Terra Portal adds human-governed AI to live production pentesting
Terra Security has announced the launch of Terra Portal, its agentic desktop app that serves as an execution layer for pentesters to direct and oversee AI-driven testing in live production environments. Terra Portal reduces the discovery-to-fix cycle for vulnerabilities from the industry average of nearly three months to a matter of hours without sacrificing safety or compliance. As a result, customers can now remediate critical findings well within the Cybersecurity and Infrastructure Security Agency’s (CISA) 15-day requirement.
Fully autonomous testing tools promise efficiency but introduce security risks and inaccuracies in production environments. Traditional pentesting tools force testers into manual workflows, limiting scalability. Terra Portal resolves this tension by enabling autonomous pentesting to scale through human-governed AI execution.
“The future of pentesting isn’t autonomous versus human,” added Shahar Peled, CEO, Terra Security. “It’s about giving humans leverage. With Terra Portal, this is the first time in history that we can combine depth, scale, and safety in security validation. Pentesters can do more meaningful, strategic work, and firms that adopt this shift will win.”
At the core of Terra Portal is a human-governed, agentic workflow featuring two distinct types of AI agents, each with different responsibilities, operating under different constraints, and governed differently by design. Ambient AI agents autonomously handle recon, code review, test case generation, reachability analysis, pentests, exploitability validation, documentation, and remediation. When complexity, risk, or organizational guardrails require expert judgment, pentesters engage with Copilot AI agents to conduct approved, controlled exploitation and reporting.
For service providers, Terra Portal enables a shift from one-off, project-based engagements to continuous, offensive security services. AI agents autonomously handle execution, while pentesters retain oversight at critical decision points. This model allows providers to support significantly more clients per tester and deliver faster turnaround times, improving customer satisfaction and retention. Governance remains intact, minimizing operational and reputation risk.
“Highly skilled Pentesters that spend too much time on repetitive and mundane tasks are wasting valuable efforts that can be better spent on strategic judgement,” said Gev Hadari, Head of Adversary Services at Terra Security. “The Agentic Gateway turns expert time into a force multiplier, allowing a single Pentester to safely oversee work that previously required entire teams.”
Terra Portal integrates natively with Terra’s broader agentic penetration testing platform. The platform uses a coordinated swarm of autonomous AI agents to continuously scope environments, discover attack surfaces, generate hypotheses, and validate vulnerabilities. When agents reach their limits, the gateway lets human testers step into the same workflow, preserving context and improving efficiency.