NEW YORK, Aug. 6, 2025 /PRNewswire/ —Â OX, a leader in Application Security, today announced the launch of Agent OX, an AI assistant that delivers organization-specific vulnerability fixes. The new capability deploys specialized AI agents, each trained on specific vulnerability types and programming languages, to provide highly accurate, context-aware fixes tailored to each organization’s codebase and architecture.
When AI security tools suggest fixes without explanation or rationale, developers are hesitant to trust and implement those fixes. They want to see the suggested changes, understand them, and feel that they can trust them.
Unlike generic AI security tools, OX’s multi-agent system uses specialized AI models to analyze organization-specific codebases and architecture. This approach provides more targeted remediation suggestions that understand both the technical context and business requirements of each development environment. It also allows developers to actually understand the proposed fixes before they implement them – with one click.
“Security tools shouldn’t just point out flaws; they need to help developers fix vulnerabilities intelligently,” said Neatsun Ziv, co-founder and CEO of OX. “We built this capability because developers need solutions that engender trust and understand their specific codebase, as opposed to generic fixes that often create more problems than they solve.”
The feature operates through a three-step intelligent process:
- Detection: OX identifies vulnerabilities through native scanning and third-party integrations across code, dependencies, containers, and runtime environments
- Prioritization: Proprietary code projection technology determines if vulnerabilities are actually reachable, exploitable, and impactful – eliminating noise and false positives
- Multi-Agent Remediation: Specialized AI agents, each expert in different vulnerability types and programming languages, analyze the organization’s code architecture and runtime context to generate secure, tailored fixes – quickly and efficiently.
Developers maintain complete control throughout the process. Suggested fixes appear directly in their existing tools, allowing teams to review, customize, approve, or reject changes without triggering re-scans or creating branch conflicts.
The initial release supports Python and JavaScript, with Java and additional languages planned for future updates.
OX is trusted by over 200 organizations, including Microsoft, IBM, eToro, and SoFi. Agent OX is now available to all OX customers.
About OX
OX is an Application Security Platform that helps teams focus on the 5% of security risks that actually matter. The platform provides evidence-based risk prioritization across the entire software development lifecycle by analyzing exploitability, reachability, and business impact. With comprehensive code-to-cloud coverage, 100+ integrations, and no-code workflows, OX delivers guided remediation that integrates seamlessly into developer workflows.
OX was founded in 2021 by former Check Point executives Neatsun Ziv and Lior Arzi.
Media Contact
ox@concrete.media
SOURCE Ox Security
Read More: Multi-Agent Reinforcement Learning: When Machines Team Up