Ep 78 - Learn By Building: From Strategy Decks To Working Agents w/ Matt Bartles

Overview

“We’ll learn AI once we understand it” sounds responsible, but it’s one of the fastest ways to fall behind. We sit down with Matt to argue for a different approach: learn AI by building with it, in small scopes, with real users, and with the humility to let the work teach you what the strategy can’t. The result is faster AI adoption, better judgment about what models can and cannot do, and a team that develops true operational muscle instead of slide-deck confidence. We dig into why long AI roadmaps are so fragile, how experimentation creates better plans, and what the real costs look like when you delay hands-on work. That includes the unglamorous details that decide whether an AI feature scales: token costs, context loading, caching, latency, and picking the right model for the job. We also explore when open models make sense, what it takes to host them, and why workflow design matters just as much as model choice in complex environments like banking and underwriting. Then we get practical about building agents. A simple “meal planner” agent becomes a lesson in inconsistency, unclear pathways, and why agents can fall apart when they must choose from a long list of similar options. From there, we talk guardrails: where probabilistic AI is fine, where deterministic rules must take over, and how governance should tighten as usage grows. If you’re leading teams through AI strategy, enterprise AI, or agentic AI pilots, you’ll leave with a clearer playbook for building safely and learning fast. Subscribe for more conversations like this, share the episode with a teammate, and leave a review if it helps. What’s the smallest AI build you could ship in the next 30 days? Want to join a community of AI learners and enthusiasts? AI Ready RVA is leading the conversation and is rapidly rising as a hub for AI in the Richmond Region. Become a member and support our AI literacy initiatives.