Thinking in pipelines for AI agents with David Burkett

LimaCharlie

Mar 19, 2026

Join us for this session of Defender Fridays as we explore thinking in agent pipelines with David Burkett, Cloud Security Researcher at Corelight and Founder of Magonia Research.

At Defender Fridays, we delve into the dynamic world of information security, exploring its defensive side with seasoned professionals from across the industry. Our aim is simple yet ambitious: to foster a collaborative space where ideas flow freely, experiences are shared, and knowledge expands.

What We'll Discuss

In this episode, David Burkett shares his evolving perspective on LLMs and agentic workflows, drawing on his experience as a cloud security researcher and detection engineer to explore how pipeline thinking can dramatically improve the quality and reliability of AI-driven security operations.

Key Topics:

Why thinking in pipelines rather than single agents raises detection fidelity
Using sub-agents as specialists with isolated context for validation and consensus
Gating agent output with tests to prevent hallucinations from propagating
Applying pipeline thinking to detection engineering with LimaCharlie
Optimizing token usage with lazy loading and local information corpuses
The case for turning reasoning to maximum for decision-making agents
Comparing frontier models and when to use local, de-safetied models for security research

Register for Live Sessions

Join us every Friday at 10:30am PT for live, interactive discussions with industry experts. Whether you're a seasoned professional or just curious about the field, these sessions offer an engaging dialogue between our guests, hosts, and you – our audience.

Register here: https://limacharlie.io/defender-fridays

Subscribe to our YouTube channel and hit the notification bell to never miss a live session or catch up on past episodes on our website!