ATLANTA, Aug. 13, 2026 (GLOBE NEWSWIRE) -- Airia, the enterprise AI platform for discovering, securing, governing, and optimizing AI at scale, today announced that Agent Constraints, Airia's policy engine for AI agent tool calls, can now trigger Security Runbooks inline, at the moment an agent attempts a tool call. The goal: catch risky actions before they happen, not just respond to them after the fact.

Rather than a single allow-or-deny check, a runbook runs a customer-defined sequence of steps, and the outcome of that sequence determines whether the call proceeds.

Traditional runbooks, like the SOAR playbooks they descend from, run after a violation is already detected, which is useful for response but too late to prevent the action itself. Airia moves that same step-by-step logic upstream: When Agent Constraints flags a tool call for review, a runbook runs before the agent's action completes, not after.

"Most automated response happens after an agent has already acted," said Kevin Kiley, CEO of Airia. "Running a runbook at the moment of the tool call means you can actually gather what you need to know, confirm the system is in a safe state, and only then let the action through, at the speed agents operate, with the audit trail regulators expect."

The runbook returns a verdict, and Airia resumes the call, blocks it or escalates it for review. If-then-else logic lets administrators automate routine sequences while reserving on-demand workflows for high-stakes actions.

About Airia

Airia is the enterprise AI platform for discovering, securing, governing, and optimizing AI at scale, giving security, compliance, and IT teams full visibility and control over every agent, model, and workflow. Named a Visionary in the 2026 AI Governance Magic Quadrant and trusted by more than 500 enterprises. Learn more at airia.com.

Media Contact
McKenzie Semrau | mckenziesemrau@airia.com