Presentation: Opening the Black Box: Critical Explainability for AI Agent Tool Selection with Kiji Inspector

November 12, 2026 · 11:00 am 1 sources

Image: InfoQ

Coverage

More coverage

• Presentation: Opening the Black Box: Critical Explainability for AI Agent Tool Selection with Kiji Inspector
  InfoQ · November 12, 2026 11:00
  Hannes Hapke shares how Dataiku’s open-source Kiji Inspector applies Sparse Autoencoders (SAEs) directly to decision tokens to expose why agents pick specific tools. Moving past superficial chain-of-thought narratives, he discusses causal ablation, layer activation extraction via patched vLLM…