Augmenting Threat Intel Analysis with Agents - Chris Wallis, Sai Kiran Uppu, Ramin Farassat - ASW #396
Summary
In this episode, hosts Mike Shima and John Kinsella interview Cy Karanupu, a senior security researcher at Adobe, who details how his team uses LLM agents to automate threat intelligence analysis and hunt across petabytes of enterprise data. Karanupu explains the architecture of their multi-agent harness, which relies on specific markdown role definitions, budget constraints, and human-written query examples to prevent hallucinations and optimize performance. The discussion highlights the critical need for human-in-the-loop verification to validate agent findings and the importance of compr…
Listen ad-free on Castria