Coding pipelines are evolving and AI agents are taking the wheel. In this episode of Pop Goes the Stack, #F5's Joel Moses teams up with Buu Lam to dive into “vibe coding”—where tools like Claude Code and GitHub Copilot plan, build, and optimize apps faster than humans can debate lint rules. But is faster better? While agentic #AI unlocks game-changing efficiency, it also introduces new risks: API keys hardcoded into apps, runaway GitHub actions, and a stark need for guardrails like sandboxing, runtime tripwires, and logging. As we embrace smarter pipelines, how do we stay in control? Join us as we explore the promises and pitfalls of shifting left with AI agents—and why the era of “self-improving code” is both exciting and terrifying. The machines are coding. Are you ready to debug? Chapters: 00:00 Welcome to Pop Goes the Stack 00:17 What does shift left mean when agents are writing code? 01:00 Vibe coding programming experiences 03:30 Using vibe coding for real projects 07:13 Agentic AI in development 08:42 Risks of shift left in agentic coding 13:04 Guardrails to mitigate risks 14:48 Practical lessons from vibe coding 16:55 The benefits of agentic coding 18:20 Key takeaways: Lessons for safe AI use Learn how you can stay ahead of the curve and keep your stack whole with additional insights on app security, multicloud, AI, and emerging tech: https://go.f5.net/obmkwozk More about F5: https://go.f5.net/tqcjdsxc Read our blog: https://go.f5.net/fcdk6kn1 Follow us on LinkedIn: https://go.f5.net/6ol40tud

 122      2