Is your company using AI to trim your budget, or to multiply your team's impact? We're joined by Matt Culver, a senior engineering leader at Super.com, to discuss why the common view of AI as a tool for cost-cutting is a misguided "accounting mindset" that ultimately destroys trust. He argues that leaders should instead see efficiency gains from AI as a powerful opportunity to reinvest in their teams. This conversation reframes the AI debate by urging leaders to look beyond the coding loop to improve the entire product development lifecycle—from ideation to delivery.

Matt explains that the key to successful AI adoption is aligning new initiatives with the developer's core incentives: removing friction and enabling the creative flow state that makes their job enjoyable. He provides a human-centric approach for channeling AI's power to solve upstream problems in product planning and market research, rather than just generating more code. Learn how to use AI not as a means to an end, but as a way to empower your developers, generate more value, and build a high-trust engineering culture.

Bring AI into your code review process with LinearB

Follow the hosts:

• Follow Ben
• Follow Andrew

Follow today's guest(s):

• Learn more about Super: Super.com
• Connect with Matt: LinkedIn | [email protected]

Referenced in today's show:

• A small number of samples can poison LLMs of any size
• Revisiting "Intelligence Drift"
• AI profiteering is now indistinguishable from trolling 
• The AI water issue is fake
• HTML’s Best Kept Secret: The Tag 
• Life in a World of Pervasive Immorality: The Ethics of Being Alive

Support the show:

• Subscribe to our Substack
• Leave us a review
• Subscribe on YouTube
• Follow us on Twitter or LinkedIn

Offers:

• Learn about Continuous Merge with gitStream
• Get your DORA Metrics free forever

With massive context windows and new agent frameworks, do vector databases still matter? Ram Sriharsha, CTO at Pinecone, joins the conversation to make the definitive case that they're more critical than ever. He explains that at the core of all AI is search, and externalizing this function is non-negotiable for security, auditability, and control.

Ram offers a clear starting path for engineering leaders: begin with simple Retrieval-Augmented Generation (RAG) applications, but immediately implement a robust evaluation framework to manage hallucinations and ensure quality. He shares his perspective on the skills that matter most now, arguing that curiosity and the rise of the generalist engineer are critical in an AI-powered world. This episode is a guide to building the AI stack from the ground up, from using AI as a "good junior engineer" for testing to cultivating the engineering mindset of tomorrow.

Bring AI into your code review process with LinearB

Follow the hosts:

• Follow Ben
• Follow Andrew

Follow today's guest(s):

• Learn more about Pinecone: pinecone.io
• Pinecone Tutorials & Blog: Explore guides on RAG, vector databases, and more
• Connect with Ram Sriharsha: LinkedIn

Referenced in today's show:

• Your New 500K AI Coworkers Just Arrived
• How I influence tech company politics as a staff software engineer
• Coinbase says 40% of code written by AI, mostly tests and Typescript
• Celebrating 1 Trillion Web Pages Archived

Support the show:

• Subscribe to our Substack
• Leave us a review
• Subscribe on YouTube
• Follow us on Twitter or LinkedIn

Offers:

• Learn about Continuous Merge with gitStream
• Get your DORA Metrics free forever

Vibe coding is a developer's dream, but in the enterprise, it can be a nightmare of risk and shadow IT. So how do you saddle the 'wild horse' of modern AI development? Dan Fernandez, VP of Product Management, Developer Services at Salesforce, joins the conversation to share the answer: a new category his team is pioneering called Enterprise Vibe Coding. This discussion reveals how to move beyond flashy greenfield AI demos and build for the reality of most enterprises, where the goal is to safely reuse existing systems, not reinvent them from scratch.

Dan breaks down the specific guardrails Salesforce has built, from sandboxed environments for safe testing to automated "quality gates" that act as a bouncer for both human and AI-generated code. He shares the powerful lesson that building customer trust through policies like zero data retention is more important than any single feature. He explains why the real work of enterprise AI is more like secure "plumbing"—connecting the hardened systems you already have. This is an essential guide for any leader looking to apply the speed of AI to the complex reality of enterprise software.

Get the guide: AI productivity guide for engineering leaders

Follow the hosts:

• Follow Ben
• Follow Andrew

Follow today's guest(s):

• Unleash Your Innovation with Agentforce Vibes: Vibe Coding for the Enterprise
• Learn more about Salesforce for Developers: developer.salesforce.com
• Salesforce Extensions for VS Code: VS Code Marketplace
• Salesforce Code Builder: Learn more about the zero-install IDE
• Connect with Dan Fernandez: LinkedIn

Referenced in today's show:

• Future of tech leadership survey report 2025 - Riviera Partners
• Stop Avoiding Politics – Terrible Software 
• Agentic Commerce 
• I built ChatGPT with Minecraft redstone!

Support the show:

• Subscribe to our Substack
• Leave us a review
• Subscribe on YouTube
• Follow us on Twitter or LinkedIn

Offers:

• Learn about Continuous Merge with gitStream
• Get your DORA Metrics free forever

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, 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.

Check out:

• Watch Closing the AI gap: Surpassing executive expectations for AI productivity

Follow the hosts:

• Follow Ben
• Follow Andrew

Follow today's guest(s):

• Learn more about Cloudflare's work with AI: agents.cloudflare.com
• Read the latest from Cloudflare: The Cloudflare Blog
• Cloudflare's Unique Primitives Mentioned: Durable Objects
• The MCP UI Project: MCP UI on GitHub (Project by Ido Salomon)
• Observability Tools Mentioned: Datadog | Honeycomb
• AI Tools Mentioned: Block/Square's "Goose" | Cursor
• Connect with Brendan Irvine-Broque: X @irvinebroque | LinkedIn

Referenced in today's show:

• AI Has Won: Google’s DORA Study Shows Universal Dev Adoption
• The Theatre of Pull Requests and Code Review
• AI isn't replacing radiologists
• Is it time to look for a new job? And how do I start?

Support the show:

• Subscribe to our Substack
• Leave us a review
• Subscribe on YouTube
• Follow us on Twitter or LinkedIn

Offers:

• Learn about Continuous Merge with gitStream
• Get your DORA Metrics free forever

What do you learn after spending 15 years at Apple and demoing your work directly to Steve Jobs? Ken Kocienda, Co-founder of Infactory AI and author of Creative Selection, joins us to share the answer. As a former Principal Engineer at Apple who helped create the iPhone keyboard and autocorrect, Ken discusses his incredible journey from a history major to a key figure in building technology used by billions. He explains his core philosophy of bridging the gap between the liberal arts and technology to create meaningful products, and why he believes AI is the next frontier for this mission. (BTW – we sat down with his co-founder Brooke, so if you like this episode be sure to check that one out!)

The conversation dives into his disciplined, spec-driven approach to coding with AI and the power of "extractive AI" to unlock hidden value in data. Ken reveals the crucial lesson he learned from Steve Jobs—that "everything is provisional"—and how his "evolutionary design" process is perfectly suited for today's AI challenges. This episode is a deep dive into the timeless principles of design and a powerful argument for why the best technology is so intuitive, it makes technical literacy irrelevant.

Check out:

• Register now: AI productivity guide for engineering leaders

Follow the hosts:

• Follow Ben
• Follow Andrew

Follow today's guest(s):

• Learn more about Infactory AI: infactory.ai
• Connect with Ken on LinkedIn
• Ken's Book: Creative Selection: Inside Apple's Design Process During the Golden Age of Steve Jobs

Referenced in today's show:

• MCP is probably the first protocol in tech history with more builders than users… or at least that’s how it feels.
• Albania appoints world’s first AI-made minister

Support the show:

• Subscribe to our Substack
• Leave us a review
• Subscribe on YouTube
• Follow us on Twitter or LinkedIn

Offers:

• Learn about Continuous Merge with gitStream
• Get your DORA Metrics free forever

What does it take to transform a brilliant AI model from a research paper into a product customers can rely on? We're joined by Elizabeth Lingg, Director of Applied Research at Contextual AI (the team behind RAG), to explore the immense challenge of bridging the gap between the lab and the real world. Drawing on her impressive career at Microsoft, Apple, and in the startup scene, Elizabeth details her journey from academic researcher to an industry leader shipping production AI. 

Elizabeth shares her expert approach to measuring AI impact, emphasizing the need to correlate "inner loop" metrics like accuracy with "outer loop" metrics like customer satisfaction and the crucial "vibe check." Learn why specialized, grounded AI is essential for the enterprise and how using multiple, diverse metrics is the key to avoiding model bias and sycophancy. She provides a framework for how research and engineering teams can collaborate effectively to turn innovative ideas into robust products. 

Check out:

• Register now: Closing the AI gap: Exceeding executive expectations for AI productivity

Follow the hosts:

• Follow Ben
• Follow Andrew

Follow today's guest(s):

• Learn more about Contextual AI: Contextual.ai Website
• Follow Contextual AI on Social Media: LinkedIn | X (formerly Twitter)
• Connect with Elizabeth: LinkedIn

Referenced in today's show:

• Throwing AI at Developers Won’t Fix Their Problems
• Why language models hallucinate
• i ran Claude in a loop for three months, and it created a genz programming language called cursed

Support the show:

• Subscribe to our Substack
• Leave us a review
• Subscribe on YouTube
• Follow us on Twitter or LinkedIn

Offers:

• Learn about Continuous Merge with gitStream
• Get your DORA Metrics free forever

AI that talks is easy, but AI that acts securely is where everything breaks down. We're joined by Alex Salazar, CEO of Arcade, to confront the massive and often underestimated gap between a flashy AI demo and a production-ready system. Drawing from his team's own pivot from building agents to building the tools that secure them, he explains why a working demo is only 1% of the journey. Alex breaks down the four "demo killers" that cause most agent projects to fail: inconsistency, security flaws, prohibitive costs, and high latency.

Alex reveals the counterintuitive solution his team discovered: the key to making non-deterministic AI reliable is to dial up determinism. Learn why giving an AI a constrained set of intention-based tools - like a calculator or a multiple-choice test - dramatically reduces errors and solves critical security challenges that plague open-ended systems. He explains why you can't just wrap existing APIs and must instead build custom, workflow-centric tools for your agents. This is an essential listen for anyone who wants to build AI that doesn't just talk, but acts securely on behalf of your users.

Check out:

• Register now: Closing the AI gap: Exceeding executive expectations for AI productivity

Follow the hosts:

• Follow Ben
• Follow Andrew

Follow today's guest(s):

• Learn more about Arcade: Arcade.dev
• Arcade's YouTube Channel: Watch examples and walkthroughs on building agents
• Connect with Alex Salazar: LinkedIn

Referenced in today's show:

• Google avoids break-up but must share data with rivals 
• Welcoming The Browser Company to Atlassian 
• "~40% of daily code written at Coinbase is AI-generated. I want to get it to >50% by October." on X 
• Crushing JIRA tickets is a party trick, not a path to impact 

Support the show:

• Subscribe to our Substack
• Leave us a review
• Subscribe on YouTube
• Follow us on Twitter or LinkedIn

Offers:

• Learn about Continuous Merge with gitStream
• Get your DORA Metrics free forever

For decades, the command line has been a developer's staple. But what if its future isn't to be a better terminal, but something else entirely? 

We're joined by Zach Lloyd, co-founder of Warp, to discuss this groundbreaking shift in developer tooling, sharing his bold vision that the future for developers is neither the IDE nor the terminal, but a new kind of platform built for launching and orchestrating AI agents. Zach explains how Warp is re-imagining the command line as the natural entry point for this evolution, transforming it from a place where you type commands to a place where you write prompts to solve complex problems.

Zach dives into the new developer workflow, where the focus moves up a layer of abstraction from the minutiae of flags and syntax to higher-level problem-solving and guiding agents. He argues that by being the platform itself—not just an app running within it—a tool like Warp can provide a far richer and more effective user experience than traditional CLI agents. Discover the new skills developers need in this era, from problem decomposition to clearly expressing intent in natural language.

Check out:

• AI code review tools: 2025 evaluation guide

Follow the hosts:

• Follow Ben
• Follow Andrew

Follow today's guest(s):

• Try Warp: warp.dev
• Warp's YouTube Channel: Check out Zach's live streams and product videos
• Connect with Zach: LinkedIn | X (formerly Twitter)
• Connect with Brooke: LinkedIn

Referenced in today's show:

• Team OKRs in Action
• In the Age of AI, some tech leaders think communications degrees may actually be more valuable than computer science degrees
• Thoughts on Motivation and My 40-Year Career
• AI, Ads & the Fight for Attention: Infactory Featured in Ad Age
• Introducing pay per crawl: Enabling content owners to charge AI crawlers for access

Support the show:

• Subscribe to our Substack
• Leave us a review
• Subscribe on YouTube
• Follow us on Twitter or LinkedIn

Offers:

• Learn about Continuous Merge with gitStream
• Get your DORA Metrics free forever

First, there was vibe coding. Now, get ready for "vibe entrepreneurship." 

Andrew McNamara, Director of Applied Machine Learning at Shopify, joins us to explain how his team is making this new era of business a reality. He shares the vision behind Shopify Sidekick, an AI co-founder designed to empower merchants by acting as their on-demand e-commerce expert. Drawing on his 16-year journey building AI assistants, Andrew reveals what it truly takes to create an AI tool that customers can trust with their livelihood.

He shares a critical insight from his applied research background: the hardest and most important part of building production-ready AI isn't the model, but the evaluation ("eval") system. Andrew breaks down Shopify's innovative approach of using an LLM-as-a-judge to measure how well they're fulfilling user goals, not just executing features. This conversation is a definitive guide to creating high-trust AI systems and offers a powerful glimpse into the future of commerce.

Check out:

• Register now: Closing the AI gap: Exceeding executive expectations for AI productivity

Follow the hosts:

• Follow Ben
• Follow Andrew

Follow today's guest(s):

• Follow Andrew on X
• Follow Andrew on LinkedIn
• Andrew's Talk at ICML
• Learn more about Shopify Sidekick
• Follow Fatima on LinkedIn

Referenced in today's show:

• The Economics of Software Innovation
• “AI First” and the Bus Factor of 0
• GitLab 18.3 released with Duo Agent Platform in Visual Studio (Beta) and Embedded views

Support the show:

• Subscribe to our Substack
• Leave us a review
• Subscribe on YouTube
• Follow us on Twitter or LinkedIn

Offers:

• Learn about Continuous Merge with gitStream
• Get your DORA Metrics free forever

The single biggest predictor of success with AI isn't the model you choose, it's the DevOps culture you've already built. 

Martin Woodward, VP of Developer Relations at GitHub - and the sixth person to ever use Copilot - joins us to explain why this surprising insight is key to the new era of autonomous coding agents. He traces the evolution of GitHub Copilot from a simple autocomplete to a powerful agent that opens its own pull requests, arguing that AI's true power is as a massive accelerant for the iterative loops high-performing teams have already perfected.

Martin explains that teams with strong guardrails for shipping quickly and safely are best equipped to leverage this AI revolution because they can trust the accelerated output. He also reveals how top teams use the key technique of custom instructions to guide Copilot toward writing the code of the future, not just mimicking the code of the past. This conversation uncovers how new agentic workflows are 'tricking' developers into improving their communication and documentation skills, providing a crucial look at the cultural foundations required to thrive in the AI-accelerated enterprise.

Check out:

• AI code review tools: 2025 evaluation guide

Follow the hosts:

• Follow Ben
• Follow Andrew

Follow today's guest(s):

• Martin's GitHub Galaxy Keynote: Watch "The AI-Accelerated Enterprise”
• GitHub Copilot:  Learn more about the tools and features
• GitHub Universe Conference: Look out for announcements for the upcoming conference
• Connect with Martin:  Martin's Social Media Hub (Martin.Social)
• Connect with Erika on LinkedIn 

Referenced in today's show:

• GPT-5: Overdue, overhyped and underwhelming. And that’s not the worst of it.
• Auf Wiedersehen, GitHub ♥️
• I Tried Every Todo App and Ended Up With a .txt File
• [BUG] Claude says "You're absolutely right!" about everything · Issue #3382 
• Why MCP’s Disregard for 40 Years of RPC Best Practices Will Burn Enterprises

Support the show:

• Subscribe to our Substack
• Leave us a review
• Subscribe on YouTube
• Follow us on Twitter or LinkedIn

Offers:

• Learn about Continuous Merge with gitStream
• Get your DORA Metrics free forever