Multi-model AI isn’t a buzzword anymore, it’s how organizations are actually operating. In this episode of #F5's Pop Goes the Stack, Lori MacVittie and Joel Moses dig into fresh findings from F5's State of Application Strategy (SOAS) Report, showing companies run an average of seven models, and more than half are already orchestrating multiple models together. That’s a big shift, and it changes what “infrastructure readiness” even means. Why do teams chain models in the first place? The answer: cost, capability, and risk. The uncomfortable part? Most infrastructure is still built for deterministic systems, and AI routing is not the same problem as load balancing. Model routing isn’t about spreading traffic evenly. It’s about making a decision on every request: which model is best for this job, what will it cost, what’s the risk, and what’s the fallback when the answer is wrong or low quality. Joel frames it as a category change, from “where should this request go?” to “what should happen as a result of this request?” That shift forces new requirements: policy enforcement across models, identity-aware access, decision justification, and mechanisms to recover when output quality degrades due to drift, configuration changes, or poisoned inputs like compromised RAG data. Lori ties it back to governance, not just availability, and why “AI workloads” expose gaps that traditional tooling can’t cover. While many organizations are operationalizing #AI, that doesn’t mean it’s manageable yet. If you want to know how to move forward from here, this is an episode you don't want to miss. Chapters: 00:00 Welcome to Pop Goes the Stack 00:21 F5 research confirms multi-model AI is already real 01:17 Multi-model orchestration: Reasoning vs cost tradeoffs 02:15 Where does delivery and security matter most in AI? Input, output, identity, or routing? 03:54 Why load balancing breaks: Model routing isn’t “distribution” 04:45 “Measuring fog with a ruler”: Uncertainty vs deterministic tools 06:01 Model routing is control: 100 variables we don’t measure yet 07:33 Decision points: Which model is right for this request? 08:27 Infrastructure isn’t AI-ready: Deterministic vs probabilistic systems 12:47 Routing becomes governance: Policy, access, and enforcement 15:19 Failover becomes “bad vibes”: Retries, prompts, temps, RAG 17:41 Key takeaways: Infrastructure is fundamentally changing for AI to be operational and manageable Get your copy of the 2026 State of Applications Strategy Report: https://go.f5.net/4jhryeya 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/2r85m4ae More about F5: https://go.f5.net/eumc26xr Read our blog: https://go.f5.net/ftvta5u6 Follow us on LinkedIn: https://go.f5.net/fmtcbcpy

 119      6