Story
infoq_ai_ml · Nov 12, 2026 · news
Source brief
Presentation: Opening the Black Box: Critical Explainability for AI Agent Tool Selection with Kiji Inspector
infoq.comNov 12, 2026
original source linked
In brief
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...
Feed lens
agent
Continue reading