the Proceedings of Machine Learning Research. Their contributions feed into TopoBench, an open benchmarking library for the research community.