Cisco AI Defense: Explorer Edition Brings Agentic AI Red Teaming to Builders
When we launched Cisco AI Defense early last year, it marked a major milestone in our greater mission to enable secure AI adoption. It was the industry’s first comprehensive AI security solution, offering centralized visibility into AI assets, robust algorithmic red teaming for models, and runtime protections for AI applications. More recently, the rapid proliferation of agents has sparked significant conversation around the numerous associated risks with their deployment. Last month, we announced updates to AI Defense to combat agentic risk with capabilities like MCP scanning, agentic red teaming, and purpose-built guardrails.
