Learn when to require human-in-the-loop approvals for AI agents, how to wire them into tool-level policy, and how to capture them as audit-grade evidence.
The Mini Shai-Hulud worm pushed malicious npm packages with valid SLSA Level 3 attestations. Here's why signing isn't enough—and what defense actually requires
Package agent skills, configs, and model weights as versioned ModelKits with KitOps v1.12.0. Push to Jozu Hub and serve locally with Jozu Rapid Inference Containers.
Learn how to package a quantized LLM as a ModelKit, deploy it locally with a Jozu Rapid Inference Container, and connect it to OpenCode to run a fully private AI coding agent on your own hardware.
Signing your AI models isn’t enough. Learn why fine-tuned model provenance requires graph traversal, not just attestations, to close the supply chain gap.
Anthropic launched Claude Managed Agents on April 8, 2026. It addresses one of the biggest barriers to enterprise agent adoption: the infrastructure overhead required to execute complex and long-running Claude agents in production. This post breaks down what Claude Managed Agents provides, what problems it solves well, and where enterprises still have governance gaps that
