AI Architecture29 min read
Presentation: Opening the Black Box: Critical Explainability for AI Agent Tool Selection with Kiji Inspector
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.
By Hannes HapkeInfoQ - AI/ML/Data

Read the full story
Originally published by InfoQ - AI/ML/Data on Nov 12, 2026.
Comments
Sign in to join the discussion.