Traditional security playbooks often fail because they cannot capture the fluid, context-dependent reasoning required when a routine investigation hits a non-scripted "judgment point." Legion Investigator addresses this gap by employing goal-oriented AI agents that move beyond rigid scripts to interpret findings and execute complex, multi-step investigations based on your team's unique environment and expertise. By bridging the divide between automated execution and human-level reasoning, the platform ensures that every alert (no matter how unpredictable) is handled with the depth and consistency of a senior analyst.
Segment Resources:
Request a demo of the platform and the AI Investigator:
Website: https://www.legionsecurity.ai/
This segment is sponsored by Legion Security. Visit https://securityweekly.com/legionrsac to learn more about them!
Read the interview summary from SC Media here: Legion’s Ely Abramovitch on goal-oriented AI investigations
- 0:00 - RSAC 2026 Interview – Legion Security & AI Investigations
- 0:56 - What is Legion Investigator? Goal-Oriented AI Explained
- 02:08 - Task-Based vs Goal-Based AI in Cybersecurity
- 02:41 - Deterministic vs Exploratory Security Workflows
- 03:04 - Why Traditional Playbooks Fail in Real Investigations
- 03:53 - AI Extending Investigations Beyond Human Limits
- 04:33 - Can AI Investigations Be Trusted? Auditability Explained
- 05:58 - Guardrails, Permissions & Explainable AI Decisions
- 06:32 - From AI Discovery to Automated Security Workflows
- 06:51 - How AI Learns & Adapts to New Security Environments
- 07:14 - Personalized AI for Enterprise Security Operations
- 08:20 - Why One-Size Security Playbooks Don’t Work
- 09:31 - Cyber Attacks at Machine Speed – Why AI Defense Matters
- 10:53 - Phishing, Polymorphic Malware & Modern Threats
- 12:14 - Capturing Tribal Knowledge with AI Investigations
- 13:27 - Faster Incident Response with AI (MTTD, MTTR)
- 14:43 - Measuring ROI of AI in Security Operations
- 15:36 - Automating Repetitive Security Tasks with AI
- 16:34 - Human + AI Collaboration in Cybersecurity
Ely Abramovitch is the Co-Founder and CEO of Legion Security, the world’s first browser-native AI SOC platform. With a background leading product management for Microsoft Sentinel, he has a proven track record of scaling multi-billion dollar security solutions. Abramovitch’s vision focuses on automating complex threat investigations by having AI learn directly from human analyst workflows. He is also a former jazz pianist whose transition into mathematics and technology has shaped his creative approach to solving enterprise security challenges.
