Apiiro has launched Guardian Agent, an AI agent that the company says helps prevent coding agents from generating vulnerable or non-compliant code by rewriting developer calls to secure calls.
Introduced on January 28, Guardian Agent is now in private preview. Describing the technology as introducing a fundamentally new paradigm for software security in the era of AI-driven development, Apiiro said Guardian replaces traditional app approaches based on detecting and patching vulnerabilities after the code is written. According to Apiir, Guardian Agent replaces this reactive model with a proactive one that stops risk before code is generated by guarding AI coding agents in real time. Guardian Agent works in real-time directly from the IDE and CLI developer tools. The agent is powered by Apiiro’s code analysis technology and a software graph that “deeply understands” the customer’s software architecture and adapts to its changes, the company said.
Elaborating on the inspiration for Guardian Agent, Apiiro said that coding AI agents break the physics of app security. Enterprises generate four times more code after adopting AI coding agents and expand the application attack surface sixfold. This expansion is driven by the rapid generation of new APIs, duplicate open source technologies and dependencies and other resources that reshape the software architecture with every code change, Apiiro said. Much of the code is generated without the developers being fully aware of it. Apiiro emphasized that preventing vulnerabilities before code exists improves security outcomes and increases developer productivity.