Big Techday 25: Chess AI: How to explain a chess game with AI? - Dr. S. Steinfurt & K. Pervunin

Chess AI: How to explain a chess game with AI? - From traditional engine analysis to LLM agents

Board games such as chess and go have traditionally been fertile grounds for research and experiments with new AI methods. These days, chess engines like Stockfish or AlphaZero are far superior even to the best human chess players in the world. Although advances in pure playing strength are of little relevance for the average player, the educational aspect remains largely unexplored.

The presented chess AI combines several approaches to make chess knowledge more accessible:

The evaluations of state-of-the-art neural-network-based engines can be accessed by an LLM-based agent (powered by e.g. Grok-4) via tool calls.
These tools allow the agent to thoroughly analyze possible moves, offer comprehensive overviews of positions, point out potential errors, and highlight particularly strong moves.
The resulting agent commentary is transformed into a full chess video based on ElevenLabs’ text-to-speech service for narration.

The video can either be in short form, presented as a puzzle, or as full video providing an in-depth analysis.

Feel free to take a look at the corresponding YouTube channel ‪@TNGAIChess‬.

About the speakers:
Dr. Stephan Steinfurt: Dr. Stephan Steinfurt is a Senior Consultant at TNG Technology Consulting, combining scientific excellence with technological leadership capabilities. After his early career in autonomous driving, he currently works as Team Lead in the area of smart home solutions at an international home appliance manufacturer. Additionally, he develops tools for automated chess analysis using Large Language Models - a synthesis of professional expertise and personal passion, as Stephan has played online chess for over 20 years (Blitz Elo 2300-2400). Before joining TNG, he earned degrees in Physics and Mathematics at Heidelberg University and the University of Cambridge. Subsequently, he completed his PhD in theoretical physics with a focus on string theory and black holes in Munich.

Konstantin Pervunin: Konstantin Pervunin is a Software Consultant at TNG Technology Consulting with a Computer Science degree from TU Munich, specializing in Machine Learning. He develops a Chess AI that makes strategic decisions transparent through Explainable AI and LLMs. Previously, he worked on embedding-based semantic search systems in the field of Natural Language Processing.