InfoQ - AI Interpretability - Presentations https://www.infoq.com InfoQ AI Interpretability Presentations feed Presentation: Opening the Black Box: Critical Explainability for AI Agent Tool Selection with Kiji Inspector https://www.infoq.com/presentations/explainable-ai-llm-agent-decisions/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=AI+Interpretability-presentations <img src="https://res.infoq.com/presentations/explainable-ai-llm-agent-decisions/en/mediumimage/HannesHapke-medium-1793278895069.jpeg"/><p>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 engines, and production monitoring workflows for software architects and senior engineering leaders.</p> <i>By Hannes Hapke</i> Transcripts AI Interpretability Responsibility Agents Governance QCon AI Boston 2026 AI Architecture Large language models Explainable AI Development Architecture & Design AI, ML & Data Engineering presentation Thu, 12 Nov 2026 11:00:00 GMT https://www.infoq.com/presentations/explainable-ai-llm-agent-decisions/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=AI+Interpretability-presentations Hannes Hapke 2026-11-12T11:00:00Z /presentations/explainable-ai-llm-agent-decisions/en