Your AI demo is a lie (and how to make it real) | Arcade’s Alex Salazar
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 productivityFollow the hosts:Follow BenFollow AndrewFollow today's guest(s):Learn more about Arcade: Arcade.devArcade's YouTube Channel: Watch examples and walkthroughs on building agentsConnect with Alex Salazar: LinkedInReferenced 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
--------
1:01:58
--------
1:01:58
The future of the terminal is not a terminal | Warp’s Zach Lloyd
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 guideFollow the hosts:Follow BenFollow AndrewFollow today's guest(s):Try Warp: warp.devWarp's YouTube Channel: Check out Zach's live streams and product videosConnect with Zach: LinkedIn | X (formerly Twitter)Connect with Brooke: LinkedInReferenced in today's show:Team OKRs in ActionIn the Age of AI, some tech leaders think communications degrees may actually be more valuable than computer science degreesThoughts on Motivation and My 40-Year CareerAI, Ads & the Fight for Attention: Infactory Featured in Ad AgeIntroducing pay per crawl: Enabling content owners to charge AI crawlers for accessSupport 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
--------
57:32
--------
57:32
Forget vibe coding. Say hello to vibe entrepreneurship. | Shopify’s Andrew McNamara
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 productivityFollow the hosts:Follow BenFollow AndrewFollow today's guest(s):Follow Andrew on XFollow Andrew on LinkedInAndrew's Talk at ICMLLearn more about Shopify SidekickFollow Fatima on LinkedInReferenced in today's show:The Economics of Software Innovation“AI First” and the Bus Factor of 0GitLab 18.3 released with Duo Agent Platform in Visual Studio (Beta) and Embedded viewsSupport 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
--------
42:43
--------
42:43
You can't have AI without DevOps | GitHub’s Martin Woodward
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 guideFollow the hosts:Follow BenFollow AndrewFollow today's guest(s):Martin's GitHub Galaxy Keynote: Watch "The AI-Accelerated Enterprise”GitHub Copilot: Learn more about the tools and featuresGitHub Universe Conference: Look out for announcements for the upcoming conferenceConnect 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 EnterprisesSupport 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
--------
57:36
--------
57:36
The art of letting go as a manager | Transcend’s Minh Nguyen
What's the hardest habit for a top engineer to unlearn in a leadership role? For Minh Nguyen, VP of Engineering at Transcend, it was breaking the "I'll do it myself" mentality. In this episode, she shares her impressive journey from individual contributor to VP at the same high-growth startup, offering a rare and honest look at this challenging transition. Drawing on her background in philosophy, Minh details the hard-won lessons of reorienting from hands-on coding to high-impact leadership, from learning to delegate to setting a clear, communicable strategy.The conversation then shifts from personal growth to organizational design. Minh dives into the practicalities of scaling, revealing why Transcend structures teams around customer problems instead of technical stacks. She candidly discusses her experience pivoting away from a "catchall" platform team to a more effective, product-focused model. This episode is a deep dive for any leader on building a resilient, high-fidelity engineering culture that thrives under pressure, packed with invaluable insights for navigating the challenges of growth.Check out:The DevEx guide to AI-driven software developmentDownload: The 6 trends shaping the future of AI-driven development Follow the hosts:Follow BenFollow AndrewFollow today's guest(s):Connect with Minh Nguyen on LinkedInLearn more about Transcend: Transcend.ioConnect with Jennifer Riggins on LinkedInReferenced in today's show:This Start-Up’s $20 Billion Sale Died. It Came Fighting Back.Perplexity is using stealth, undeclared crawlers to evade website no-crawl directivesIf you're remote, rambleAI promised efficiency. Instead, it’s making us work harder.Writing code was never the bottleneck!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
Dev Interrupted is the go-to podcast for software engineering leadership. Each week, hosts Andrew Zigler, Ben Lloyd Pearson, and Dan Lines sit down with industry experts to explore the strategies, struggles, and stories behind high-performing software teams. Paired with weekly industry news coverage, the conversations dive deep into the real challenges that define excellence in modern tech.
Colombia