AI models are starting to act like appliances, locked into one narrow way of working, instead of the flexible infrastructure they used to be. Drew Breunig, an AI and data strategist working with the Overture Maps Foundation, joins us to explain why, and what it means for anyone building something that doesn't look like Claude Code. Drew walks through his "Winchester Mystery House" idea: what happens once code gets so cheap to write that the only real bottleneck left is feedback. From there we dig into DSPy: signatures, the GEPA optimizer, and the brand-new Flex optimizer, which rewrites your code instead of just your prompt, complete with a real before-and-after on cost and accuracy. We also get into why so many AI-built apps and websites end up looking identical, the actual difference between an agent and a workflow, what Drew learned a year after shipping a code library with no code in it, and why he thinks the most valuable thing you can do right now is close the laptop and go talk to people.

A pragmatic, data-backed RETEX on balancing developer autonomy with strict AI FinOps controls. It breaks down the mathematical economics of managed SaaS APIs (Gemini 3.5 Flash vs Claude Opus), exposes the massive fixed hardware and engineering overhead of self-hosting MoE models on GCP GKE clusters, and highlights the workflow-destroying memory and prefill latency bottlenecks of local workstation execution. It concludes with a staged, hybrid strategy to achieve predictable costs and model independence.

OpenAI's Codex developer experience lead sits down with a former comedian turned ML engineering lead for a conversation about what happens when computer use agents stop being a novelty and start actually running your day. The conversation moves through building an AI-powered morning brief that reads every email, Slack message, and tweet before you've even opened your laptop, letting pinned threads check in on themselves every 30 minutes, and a skills system built to mirror how a person actually writes and reviews code. There's a close look at the guardrails and permission layers that keep an autonomous agent from pushing to the wrong repo or replying to the wrong tweet, how a codebase merging thousands of pull requests a day survives thanks to self-healing review before anything hits CI, and the idea of AI deference - when an agent should push through a task alone versus stop and ask for help. The back half gets personal: why developing taste and vocabulary now matters more than working harder, what it actually takes to delegate to an agent the way you'd onboard a new employee, and why this might be the year voice-orchestrated computer use finally makes everyone feel like they're talking to Jarvis.

A deep dive into the "design-by-intuition" tax in AI engineering, comparing convergent and divergent agent loops. It introduces agent-evolutions, a genetic search framework that spawns variants in parallel, evaluates them against frozen binary gates and numeric rubrics, and relies on a robust file-based sub-agent contract rather than chat parsing.

In this episode, we're joined by Josh Collier, FinOps Lead at Superhuman (formerly Grammarly), to explore what it really costs to run AI at scale and why the rules of the game changed faster than anyone expected.

In this episode, we're joined by David Soria Parra, Engineering Lead at Anthropic and one of the core maintainers of the Model Context Protocol (MCP), to explore the biggest evolution of the protocol since its launch and why MCP is becoming the foundation for the next generation of AI agents.

Rosie is iFood's AI support agent, serving millions of customers across Brazil. Rather than trying to eliminate latency, the team designed the system around it. In this conversation, César Gomes explains how iFood uses asynchronous workflows, specialized agents, rollback strategies, delayed memory consolidation, and a reviser agent to keep conversations responsive while reducing costly hallucinations. The result is a production-ready architecture focused on one outcome: shortening the path from customer problem to resolution.

Manish Dasaur is a Managing Director at PwC with over 20 years in data and AI, having helped 100+ clients navigate AI disruption and extract real business value from data, AI, and agentic AI initiatives. In this episode, he breaks down why most enterprise AI programs stall — and the playbook the winners are using instead.