Dataiku launches Kiji Inspector with support for NVIDIA Nemotron open models to improve explainability, transparency, and governance for AI agents.
Dataiku has announced support for NVIDIA Nemotron open models through the launch of Kiji Inspector, an open-source explainability framework developed for enterprise AI agents.
Introduced through Dataiku’s 575 Lab open source office, Kiji Inspector is described as one of the first open-source explainability frameworks purpose-built for enterprise AI agents. NVIDIA Nemotron is the first model family supported by the framework.
The launch comes as organisations increasingly operationalise AI agents across critical workflows, particularly in regulated and high-stakes environments where performance alone is not sufficient. Enterprises also need to understand, validate, and govern how AI systems reach their outputs.
Kiji Inspector is designed to address limited visibility into how AI agents make decisions. At the core of the framework is a sparse autoencoder, which examines the model at the moment it commits to a tool and identifies the signals behind that choice, translating them into explanations that teams can trace, validate, and trust.
Hannes Hapke, Director of 575 Lab at Dataiku. said: “Without explainability, scaling AI means scaling uncertainty. Bringing Kiji Inspector to NVIDIA Nemotron open models changes that equation. It enables organisations to inspect and refine AI explainability before risk becomes reality. This is essential as agentic systems move from experimentation to trusted infrastructure.”
The release also builds on the broader alignment between Dataiku and NVIDIA around production-grade generative and agentic AI. NVIDIA Nemotron open models provide the performance and advanced capabilities needed for enterprise AI agent systems, while Dataiku provides orchestration across data platforms, enterprise applications, and AI services within a governed framework.
Amanda Saunders, Director of Generative AI, NVIDIA, commented: “Open models like NVIDIA Nemotron give organisations visibility into how their systems operate, enabling deeper understanding, auditability, and control. By combining Nemotron’s state-of-the-art open-source models with the Kiji Inspector, users can understand what moved the agent’s LLM to make the decision.”
Stay updated on crypto and AI by following our socials.
