AI agents can build a demo in a day. But what happens when they touch a production system with years of technical debt, undocumented decisions, security requirements, and real customers?In this episode of So What About AI Agents, Philippe Trounev sits down with Krishna Kumar Sharma, former Head of Engineering for AI at Amazon and founder of Omokai, to talk about what agentic software development looks like outside of greenfield demos and AI hype.Krishna introduces his D3 framework — Discover, Define, Deliver — an approach to AI-assisted engineering based on the same principles used by mature software teams: understand the system, define the work, execute deliberately, and review everything.We get into:• Why greenfield AI coding demos don't represent enterprise software development• How AI-generated technical debt can compound at enormous speed• Why spawning 20, 50, or 100 agents usually isn't the answer• “Token maxing” versus ROI maxing• Using different AI models to review and challenge each other's work• Why cheaper and local models can often handle implementation after good planning• Claude, Codex, Gemini, GLM and local/edge models• Prompt caching and whether context-optimization tools actually save money• Security risks created by executives and teams vibe coding directly into production• Why human review still matters in agentic engineering• The D3 framework for AI-assisted brownfield development• Why boring, structured engineering practices become even more important with AIIn the second half, we move from software agents into the physical world.Krishna explains how Omokai is developing voice-driven command-and-control systems for robots and drones, including autonomous systems capable of operating with AI at the edge.We discuss:• Voice-controlled robots and drone swarms• Running small language models directly on robotic systems• Human-in-the-loop controls for safety-critical actions• Guardrails for autonomous machines• Robotics interfaces such as ROS2, MAVLink and PX4• Operating robots without continuous cloud connectivity• Sensor fusion, LiDAR, vision and GPS-independent navigation• Defense, security, inspection, disaster response and caregiving applications• What happens when AI agents move from software into the physical worldThe central argument of the conversation is simple:More agents aren't automatically better. More tokens aren't automatically better. The goal should be producing more value for every dollar, model call, and engineering hour you spend.Subscribe to So What About AI Agents for conversations with founders, researchers, engineers and operators actually building and deploying AI agents in the real world.https://www.docsie.io

Every CIO is asking the same question: What happens to IT when AI starts doing the work?In this episode of So What About AI Agents, Philippe Trounev sits down with Shayde Christian, SVP of Data & Analytics at Cloudera, to discuss how one of the world's largest enterprise data companies is using AI internally—not just to automate tasks, but to redesign how IT operates.Instead of focusing on AI hype, this conversation explores what actually happens inside a large enterprise when AI agents become part of daily operations.Topics include:• How Cloudera built internal AI agents for enterprise workflows• Why AI assistants and autonomous agents are fundamentally different• AI governance, testing, and production deployment• Building trustworthy enterprise AI systems• Why Cloudera reinvested AI productivity instead of laying off employees• How data teams are evolving into AI engineering teams• Measuring ROI from enterprise AI• The future role of IT departments• What CIOs and technology leaders should be preparing for todayIf you're responsible for enterprise AI, digital transformation, IT leadership, or building AI products, this episode offers practical lessons from real production deployments—not theory.GuestShayde ChristianSVP, Data & AnalyticsClouderaLinkedIn:https://www.linkedin.com/in/shaydechristian/Subscribe for weekly conversations with CTOs, CIOs, AI founders, enterprise architects, and technology leaders building production AI systems.Chapters00:00Introduction to AI Agents and Cloudera02:35The Role of AI Agents in Data Management05:46Challenges in Building AI Agents08:14AI Test Beds and Governance11:13Redesigning Roles in the Age of AI14:16The Future of AI in Business Workflows16:48AI Trust and Human Interaction19:39Agent TAM and Decision Intelligence22:28Governance and Accountability in AI25:21Concrete ROI Examples from AI Agents28:18The Future of IT and AI Integration30:50Final Thoughts and Advice for Leaders#AI #EnterpriseAI #Cloudera #CIO #ITLeadership #DataAnalytics #ArtificialIntelligence #AIAgents #Automation #digitaltransformation https://www.docsie.io

In this episode of So What About AI Agents, Philippe Trounev sits down with Geoff Mattson, CEO of SecureAuth, to explore one of the biggest unanswered questions in enterprise AI:How do you secure autonomous AI agents?As organizations rapidly deploy AI agents across customer service, operations, engineering, and internal workflows, traditional identity and security models are beginning to break down. Systems designed for human users were never built for autonomous software capable of making decisions, invoking tools, spawning sub-agents, and operating at machine speed.Geoff shares his perspective on:• Why AI agents fundamentally challenge traditional identity systems• The difference between authentication and authorization in agentic environments• Agent control planes, permissions, and governance• Prompt injection and agent hijacking risks• Multi-agent architectures and delegation chains• Why "vibe coding" executives are creating unexpected security concerns• The future of enterprise AI security and autonomous digital workers• What organizations should do before giving AI agents real authorityWhether you're building AI agents, deploying enterprise AI systems, or responsible for security and governance, this conversation explores the emerging challenges that come with autonomous software operating inside modern organizations.Guest: Geoff Mattson, CEO of SecureAuth