InfoQ AIGitHub
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.
Read at InfoQ AI ↗Related

GitHubJioHotstar Benchmarks Knowledge Bases for AI Coding Agents InfoQ AI

GitHubHow LinkedIn, Netflix & DoorDash Run Agents, Evals & Inference in Production: QCon AI New York 2026 InfoQ AI

LabsAutomating AWS Agent Registry updates with push-based architecture AWS Machine Learning

GitHubScaling AI agents with open standards: Kurtis Van Gent on MCP and Agent Skills joining the AAIF Google Open Source Blog

ToolsContext Engineering (Agent Memory) for AI Agents Starts with Retrieval LangChain
