Security | Threat Detection | Cyberattacks | DevSecOps | Compliance

Knowing an AI tool exists is not the same as knowing what it did with your data. This is Part 3 of Cyberhaven's 4-part AI Security product launch series, covering Agentic AI Visibility and AI Risk IQ, Cyberhaven's evidence-based risk scoring system for every AI app and agent in your environment.

Visibility without enforcement is just an alert backlog. This is Part 4 of Cyberhaven's four-part AI Security product launch series, covering how Cyberhaven enforces risk-based controls at the data level, not the tool level, using Data Lineage as the foundation.

Security teams cannot govern what they cannot see. This is Part 2 of Cyberhaven's four-part AI Security product launch series, focused on Shadow AI Discovery and how Cyberhaven automatically inventories every AI app and agent running across your organization.

Autonomous AI agents are running on enterprise endpoints right now, accessing files, processing sensitive data, and executing actions outside the visibility of most security programs. This is Part 1 of Cyberhaven's four-part AI Security product launch series. What this video covers: Most AI security tools were built for browsers and SaaS apps. They cannot see agents operating at the OS level, coding assistants running in IDEs and CLIs, or MCP servers executing in the background. Cyberhaven's AI Security platform was built to close that gap.

Most organizations have no idea how many MCP servers are running in their environment—and attackers are counting on that. In this clip, Adrian Culley breaks down the exact steps security teams need to take now: run the network scan, apply stringent code review to every MCP server project you find, and mandate authentication. Authorization may be optional in the MCP spec—but it doesn't have to be optional in your deployment.

Join us for this week's Defender Fridays as Carlo Anez, Founder & Lead Instructor at IgniteCyber Academy and DEFCON Training Instructor, breaks down how to build practical blue team skills using open-source labs, MITRE ATTACK, and real-world defender workflows, and where AI fits into the picture without replacing the analyst.