{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Embracing Digital Transformation","title":"#370 How to Control AI Agents with Formal Methods and Ephemeral Access","html":"","width":"100%","height":180,"duration":2811,"description":"AI isn’t just generating content anymore — it’s becoming an operational actor inside enterprise systems. Doctor Darren sits down with Ev Kontsevoy to unpack how AI agents, formal methods, ephemeral access, and action-based governance can help technologists and business leaders keep control as automation speeds up and scales out.\n\n## Key Takeaways\n- **AI changes the risk model:** fast, probabilistic systems can make mistakes at machine speed, so old “critical vs. non-critical” thinking no longer works.\n- **Role-based access control (RBAC) is straining at scale:** as organizations grow, roles multiply faster than employees, making policy management harder to govern.\n- **Move from identity-based to action-based control:** define what the business action is, then bind permissions to that action instead of to a long-lived role.\n- **Ephemeral access improves security:** grant access only for the duration of the task, then let it disappear when the work is complete.\n- **Formal methods matter again:** if AI agents are going to act on infrastructure, workflows need to be precise, verifiable, and impossible to misinterpret.\n- **Treat AI like a first-class operating force:** the winners won’t just deploy more AI — they’ll govern it with stronger, more scalable controls.\n\n## Chapters\n- **00:00** Opening thoughts on AI risk, speed, and governance\n- **02:15** EV’s background in engineering and building for engineers\n- **06:10** Why AI changes infrastructure and enterprise control\n- **10:05** From cars and licenses to modern computing regulation\n- **15:20** Human language vs. precise machine instructions\n- **20:35** Formal methods, verifiable software, and safer automation\n- **26:40** Why AI makes every software path feel “critical”\n- **32:10** Deterministic software, human error, and AI’s new risk profile\n- **38:00** Identity, memory, capability, and motivation in AI agents\n- **44:15** Why RBAC breaks at scale and what comes next","thumbnail_url":"https://img.transistorcdn.com/IRrW2aizIeoZDn3gKLEax-JYQ8V_WzaFpHdgsslDx3k/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9jM2Ji/MDk1OTdiYzA4ZWMw/NWNlOTY0N2RhMWQ3/YmY5Mi5wbmc.webp","thumbnail_width":300,"thumbnail_height":300}