Chess AI

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.

Our chess AI combines several approaches to make the chess knowledge more accessible:

• The evaluations of state-of-the-art neural-network based engines are color: Color value is invalid provided to a ReAct agent powered by a strong reasoning LLM like Gemini 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. This can either be in short form, presented as a puzzle, or in full-video format providing an in-depth analysis.

In the past month, the videos uploaded to our YouTube channel youtu.be/@TNGAIChess have amassed 500'000 views!