alphalist.CTO Podcast - For CTOs and Technical Leaders

Alex Nahas is 28 years old and has already initiated a W3C web standard. Working as a backend engineer at Amazon, he ran into a problem most enterprises face: MCP requires OAuth, but most enterprise infrastructure runs on SAML. His solution was elegant: run the MCP server in client-side JavaScript, letting AI agents use the browser's existing authentication context rather than rebuilding auth from scratch.

What started as an internal tool became an open source project, then a viral Hacker News post published while under anesthesia, and ultimately an invitation from Google and Microsoft to help shape WebMCP as an official web standard.

In this episode, Alex and Tobi explore what WebMCP actually is, why the browser is the most underestimated sandbox in AI development, and what the agentic web might look like two years from now.

Topics covered:

What MCP actually is and why it's just an RPC framework at its core
Why OAuth is a dealbreaker for most enterprise infrastructure
How WebMCP lets AI agents operate within existing browser authentication
The Hacker News post that started it all, and why Alex doesn't remember posting it
How Chrome is natively building WebMCP support
The chicken-and-egg problem of standard adoption
Real-time bidding for agents and what it means for digital advertising
Why agents don't need their own identity
Where the agentic web is headed in the next two years

Most people assume the web runs on Google. The reality is more concentrated: only three companies on earth operate truly independent search indices — Google, Bing, and Brave. Jean-Paul Schmetz helped build one of them.

In this episode, Jean-Paul traces the arc from writing appointment software in a Belgian Radio Shack in 1981, through founding and selling Clix — a European search engine backed by Burda — to his current role as Chief of Ads at Brave, where he now sells search infrastructure to the AI companies that need it most.

For CTOs, this is a rare look inside an infrastructure layer most take for granted: how search indices are actually built, why it takes decades and hundreds of millions to do it properly, and why the entire AI grounding market quietly runs on infrastructure a small group of engineers spent their careers building.
Topics covered:

- Why only Google, Bing, and Brave have truly independent global search indices
- How AI companies use search grounding — and what happens when Google and Bing cut them off
- The SERP API gray market and why it probably has a two-year shelf life
- What it actually costs to crawl and index the web at scale
- The advertising model that will eventually come to AI — and why it's inevitable
- Jean-Paul's Stanford years: machine learning with Andrew Ng, and what was obvious in 2013 that took until 2022 to matter
- Build vs. buy for search infrastructure in 2025

Neal Ford: software architect, author, speaker, and independent consultant (formerly 20+ years at ThoughtWorks), joins Tobias to explore what happens to software architecture when AI agents write the code.

We unpack the critical distinction between behavior and capabilities: why everyone focuses on what code does, but too few think about scalability, security, and responsiveness. Neal introduces architectural fitness functions as the essential guardrail for agentic systems, and explains why non-deterministic code generation demands deterministic tests.

Finally, we dig into legacy modernization, the Dreyfus scale applied to LLMs, ephemerality as the new architectural dimension, and why AI is a multiplier, not a replacement, for experienced engineers.

Lee Zen, CTO of Yahoo, joins Tobias to unpack what it takes to modernize one of the internet’s most iconic consumer portfolios—Mail, Finance, Sports, News, and Search—while operating with real legacy constraints at massive scale.

We talk about Yahoo’s evolution from its public days to private equity ownership, how modernization actually happens (cloud, platform bets, experimentation), and why shipping velocity becomes the most honest forcing function when you’re rebuilding the engine mid-flight.

Finally, we go deep on AI: where it meaningfully improves consumer experiences (mail catch-up, news takeaways, fantasy insights), how teams should avoid “AI labels” without user value, and what it means when AI becomes a tool—and increasingly a coworker.

Greg Foster, Co-founder and CTO of Graphite (recently acquired by Cursor), joins the podcast to discuss the massive shift occurring in software engineering: the move from maximizing "Inner Loop" speed (writing code) to solving "Outer Loop" bottlenecks (reviewing, testing, merging).

With AI generating code faster than humans can review it, the traditional Pull Request model is under pressure. Greg explains how "Stacked PRs" and agentic review workflows are essential for high-performing teams, and why he believes the role of the software engineer is evolving into an "architect of agents."

We also cover the strategic rationale behind the Graphite/Cursor merger, the controversial "PRs per engineer" metric, and why he predicts that by 2029, manual code writing will be near zero—but demand for engineers will be higher than ever.