Building the internet’s next infrastructure layer | Cloudflare's Brendan Irvine-Broque
Inside the proving ground where MCP is battle tested for a global scale
The Model Context Protocol (MCP) is evolving beyond local developer experiments and into the secure, remote infrastructure that will power the next generation of the internet. Brendan Irvine-Broque, Senior Director of Product at Cloudflare, joins us to share a roadmap for this future. He explains how Cloudflare’s “customer zero” philosophy of dogfooding their own tools provides a unique perspective on what it takes to scale MCP for production.
Brendan makes the case for observability as the ideal starting point for enterprises and lays out the vision for MCP’s ultimate destination: a universal protocol for agent-to-agent communication. The conversation explores how remote servers can create a decentralized layer for security and user memory, and what the exciting development of MCP UI means for the future of chat-based applications. This is an essential look at the next wave of agentic systems and the infrastructure required to build it.
“One of the things that I’m really excited about right now is that a lot more people are starting to recognize that MCP isn’t just this protocol for an agent or some other tool to talk to a set of APIs, but can be a protocol for agents talking to other agents.” - Brendan Irvine-Broque
The Download
When AI amplifies your mess, it’s time to clean up your codebase. 🧩
1. Google’s DORA study shows universal dev adoption of AI 🧠
Google’s latest DORA drop is creating waves across the tech industry. The report reveals that 90% of software teams now use AI daily, prompting the removal of this question from future surveys (it’s assumed moving forward). The key takeaway showed that AI amplifies both good and bad practices. Strong engineering teams benefit, while those with weak processes find their problems exacerbated. The report also introduces the AI capabilities model, with more insights and discussions to come as the industry works through the results.
Read: AI Has Won: Google’s DORA Study Shows Universal Dev Adoption
2. Using pull requests and code commits to tell a story for your reviewer 🎭
An article by Meks McClure highlights a talk from Goatmire Elixir, focusing on the art of storytelling in code commits and PRs. The speaker, Saša Jurić, emphasizes the importance of a coherent narrative in code for the reviewer’s benefit. While the advice is valuable, the challenge lies in expecting teams to maintain this level of git hygiene and polish without additional tooling and automation. Perhaps git as we know it will evolve to meet the code proliferation and context-capturing challenges defining the current era of software creation.
Read: The Theatre of Pull Requests and Code Review
3. AI isn’t replacing radiologists, yet 🩻
In the world of radiology, AI-enabled devices dominate, making up nearly 80% of the AI medical device market. So human radiologists are irrelevant now, right? Far from it. A recent article by Deena Mousa at
explains that interpreting radiology images is just a fraction of a radiologist’s role. While AI excels in pattern recognition, it struggles with new hardware, limited training data, edge cases, and, you know, the all-too-critical human interaction element that underpins all healthcare. The productivity augmentations from AI are different than many might expect, highlighting the complexities of integrating AI into real-world applications and also showing a relatable parallel to transformations in our own industry.Read: AI isn’t replacing radiologists
Closing the AI gap 🧗
Executives expect AI to transform productivity, but are your teams actually seeing the results? Check out LinearB’s on-demand workshop, “Closing the AI Gap,” (hosted by me!) to learn how to surpass executive expectations for AI productivity. Discover how leading enterprises like Expedia and Adobe are using MCP insights and AI workflows to boost developer experience and measure real ROI. Yes, that’s right, a demo of MCP in action for executive insights!
You’ll learn where AI is helping your engineers and where it’s hurting, and how to focus your AI investments to show real impact.
Watch: Closing the AI gap: Surpassing executive expectations for AI productivity
4. Is it time to look for a new job? And how do you start? 🤔
Ami Vora at
offers timeless advice on professional development and job searching. For example, regularly interviewing for new roles, even without the intent to leave, helps clarify your strengths and values. But first, Vora suggests writing a pitch about yourself and seeking feedback from those who know you best. Ensuring you’re confident in your career goals is crucial before embarking on a job search. This approach turns the urge to explore new opportunities into a productive exercise for career advancement, and a muscle all knowledge workers should continue to exercise as they develop their careers.