Operations | Monitoring | ITSM | DevOps | Cloud

Ep 36: Do not resuscitate: Legacy tech in modern medicine

In this episode of Masters of Data, we dig into the cybersecurity nightmare that is modern healthcare IT, from ransomware attacks shutting down entire hospitals to IoT medical devices running software older than some of our passwords. We explore why healthcare organizations make such attractive targets for cybercriminals, and why the combination of life-or-death stakes, skeleton-crew security teams, and Windows-95-era equipment is a recipe for chaos.

Claude Code is running bash commands on your infrastructure. Here's how to watch it.

I’ve been staring at Claude Code telemetry for the past few weeks, and I keep noticing the same thing: most teams drop it into their environment, say “it’s amazing,” and have absolutely no idea what it’s actually doing at the system level. That’s fine for a personal dev tool. It’s not fine when you’ve rolled it out to 50 engineers.

The architecture advantage: Why the data layer decides the AI race

Dozens of startups are sprinting to build the next “agentic SIEM” that can autonomously detect, investigate, and respond to threats. They’re well-funded, well-marketed, but structurally hollow. Here’s what it usually looks like: an LLM layer on top of a thin orchestration engine on top of fragmented or customer-hosted data lakes. While it looks impressive in a demo, it quickly falls apart in production. Why? It’s not built on a strong foundation.

Skills vs. MCP: You're probably reaching for the wrong one

Everyone is adding Model Context Protocol (MCP) servers to everything right now. And I get it. MCP is clean. It’s standardized. You write a server, expose some tools, and suddenly your LLM can query your log platform, pull a dashboard, and fire an alert. It feels like the right abstraction. But I’ve watched teams at serious companies burn weeks building MCP integrations for workflows that should have been skills, and build skills for things that genuinely needed MCP.

Ep 24: Governing AI in the age of agentic systems and Model Context Protocol

On this episode of Masters of Data, we unpack David's new white paper on AI governance for agentic systems. He explains model context protocol (MCP) as "APIs for agents", how AI systems talk and execute tasks. The catch? Autonomous agents are insider threats that move fast and cause serious damage. David introduces the Model Control Plane (MoCop), a twelve-pillar framework designed to prevent your AI from going rogue. We cover his roadmap for security leaders to build real controls and telemetry. His advice: treat agents like interns with root access. Get ahead of this before your agents do.