Summit Talk: Agentic Coding That Doesn’t Fall Apart
With Ethan Robish
August 14 @ 11:00 am – 11:25 am ET
How do you get a coding agent to write quality, well-architected code instead of a teetering house of cards?
Join Ethan Robish, Black Hills Infosec former pentester and current SOC architect, for a technical session on the scaffolding, guardrails, and processes that turn agentic coding from a novelty into a production-grade workflow.
You’ll learn how to write specs your agent can actually execute, enforce test-driven development from the first prompt, codify domain knowledge into reusable skills around the APIs and tools you depend on, and apply the checks and balances that keep AI-generated codebases maintainable instead of disposable.
Whether you’re shipping side projects or production systems, you’ll walk away with a repeatable blueprint for building real software with agents — not just demos.
Chat with your fellow AI Summit attendees in the Antisyphon Discord server: https://discord.gg/antisyphon
This talk is part of Antisyphon Training’s Infosec: Age of AI Summit, a free, six-hour, live virtual event designed to give you a practical, real-world look at how cyber experts are using AI and what security professionals need to know as adoption grows.
For those who want to go further, high-quality, affordable hands-on workshops are available Aug. 17-18 to help you learn AI security concepts, techniques, and tactics.
See the entire Antisyphon Training Course Catalog for affordable cybersecurity training!
About the Instructor
Ethan Robish
Bio
Ethan Robish has spent over a decade at Black Hills Information Security wearing a variety of hats — breaking into networks as a Penetration Tester, hunting attackers across them as a Threat Hunter, writing the tools he wished he had as a Software Developer, engineering the detections that catch real intrusions, and now, as SOC Architect, designing the automation and triage pipelines that power the BHIS SOC. His current focus is building production-grade systems with AI coding agents, codifying the specs, tests, and guardrails that turn agentic coding from a novelty into a dependable engineering practice.
