Ops used to be a world of YAML, caffeine, and careful deploy rituals. Now it’s probabilistic models, token-based cost surprises, and reliability questions that sound more like, “Will the model mean the same thing tomorrow?” In this episode of #F5's Pop Goes the Stack, Lori MacVittie and Joel Moses dig into what happens when production expectations collide with non-deterministic #AI systems, and why the next phase of automation needs more than a chat interface and optimism. They’re joined by John Capobianco from Itential to explore “VibeOps,” an approach to conversational operations that doesn’t throw away deterministic workflows, but connects them to agent reasoning, tool calling, and modern protocols like MCP. The discussion breaks down agent “skills” as a way to describe what an agent can do, constrain what it can’t, and build guardrails in a format teams can manage. From red-teaming experiments to real-world concerns about failure rates at scale, the conversation stays grounded in what it takes to make AI useful in production: external knowledge, policy alignment, composable skills, and a maturity path from lab-only to read-only to supervised execution, and only then toward autonomy. The takeaway is clear: conversational ops can accelerate work, improve documentation and ticket quality, and reduce toil, but governance and accountability still matter. If you’re navigating AIOps, agent adoption, or the post-MCP tooling wave, this episode offers a realistic starting point. Chapters: 00:00 Welcome to Pop Goes the Stack 00:19 Ops is shifting: From YAML to probabilistic production 01:34 Introducing “VibeOps” (yes, we said it) 02:00 What Itential is building: Deterministic workflows + agents 03:05 Teach AI agents “skills” like how to run your 1,400-line playbook 04:37 Guardrails by design: What the agent is NOT allowed to do 07:12 Why VibeOps exists: Network automation adoption is still disappointingly low 09:31 VibeOps as Post-MCP world: Plug-and-play tools for natural language ops 11:49 Deterministic prod vs probabilistic AI: How to make it safe 14:33 The rollout path: Lab → read-only → human-in-loop → autonomy 15:59 Automatic AI execution: How comfortable are enterprises today? 18:28 Is the future an HR department for AI agents? 20:55 Governance that works: Tickets, approvals, and better runbooks 23:17 Key Takeaways: It's time, start teaching your agents today! Learn how you can stay ahead of the curve and keep your stack whole with additional insights on #AppSecurity, multicloud, AI, and emerging tech: https://go.f5.net/se8ugu4k More about F5: https://go.f5.net/l876mqn9 Read our blog: https://go.f5.net/40840ksk Follow us on LinkedIn: https://go.f5.net/9945c9lk Itential on LinkedIn: https://www.linkedin.com/company/itential/

 109      4