practitionerAI and LLM Security
Guide AI coding agents at the architecture level before letting them write code
Said by Chris Romeo ·
“The interaction with AI, if you keep it to the conversation, is not as valuable as what I'm finding using the AI to interact with the architecture and the design early and guide it via architecture and design versus trying to guide it command by command through a chat window or something. So forcing it and myself to pull back, look at the 20,000-foot 10,000-meter, I'm guessing, view, and then, and then go back down and dive at various levels of abstraction like specs and things before letting it code.”
Transcript evidence from AppSec Has Never Mattered More: The Time to Exploit Is Now Negative.