Agentic AI
SOC Automation
Investigation Layer
AI Architecture
Inside an Agentic Investigation: The Architecture That Actually Works
Denis StefanMay 7, 20269 min read
Denis StefanMay 7, 20269 min readAI Engineer at Arcanna
He builds the interface that lets users design agentic workflows inside Arcanna — the place where a complex investigation gets decomposed into a chain of agents, each with the right tools and guardrails. He spends his time where AI engineering meets the operational reality of production SOCs.
Related Articles
AI Governance
Governing AI in the SOC: The Case for a Trust Layer
If AI is making security decisions inside your environment, who's accountable when it's wrong? Alina Marcu, PhD, on why AI in the SOC needs a Trust Layer.
April 28, 2026Read
SOC Automation
Why SOAR Breaks at Scale, and What Actually Replaces It
SOAR hit its ceiling. Playbook sprawl, LLM inconsistency, and headcount-driven scaling broke the model. Here's what the next layer of SOC automation looks like.
April 21, 2026Read
Interview
AI in the SOC: A 27-Minute Conversation with Darius Iakabos
Darius Iakabos, Lead Solutions Architect at Arcanna, on how decision models and agentic workflows are changing SOC operations.
April 22, 2026Read