Application and network security company Radware Ltd. today expanded its Agentic AI Protection product with compliance reporting, deeper visibility into artificial intelligence agent activity, and new protection for agents that run directly on developer machines, including Anthropic PBC’s Claude Code.

As enterprises hand more of their operations to AI agents, security and compliance teams are under pressure to show those systems can be tracked and controlled. Radware said the release is designed to give them that oversight and to help them keep up with regulators now drafting rules for how AI is used.

The visibility improvements center on monitoring and mapping features that chart agent activity, interactions and dependencies. Radware said the tools help security teams see how autonomous systems connect to applications, services and other enterprise resources, an area that has been hard to observe as agent deployments multiply.

Audit-ready reporting rounds out the release. Radware built it to line up with three standards regulators increasingly cite: ISO 42001, the European Union’s AI Act and the National Institute of Standards and Technology’s AI Risk Management Framework. The reports are meant to give companies a paper trail showing how they track and contain the risks tied to AI-driven work.

The most notable addition is protection for developer-hosted AI agents. Coding assistants such as Claude Code run on developer endpoints rather than in the software-as-a-service environments where most agent security tools operate, leaving a gap Radware is now moving to close. The company said the update lets security teams monitor agent behavior across conversations, govern which tools an agent can use and guard sensitive data on developer machines.

That extends Radware’s coverage beyond SaaS deployments to agents running on local host endpoints, a distinction that matters as developers increasingly lean on AI to write and review code.

“Organizations are deploying AI agents across increasingly complex environments, creating new requirements for visibility, governance and security,” said David Aviv, chief technology officer at Radware. “These enhancements help organizations better understand agent behavior, support their compliance efforts and help extend protection to AI agents operating across both SaaS and local developer-hosted environments.”

Radware describes Agentic AI Protection as a single product that pairs visibility, governance and compliance reporting with real-time behavioral defense. The company, better known for its application and network security and its distributed denial-of-service mitigation, has been pushing further into AI security as enterprises look to lock down the agents they are deploying.

The new capabilities are available now as part of the Agentic AI Protection product.

Image: Radware