Crogl Featured by Intellyx for Reinventing Security Operations with AI
Industry analyst firm Intellyx recently spotlighted Crogl in a Brain Candy Brief authored by Jason Bloomberg, recognizing Crogl for reinventing security operations with AI and an autonomous knowledge engine.
Compound AI Architecture
Crogl leverages several types of AI and an autonomous enterprise knowledge engine to normalize alerts and other security-related data, facilitating the analysis and remediation of security threats and other issues by leveraging the enterprise's existing security tooling.
Crogl includes a compound AI system that includes LLMs and smaller models as well as agentic AI orchestration, unlike other security tools with LLMs bolted on. Crogl's generative AI capabilities leverage results from the knowledge engine to provide natural language explanations, rather than requiring human-generated prompts.
Two Data Pipelines
The Crogl platform contains two data pipelines. The first leverages AI for continuous learning from tickets and other input documents. The second pipeline offers task-oriented threat investigation and hunting.
Every alert that comes into the platform — either from an internal tool or an external threat advisory — enters the knowledge engine, where Crogl normalizes and transforms it into an input action into the appropriate security tool, following each tool's data input schema requirements.
Full Auditability
Crogl documents each step it takes as it triages and analyzes security issues and prepares recommended mitigations, informing security analysts what actions it has taken as well as providing an audit trail.
Privacy-First Deployment
Each Crogl deployment is fully self-contained, running in customers' own cloud instances or on-premises. The platform can even run in fully air-gapped mode.
To maintain customer privacy, Crogl only accesses customer data when customers opt in for support purposes — but the company never leverages customer data for any other reason, including model training.
Intellyx has since published multiple follow-up analyses on Crogl, including deep dives on the central role of the knowledge graph, autonomous investigations, and no data movement or schema normalization.