New parts of Agent Access Control, plus analysis of agent identity standards as they move. Roughly monthly. No filler, no cadence promises I won't keep.
In late July 2026 I gave a talk in Berlin on AI agent governance and safety, written for people who are new to the space. The topic sprawls across technical, architectural and legal ground, so this written version stays where engineers have real leverage: the control points where vulnerabilities actually happen.
MCP enterprise-managed authorization (EMA) lets the corporate identity provider decide which MCP servers employees can reach, with no per-server consent prompts. A practical, spec-accurate guide to the ID-JAG flow with a build checklist, and a hard line between what EMA secures (the connection) and what it leaves to you (per-action authorization).
Exploring how the EU AI Act extends the principles of GDPR from data protection to system accountability, and why this new regulatory wave feels fundamentally different.
An in-depth exploration of how Large Language Models (LLMs) and specialized AI agentic platforms will shape the future, examining current challenges, technological advancements, practical use-cases, and strategic insights.
Contrary to common understanding, shared AI conversations often end up being publicly indexed and available. This chapter warns businesses about the real and immediate threats, and guides how to safeguard against data leakage via AI tools.
Planning is a fundamental aspect that transforms AI agents from simple chatbots into intelligent assistants capable of executing complex tasks. This article dives deep into the concept of planning, the challenges it presents, and provides real-world examples.
