I just open-sourced a public-safe demo of something I think the AI industry is going to need more...
I just open-sourced a public-safe demo of something I think the AI industry is going to need more of:
Execution-boundary governance.
Most AI agent systems today focus on what the model can do.
This demo focuses on what the model is allowed to propose before any consequence-binding action exists.
The repo demonstrates a deterministic governance chain for external coding agents like Claude or Codex:
An Implementation of the Microsoft Agent Governance Toolkit for Safe AI Agent Tool Use with Policies, Approvals, Audit Logs, and Risk Controls
Microsoft’s open-source toolkit for controlling out-of-control AI agents
An open-source toolkit for controlling out-of-control AI agents
The Untrusted Autonomous Workload and AI Sandboxes | Docker
Author: Michal Harcej | 23 May 2026 The next major battle in AI may not be model capability. It...
A practical checklist for running AI coding agents in disposable, least-privilege developer environments.
I’ve been thinking a lot about a failure mode in AI-assisted development that does not fit neatly...
Eval engineering: The missing piece of agentic AI governance - SiliconANGLE
AI coding agents are getting better fast, but I kept running into the same failure modes: they skip...
The current generation of AI agents rests on a dangerous assumption: If the model behaves...
