This 30-Day Experiment Changed How AI Coding Is Done at Expel | Stack Trace

What happens when a VP of Engineering tells a group of senior engineers to stop writing code for a month? Jeffrey Wescott, VP of Engineering at Expel, joins Stack Trace by Span to talk about what's working as AI reshapes engineering teams. In this episode, Jeffrey and Stephen Poletto get into the experiment that kicked off AI adoption at Expel, why tokenmaxxing is a trap, how QA and code review change when AI writes the code, and how a cybersecurity company determines where LLMs should be used while trying to fight bad actors "at AI speed." They also dig into how AI is now lowering the floor and raising the ceiling on software development, the return of spec-driven development, and what individual engineers should be doing right now to stay valuable. Chapters: 0:00 Intro: meet Jeffrey Wescott 3:53 What is Expel? 5:18 AI in cybersecurity: defending against bad actors at AI speed 10:05 Lowering the floor, raising the ceiling: AI's impact on software engineering 24:36 "For the next month, I want you to stop writing code": AI experiments at Expel 32:31 Why tokenmaxxing is "dumb" 36:00 Conclusion 🔗 See Span in action: https://www.span.app/ 🔗 Connect with Span:   / getspan   🔗 Connect with Stephen:   / spoletto   🔗 Connect with Expel:   / expel   #aiengineering #softwareengineering #engineeringleadership #aicoding #devtools