Agentic Conversations (formally mlops.community)

Dexter Horthy, CEO and co-founder of HumanLayer, coined “context engineering” and builds tools for human-agent collaboration. He discusses why AI still produces messy code, computer-use agents tackling tedious forms, and MCPs designed around model behavior. The conversation explores browser automation, richer interfaces than chat, AI-edited demos, and the rise of software factories every engineer seems to be building.

Tim O’Reilly, founder and CEO of O’Reilly Media and a renowned technology trendspotter, explores AI’s paradoxical capabilities and the human context needed to unlock them. They discuss “magic words,” agentic systems, mechanism design, and turning organizational scar tissue into infrastructure. The conversation asks what game society is playing, how AI can share value with creators, and why open, participatory ecosystems are essential for human flourishing.

AI agents are gaining access to tools, websites, travel plans, and household tasks, but who makes sure they follow through? The conversation explores intent-based tool selection, MCP and WebMCP, benchmark reality checks, and personal assistants that might manage everyday logistics. It also examines QA agents, business-focused tests, and the challenge of reviewing a flood of AI-generated code.

Pepijn Senders, a principal engineer and former HelloFresh AI enablement leader, explores “Sonnet maxxing” while rebuilding banking software with 200 engineers. They discuss measuring AI coding ROI, token spend versus business value, keeping humans in control, multiplayer refinement sessions, how prompt language shapes technical outcomes, and a meta harness that structures Claude Code workflows.

Are “dangerously powerful” AI models a real security threat, clever marketing, or both? The conversation explores sandbox escapes, exposed networks, and agents probing the web for unlocked doors. AI also books travel, handles German bureaucracy, creates editable diagrams, and navigates online shopping. As bots gain wallets, the future of checkout, advertising, customer data, and merchant strategy gets complicated.

Sarah Drasner, Google Area Tech Lead and distinguished engineer, explores what happens when agents browse the web for us. She compares browser-use, computer-use, API, and MCP agents, then demos an agent gathering photos and logos for Canva while keeping creativity human. They unpack WebMCP’s origins, gateway possibilities, engineering instinct, thought experiments, and safer, more delightful agent experiences.

Justin Shroeder, co-founder of Standard Agents, explores a future powered by thousands of specialized AI agents instead of one all-purpose model. They discuss agent standards, runtimes, prompt engineering, and why narrow scope can improve reliability. The conversation tackles routine automation, managing countless agents, the possibility of agent marketplaces, and bringing AI builders together with domain experts.

Issac Lee, an AI and blockchain executive at NEXUS, explores MMORPGs populated by tireless AI players instead of scripted NPCs. He discusses adaptive companions, agent-generated worlds, and solving multiplayer launches with bots that never sleep. The conversation also visits NEXUS’s Da Vinci development system, text-to-3D tools, self-hosted AI infrastructure, personalized meeting notes, privacy, and shopping agents reshaping ecommerce.

Jason Ward, a C.H. Robinson FinOps practitioner and member of the FinOps Foundation’s AI working group, explores AI across logistics, from quoting to tracking. He explains secure model routing, tagging resources to control costs, and using AI to uncover observability signals. The conversation covers prompt bloat, context starvation, agentic versus conversational workloads, and experimental metrics like cost per thought.

James Barney, Global Head of AI Enablement at MetLife, explores the art of “caveman prompting” and the coming CaveBench challenge. They discuss matching models to workloads, balancing cost, speed, and accuracy, pricing surprise launches, measuring AI’s business value, and governing agents. The conversation also looks at whether chat interfaces could replace dashboards, and the risks of missing insights you never thought to ask for.