Cloud Security Podcast8 Aug 2025

AI for SOC Automation: A Blueprint for the New world of Incident Response

The nature of Security Operations is changing. As cloud environments grow in complexity and data volumes explode, traditional approaches to detection and response are proving insufficient. This episode features an in-depth conversation with Kyle Polley, who leads the AI security team at Perplexity, about a modern blueprint for the Security Operations Center (SOC).

The discussion centers on a necessary architectural shift away from traditional SIEMs, which were not built for today's scale, toward a "data lake infrastructure built for detection and response". Kyle explains how this model provides the scalability needed to handle modern data loads and enables a more effective incident response process.

A cornerstone of this new model is the use of centralized AI agents. The conversation explores how these agents can be tasked with performing in-depth alert investigations, helping to reduce analyst burnout and allowing security teams to focus on more proactive, high-impact work. This approach moves beyond simple automation to create a system where AI augments and enhances the capabilities of the human team.

Guest Socials -⁠⁠ ⁠⁠⁠⁠Kyle's Linkedin

If you want to watch videos of this LIVE STREAMED episode and past episodes - Check out our other Cloud Security Social Channels:

-⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Cloud Security Podcast- Youtube⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠

- ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Cloud Security BootCamp⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠

If you are interested in AI Cybersecurity, you can check out our sister podcast -⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ AI Cybersecurity Podcast

Questions asked:

(00:00) Introduction to Kyle Polley & The Future of SOCs(01:03) The Core Argument: Why You Must Build Your SOC Before Compliance(03:34) Beyond the Certificate: The Difference Between Being Compliant vs. Secure(04:20) Today's #1 AI Threat: The Challenge of Prompt Injection(06:00) The Architectural Flaw: Handling Untrusted Data in AI Systems(08:20) The "Security Data Lake": Moving Beyond the Traditional SIEM(15:00) The Future is Now: A Centralized AI Agent for Automated Investigations(20:06) Will AI Take My Job? How AI Elevates, Not Replaces, the Security Analyst(25:20) Redefining "Shifting Left" with Personal AI Security Agents(31:00) Can AI Reason? How Modern AI Agents Intelligently Query Logs(37:05) Rethinking Incident Response Playbooks in the Age of AI(41:00) The MVP SOC: A Practical Roadmap for Small & Medium Companies(46:08) Final Questions: Maintaining Optimism, Woodworking, and Tex-Mex(50:08) Where to Connect with Kyle Polley

Resources spoken about during the episode:

Easy Agents: an open-source framework

How to give every department their own AI Agent

Det här avsnittet är hämtat från ett öppet RSS-flöde och publiceras inte av Podme. Det kan innehålla reklam.

Avsnitt(360)

Securing Millions of AI-built Apps: How Lovable Defends Against Insider Threats

Empowering non-technical users to build production-grade applications requires a proactive, secure-by-design architecture. In this episode, Ashish sits down with Marcus Hallberg and Samuel Kelemen, se...

11 Sep 1h 10min

Why AI Won't Replace Your SOC: Federated Data & APEX Framework

Hash values, IP addresses, and domains are virtually useless as primary detection mechanisms in the era of AI-driven polymorphic malware and short-lived phishing kits. If your detection strategy is st...

1 Sep 37min

The "Hunt First" AI Security Strategy

Did you know that 82% of all intrusions don't involve any sort of malware, and AI-augmented attacks are up 89% year over year? If your security operations team is solely focused on reacting to known-b...

25 Aug 46min

Shadow AI & Sandbox Escapes: Why You Need an Agentic Control Plane?

When Claude Cowork hits a roadblock, it doesn't give up, it writes a custom Python script and downloads an untrusted NPM package just to bypass its restrictions and finish its goal. Are your security ...

18 Aug 32min

How Adobe Uses AI Agents for building a WAF Pipeline?

When vulnerability disclosures shrink the wild exploit window down to less than 24 hours (or even minutes), traditional manual patching and WAF rule creation simply cannot keep up.In this episode, Ash...

4 Aug 47min

Why Runtime Agents Are Replacing Static Posture Checks

The attack window from the discovery of a vulnerability to its exploitation has shrunk to less than 24 hours and sometimes down to just 25 minutes. Is your security team prepared for the speed of AI-d...

28 Juli 44min

The Hidden Cost of BlackBox AI: Bridging Cloud and Code Security

Traditional SCA and SAST tools are notorious for drowning security teams in false positives, historically flagging nine out of ten alerts incorrectly. But while generative AI seems like a magic bullet...

9 Juli 42min

Who Governs Your AI Agents? Identity, Offboarding & Open Standards

Are overprivileged AI agents the biggest emerging threat in cybersecurity? In a recent high-profile attack, a vibe-coding company had its entire source code stolen because an attacker exploited a long...

2 Juli 34min