Filigran launches XTM One to automate threat exposure management with AI agents

French cybersecurity company Filigran SAS today launched XTM One, an artificial intelligence orchestration layer that automates continuous threat exposure management workflows across its platform.

XTM One connects the company’s OpenCTI extended threat intelligence platform and its OpenAEV exposure validation tool into a single continuous workflow. Security teams today move manually between systems, ingesting threat intelligence in one tool, building attack scenarios in another and tracking remediation in separate dashboards. XTM One automates those handoffs by coordinating AI agents across the lifecycle, taking raw intelligence through to validated defensive action.

The XTM platform already includes AI-powered automation within OpenCTI and OpenAEV. Filigran said XTM One differs by adding a dedicated layer where agents coordinate across products rather than assisting within a single one.

“The volume of CVEs, threat actors and attack campaigns has reached a scale no human team can process manually,” said co-founder Julien Richard. “XTM One is not AI as a feature. It is AI as the operating system for threat management. Security teams deserve automation that works the way they work.”

The platform ships with prepackaged AI agents that handle some of the most time-intensive security tasks. These include intelligence ingestion and enrichment, threat summarization and reporting, attack scenario generation and validation and remediation guidance. The agents interact to form a continuous loop, letting teams identify priority threats, test their exploitability and validate defenses from one interface.

Filigran said that early platform benchmarks show organizations using XTM achieving up to 70% faster threat detection and response cycles and up to 80% less preparation time for offensive security testing.

Customers can build and deploy their own agents, workflows and integrations on top of XTM One. The platform’s Bring Your Own LLM support means they can run Filigran’s models or plug in their own and it can be deployed on-premises. Filigran is pitching that last point at regulated industries and government agencies that cannot send sensitive data off their own systems.

“The biggest barrier to threat intelligence adoption has always been complexity,” Jean-Philippe Salles, vice president of product management at Filigran, said in the announcement. The natural-language interface lets junior analysts become productive faster while removing repetitive work for experienced practitioners, he added.

XTM One will be available in three tiers. Existing Enterprise Edition customers of OpenCTI or OpenAEV receive a built-in set of prepackaged agents, a usage quota and BYOLLM support at no additional cost, while organizations needing custom agent creation, workflow orchestration and premium model packages can license XTM One separately. A free, open-source Model Context Protocol server is also available for integrating Filigran products into other AI architectures regardless of tier.

The product will be generally available this month.

Founded in 2022, Filigran raised $58 million in a Series C round in October backed by Eurazeo SE, Insight Partners LP, Accel Partners LP and Deutsche Telekom AG’s T.Capital.

Image: SiliconANGLE/Ideogram