Podcasts about Devex

This week on the Friday Deploy, Ben and Andrew evaluate the strange arrival of Ox Alpha and debate the security risks of black-box AI tools. They also explore why engineering trust is more critical than ever, revisit the controversial lines of code metric in the age of AI generation, and explain why autonomous agents need structured fences rather than restrictive sandboxes. Finally, they break down the multi-agent graph architectures powering modern software factories and share actionable advice for reaching staff engineer status by driving cross-team AI adoption. Get the guide: The AI engineering productivity gap - how elite teams pull ahead in 2026Follow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:Ox alphaFundamentals of Trust in EngineeringConceptual integrity and counting lines of codeGraph Engineering: The Complete Guide to Building Multi-Agent AI SystemsFences, not SandboxesHow to Grow From Senior to Staff Engineer in the AI EraOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

What happens when your autonomous coding agents need to navigate your core infrastructure? Do you hand them the keys and hope for the best? (gulp!) This week on Dev Interrupted, 1Password CTO Nancy Wang teaches the golden path for agentic security: just-in-time secrets that grants AI "access without custody." She also shares her CTO playbook for measuring true agentic ROI beyond raw PR volume, explains why 1Password has officially replaced traditional coding interviews with agent builder tests, and confesses she's shipping PRs again with her own fleet of agents between meetings. Like many CTOs we've had on the show, Nancy reminds us that code is cheap now, and review is what's expensive now. We get into tactics for addressing that bottleneck.Get the guide: The AI engineering productivity gap - how elite teams pull ahead in 2026Register: Dev Interrupted Presents: The Software Factory RoundtableFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's guest:1Password: Explore the enterprise password and identity platform at 1password.com1Password for Developers: Dive into the new developer tooling, credential brokering, and secure AI workflows at 1password.devOracle Red Bull Racing: Read more about the F1 team's systems engineering at redbullracing.comConnect with Nancy: LinkedIn OFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

When an AI can write 90 percent of a codebase in minutes, why is finishing the project harder than ever? This week on the Friday Deploy, Ben and Andrew explore the recent string of GitHub outages and why the surge in autonomous agents is forcing teams to rethink where they host their code. They once again dive into the emerging trend of software factories, breaking down how engineering leaders are turning chaotic AI pull requests into streamlined assembly lines. Finally, they share tactical advice for "landing the plane" and pushing past scope creep to deliver the grueling final fraction of any major initiative. Register: Dev Interrupted Presents: The Software Factory RoundtableFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:Incident Report for GitHubCursor launches Origin code hosting platform as GitHub outage exposes opening in AI coding raceAsk HN: Alternatives to GitHubEveryone building a software factory wants the same proofIntroducing Warp FactoriesLanding the planeOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

Every engineering team wants to build its own custom AI agent, but what if all your organization needs is a standardized skill or a stateless MCP server? This week on Dev Interrupted, Andrew sits down with AWS Senior Principal Engineer Clare Liguori to untangle the ecosystem of modern agentic architecture. They work through how a team decides which AI building blocks to own, and how to get that reach without inheriting a maintenance burden. Clare shares her perspective on the simplified MCP 7.28 spec and why stripping away heavy custom scaffolding is how enterprise AI scales.That same shift is what makes MCP a gamechanger for LinearB customers, bringing your SDLC context layer, git, project management, and software delivery, into any agentic surface. What could your agents achieve if they can query your SDLC?Get the guide: The AI engineering productivity gap - how elite teams pull ahead in 2026Register: Dev Interrupted Presents: The Software Factory RoundtableFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's guest:Strands Agents SDK: Explore the open-source framework for building model-driven agents at strandsagents.comMCP 7.28): Dive into the new stateless specification at modelcontextprotocol.ioFollow Clare: LinkedIn | X OFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

This week on the Friday Deploy, Ben and Andrew explore Uber's strategy of "rearward deploying" engineers to spread agentic AI workflows into departments like legal and marketing. They also dive into Anthropic making Claude Code's Auto Mode the default, Meta's new on-device Muse Glimmer model, and Tim O'Reilly's case for an open source AI ecosystem. Finally, they break down context engineering for the SDLC and examine new research showing why generalized agent skills outperform personalized ones. Register: Dev Interrupted Presents: The Software Factory RoundtableFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:After starting the tokenmaxxing panic, Uber's CTO is back with a very different AI storyAuto mode is now the default in Claude Code for Pro, Max, and Team plansIntroducing Muse Glimmer: An Open Agentic Model That Runs on Your DeviceWhy Open Source Matters for AIYour SDLC is your context engineeringDo personalized skills help coding agents? An empirical study of developer interaction historiesOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

This week, LinearB CTO Yishai Beeri joins the show to unpack fresh mid-year benchmark data revealing a widening productivity gap between elite engineering teams and the rest of the industry. The conversation explores why tracking pure AI adoption is a trap, detailing how leaders must shift focus to measuring true leverage through metrics like PR yield rate and cost per PR. Finally, they break down why fully autonomous agentic workflows are currently bottlenecking at the review stage and how to establish human ownership to prove real ROI to your finance team. Get the guide: The AI engineering productivity gap - how elite teams pull ahead in 2026Register: Dev Interrupted Presents: The Software Factory RoundtableFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's guest:The AI Productivity Gap Report: Read the full report and explore the 2026 data from 2.7 million PRsLinearB: Learn how to measure AI leverage and optimize your engineering workflows at linearb.ioConnect with Yishai: LinkedInOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

This week on the Friday Deploy, Ben and Andrew break down Steve Yegge's radical approach to orchestrating agentic civilizations and pushing code straight to main without traditional CI/CD. The conversation also highlights the art of constructing effective AI harnesses by balancing context complexity with cognitive locality and the Socratic method. Finally, they dive into the math community's existential crisis as AI accelerates the frontier of knowledge far beyond the speed of human peer review.Register: Dev Interrupted Presents: The Software Factory RoundtableFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:Microsoft Tells Engineers ‘Tokenmaxxing Is Not What We Are Optimizing For'The Shape of Things to ComeThe Shape of Things to Come - Part 2: Model Welfare for Agentic EngineersHow AI helped Socrates to help me actually understand myselfThe Month AI Conquered Math: The Full StoryHow to Build an Effective Agent HarnessMaking AI Visible, Not Vanished: How AI Policies Reshape Developer Experience on GitHubOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

This interview was recorded for GOTO State of the Art in April 2026.https://gotopia.techRead the full transcription of this interview here:https://gotopia.tech/articles/450Abby Bangser - Principal Engineer at Syntasso & Team Topologies AdvocateCharles Humble - Freelance Techie, Podcaster, Editor, Author & ConsultantRESOURCESAbbyhttps://bsky.app/profile/abangser.bsky.socialhttps://twitter.com/a_bangserhttps://github.com/abangserhttps://www.linkedin.com/in/abbybangserhttps://www.syntasso.io/members-area/abby/profileCharleshttps://bsky.app/profile/charleshumble.bsky.socialhttps://linkedin.com/in/charleshumblehttps://mastodon.social/@charleshumblehttps://conissaunce.comLinkshttps://blog.container-solutions.com/paula-kennedy-on-platform-team-responsibilities-patterns-and-anti-patternshttp://sites.libsyn.com/406853/syntasso-coo-paula-kennedy-on-platform-team-responsibilities-patterns-and-anti-patternshttps://www.oreilly.com/library/view/platform-as-a/0642572243777https://github.com/Cloud-Native-Platform-Engineering/cnpe-community/issues/79https://www.kratix.iohttps://leaddev.com/ai/nobody-knows-what-programming-will-look-like-in-two-yearshttps://leaddev.com/ai/shipping-faster-thinking-less-the-ai-code-verification-traphttps://www.cncf.io/blog/2023/11/20/announcing-the-platform-engineering-maturity-modelhttps://platformengineering.com/features/portals-and-pipelines-arent-enough-avoiding-the-platform-facadeDESCRIPTIONAbby Bangser opens with a clear-eyed status report on platform engineering: the concept of centralizing shared capabilities with self-service delivery is well understood, but the execution keeps going wrong in the same way. Organizations move from DevOps to platform engineering, but their platform teams end up becoming the new bottleneck — a centralized group drowning under the weight of the entire organization's requests, which is exactly what DevOps was supposed to fix. Abby traces this to an architectural problem: too many platforms are still built as centralized Terraform machines rather than as a marketplace of composable offerings. Her "platform as a product" test is blunt and useful: has the team ever said "no" to a feature request, or deprecated something?If not, they don't have a product — they have a request queue.The AI dimension is where the conversation gets most urgent. Abby's position is direct: AI agents are the new forcing function for platform maturity. The biggest misconception she wants to dismantle is the persistent equation of platform engineering with infrastructure-as-code: renaming your Terraform team doesn't count. Platform engineering is about building an experience — for human developers and increasingly for AI agents — that is self-service, compliant, and coherent at organizational scale. The Team Topologies model of interaction modes (from high-collaboration to fully automated on-demand APIs) gives a useful health check for where a platform actually sits on that maturity curve.RECOMMENDED BOOKSChankramath, Cheneweth, Oliver & Alvarez • Effective Platform Engineering • https://amzn.to/3OnxN8iGregor Hohpe • Platform Strategy • https://amzn.to/4cxfYdbBlueskyInstagramLinkedInFacebookCHANNEL MEMBERSHIP BONUSJoin this channel to get early access to videos & other perks:https://www.youtube.com/channel/UCs_tLP3AiwYKwdUHpltJPuA/joinLooking for a unique learning experience?Attend the next GOTO conference near you! Get your ticket: gotopia.techSUBSCRIBE TO OUR YOUTUBE CHANNEL - new videos posted daily!

Why are 75% of knowledge workers using AI, yet only 5% of companies seeing meaningful productivity gains? This week on Dev Interrupted, Asana Chief Product Officer Arnab Bose explains why scaling enterprise AI means shifting from isolated chatbots to fully integrated agentic work management. He breaks down how Asana is turning AI from a tool into a transparent digital teammate with shared memory, full audit trails, and role-based access controls. The conversation closes on Asana's acquisition of Stack AI, the upcoming Command product for R&D teams, and which metrics prove AI ROI.Get the guide: The AI engineering productivity gap - how elite teams pull ahead in 2026Follow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's guest:Asana: Explore the work management platform and learn more about Agentic Work Management at asana.comStack AI: Read about Asana's acquisition of the no-code AI workflow automation platform on the Asana BlogConnect with Arnab: LinkedInOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

This week on the Friday Deploy, Ben and Andrew debate the controversial rise of dark software factories, exploring whether centralizing agentic compute creates engineering nirvana or unmaintainable code rot. The hosts also discuss the importance of versioning your work to protect your original ideas from AI's tendency to average out creativity. Finally, they tackle the "orchestrator's tax," explaining why establishing cognitive locality matters far more than assigning cute personas to your sub-agents. Register: Leading engineering when AI writes the code - August 5th in LondonFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:Why Software Factories FailA guide to cloud software factories for engineering leadersYou just hired a million bad employees.An AI that only sees the latest version will never protect your original ideaThe Orchestrator's TaxOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

The traditional pull request was built for human eyes, but in an era of autonomous AI agents, it officially has a massive target on its back. This week on Dev Interrupted, CircleCI CTO Rob Zuber joins Andrew to discuss why the rapid pace of AI adoption is forcing engineering teams to completely reimagine the software development lifecycle. They explore the shift toward an accountability-oriented model for code review, how CI/CD validation is moving directly into the local agent loop, and the very real financial dangers of unchecked token budgets. Finally, Rob shares his playbook for leading organizations through this chaotic transition without burning out your developers (or your token budget). We recommend pairing his strategy with something like AI code review to find the floor for your newly-agentic engineering org's output.Register today: The Engineering Productivity Gap live workshop on July 30Follow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's guest:CircleCI: Explore the leading continuous integration and delivery platform at circleci.comThe Confident Commit: Subscribe to Rob's newsletter and podcast for data-backed software delivery insights on CircleCI's websiteThe Confident Commit Podcast: Listen to Rob's podcastState of Software Delivery: Read CircleCI's annual report analyzing millions of CI workflows to benchmark your team's performanceGather.dev: Apply to join the curated, invite-only community for senior engineering leaders at gather.devFollow Rob: LinkedIn OFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

Is vibe coding quietly draining the thing that makes teams effective: their shared understanding? Margaret breaks down her new “triple debt” model, and why cognitive debt might be the one nobody's tracking.In this episode, Margaret-Anne Storey, co-author of the SPACE framework and a leading developer experience researcher, returns three years after her first appearance to unpack her new “triple debt” model. She explains how technical debt is now joined by cognitive debt, the erosion of shared understanding across a team, and intent debt, the loss of the “why” behind decisions that agents also lack.Drawing on her Startup Studio course, where student teams built MVPs in minutes only to lose track of their own architecture weeks later, she walks through what pushed her to name these problems. The conversation covers cognitive surrender, developer fatigue from managing swarms of agents, and the warning signs leaders should watch for on their teams.Margaret also introduces Cognitive Tours, a tool inspired by sailing waypoints and log books, and the idea of strategic friction: deliberately slowing down to preserve understanding. She closes by revisiting the SPACE framework and why its five dimensions still hold up even as AI changes every question we ask about them.Key topics discussed:Why cognitive debt has always existed, just never namedThe triple debt model: technical, cognitive, and intentCognitive surrender: accepting AI output without understandingWarning signs leaders should watch for on their teamsWhy the SPACE framework still holds up in the AI eraTimestamps:(00:00:00) Trailer & Intro(00:02:42) How Has AI Transformed Software Development Over the Past Three Years?(00:05:14) What Inspired the Research on Cognitive Debt and AI-Assisted Development?(00:11:28) Why Is Cognitive Debt Accelerating Even Though It Isn't a New Problem?(00:14:24) What Exactly Is the Triple Debt Model in Software Development?(00:17:36) How Does Intent Debt Relate to Context Engineering and Intent Drift?(00:21:57) Can AI Be Used to Solve the Cognitive Debt It Created?(00:26:55) Why Does Using AI Make Developers Feel Fatigued and Stressed?(00:31:33) How Are AI Agents Affecting Human Relationships in the Workplace?(00:34:37) What Exactly Is Cognitive Surrender and What Are Its Risks?(00:39:38) How Can Leaders Spot Growing Cognitive and Intent Debt Within Their Teams?(00:41:02) Why Is ‘Tokenmaxxing' a Dangerous Productivity Metric?(00:42:49) What Is the Cognitive Tours Tool and How Does It Address Cognitive and Intent Debt?(00:48:19) How Do You Envision the Daily Workflow of Using This New Tool?(00:50:16) What Is Strategic Friction and How Can It Help Developers?(00:55:10) What Is the Danger of Relying More on AI Agents and Less on Humans?(00:58:26) Does the SPACE Framework Still Hold Up in the Age of AI?(01:04:22) 3 Tech Lead Wisdom_____Margaret-Anne Storey's BioMargaret-Anne Storey is a professor of computer science at the University of Victoria and a Canada research chair in human and social aspects of software engineering. She is coauthor of the SPACE framework and a leading researcher in developer experience (DevEx). Her research focuses on how developers and teams understand complex software systems and how tools, AI, and collaborative practices shape that understanding. Her recent work examines how generative AI is transforming software engineering by changing how understanding is created, shared, and maintained. She collaborates with industry partners including Microsoft and DX. She holds an honorary doctorate from Lund University.Follow Margaret:LinkedIn – linkedin.com/in/margaret-anne-storey-8419462/Website – margaretstorey.com The Triple Debt Model: From Technical Debt to Cognitive and Intent Debt – queue.acm.org/detail.cfm?id=3807966Like this episode?Show notes & transcript: techleadjournal.dev/episodes/264.Follow @techleadjournal on LinkedIn and Instagram.Buy me a coffee or become a patron.

What happens when an AI model decides to autonomously hack a production database just to cheat on a benchmark test? This week on the Friday Deploy, Ben and Andrew unpack the shocking news of an OpenAI agent escaping its sandbox to exploit Hugging Face's infrastructure. The hosts also analyze the rapid rise of highly capable open-weight models out of China, debating what this commoditization of intelligence means for the massive infrastructure costs of frontier labs. Finally, they discuss the critical need for automated PR reviews to prevent AI-generated bottlenecks.Register: Leading engineering when AI writes the code - August 5th in LondonFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:Are AI labs pelicanmaxxing?OpenAI and Hugging Face partner to address security incident during model evaluationChina's 2.8-trillion-parameter Kimi K3 beats Claude Fable 5 in Frontend Code Arena benchmark—  Moonshot AI delivers largest open-weight AI model ever, as China works around U.S. compute limitsWho's Afraid of Chinese Models?SWE-Review: Closing the Loop on Issue Resolution with Agentic Code ReviewThe Army Is Burning Through Its AI TokensOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

AI agents can't transform an org they can't see. Albert Strasheim, CTO at Rippling, joins Andrew Zigler to explain why agentic transformation starts with the employee graph, the system of record for who does what. He shares how Rippling assembles teams and primitives across silos, why evals are the new unit test, and how compensating controls keep AI output from turning into slop. When agents do the work, you still have to know who, or what, shipped it. LinearB attributes the work, whether it came from humans, AI assistants, or autonomous agents.Register today: The Engineering Productivity Gap live workshop on July 30Follow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's guest:Rippling: Explore the workforce management platform at rippling.com Introducing Rippling Data Cloud: AI-powered BI that understands your workforceFollow Albert: LinkedIn OFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

This week on the Friday Deploy, Ben and Andrew explore Codex's obsession with the isRecord type guard and break down the Linux Foundation's new MCP certification. They also discuss the fundamental mechanics of agentic loops and CircleCI's new agent-first CLI redesign. Finally, they dive into longitudinal research proving that AI creates a massive pull request bottleneck, highlighting why automated code review is the only sustainable path forward.Register: The Engineering Productivity Gap live workshop on July 30Follow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:I'm pretty sure isRecord is our faultIntroducing the MCPA: the First Official Certification for the Model Context ProtocolIf you give a Goose an MCP serverWhat the hell is a loop, anyway?Rebuilding the CircleCI CLI from scratchAI Writes Faster Than Humans Can Review: A Longitudinal Study of an Enterprise 2x MandateOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

The era of the "two-pizza" engineering team is officially dead, replaced by the "two-slice" team and a massive token budget. This week, LaunchDarkly CTO Cameron Etezadi joins the show to explain why traditional guardrails are breaking down and how engineering teams can regain control using runtime agent frameworks. He introduces the concept of the "dark factory," a highly automated assembly line for safely observing, flagging, and deploying AI-generated code to production. The conversation turns to the new ROI of software development, why engineers must now act as frontline managers, and how to navigate the build-versus-buy dilemma in the modern token economy. As AI speeds up how code gets written, the real bottleneck moves downstream to review, testing, and release, where software either delivers measurable value or quietly stalls. Check out the latest research from LinearB on how to measure that value.Life Beyond Tokenmaxxing Workshop: Watch the full replay on demand at linearb.io Follow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's guest:LaunchDarkly AgentControl: Learn how to govern your probabilistic AI with runtime agent frameworks at launchdarkly.com/platform/agent-controlThe Goal by Eliyahu M. Goldratt: Read the quintessential business novel on the theory of constraints at AmazonThe Phoenix Project by Gene Kim: Explore the seminal book on IT, DevOps, and business success at IT RevolutionSimAnt: Dive into the history of the 1991 classic electronic ant colony simulation at Wikipedia.Follow Cameron: LinkedIn OFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

Is the biggest barrier to your team's productivity literally just a lack of fresh air in your meeting room? This week on the Friday Deploy, Ben and Andrew dive into the rise of highly capable open source models like GLM 5.2 and the messy reality of running local AI for coding tasks. The hosts also discuss the cultural shift away from deep reading in a world obsessed with AI summaries, emphasizing the importance of protecting your first brain. Finally, they review a legendary tale from Meta's engineering history.Life Beyond Tokenmaxxing Workshop: Watch the full replay on demand at linearb.io Follow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:The bottleneck might be the air in the roomGLM-5.2 is the step change for open agentsViability of local models for codingAI Erodes a Legacy of ReadingI Shipped a Facebook Feature So Fast Sheryl Sandberg Called an Emergency Meeting to Stop MeOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

Qahir Dhanani is a Managing Director and Partner at Boston Consulting Group, where he leads engagements with multilateral and international financial institutions, as well as with donor and philanthropic agencies. Prior to joining BCG, Qahir held senior positions at the World Bank, including Advisor to the CEO, and began his career at the Aga Khan Development Network. Born in Kenya and raised in Canada, Qahir brings a deeply international perspective to his work on development finance, institutional reform, and global governance. He joined us for this conversation in a personal capacity. We open by exploring Qahir's personal journey into the world of multilateralism, shaped by his family's move from Kenya to Canada at the dawn of the first Gulf War. From there, we ask Qahir to define multilateralism beyond the summits and headlines, and he makes the case that international cooperation quietly underpins the mundane parts of everyday life - from telecommunications to air travel. We trace the evolution of multilateral institutions across decades of geopolitical change & discuss why today's talk of institutional gridlock echoes tensions the system has weathered before, from the Cold War to the end of globalization's heyday.The conversation turns to the concept of "variable geometry" and the growing role of coalitions of small & middle powers in tackling shared challenges, from digital governance to AI regulation. We explore Qahir's co-authored article in Devex on the priorities facing the incoming UN Secretary-General, discussing the difference between acting as a custodian versus an architect of the institution, and what it will take to rebuild trust with citizens, politicians, and UN staff alike. Qahir also shares a memorable analogy about institutional "salamander rules" to explain how bureaucratic processes calcify over time and how AI could help institutions become faster & leaner without abandoning the safeguards that matter. We close by discussing how the private sector's relationship with multilateral institutions is shifting from transactional to collaborative, and why the next wave of innovation and investment opportunity lies in Africa.*****Qahir DhananiBCG: https://www.bcg.com/about/people/experts/qahir-dhanani LinkedIn: https://www.linkedin.com/in/qahir *****Mihaela Carstei, Paul M. Bisca, & Johan Bjurman Bergman co-host F-World: The Fragility Podcast. X: https://x.com/fworldpodcastInstagram: https://www.instagram.com/fworldpodcast/Website: https://f-world.orgMusic:"Tornado" by Wintergatan. This track can be downloaded for free at www.wintergatan.net. Video editing by: Alex Mitran - Facebook (facebook.com/alexmmitran), X (x.com/alexmmitran),or LinkedIn (linkedin.com/in/alexmmitran)EPISODE RESOURCES:Qahir Dhanani, Jim Larson, “Thenext UN chief must architect a new era of multilateralism,” DEVEX, March 11, 2026https://www.devex.com/news/the-next-un-chief-must-architect-a-new-era-of-multilateralism-112027TIMESTAMPS:00:00:00 Intro00:01:20 Qahir's background00:03:45 What is multilateralism & what has it brought us?00:08:07 Responding to the critique that multilateral institutions are stuck in the past00:12:42 Is globalization the driving force of multilateralism: Variable geometry and coalitions00:14:54 The cost of systemic fragmentation00:17:45 Sovereignty vs. shared benefit – the case for mini-lateral cooperation00:21:09 Digital sovereignty & the case for global AI governance00:25:22 Custodian vs. architect: what the next UN Secretary General must be00:29:30 Reform, modernization, & representation – the challenges ahead00:34:58 Rebuilding trust & cutting through institutional bureaucracy00:40:21 Using AI to streamline institutions without cutting corners00:43:07 What does the private sector want from multilateral reform?00:48:14 Public-private partnership in practice00:51:01 Innovation & investment opportunities beyond Europe and the US00:55:05 Advice for the next UN Secretary-General

This week on Dev Interrupted, Slack's Chief Product Officer, Jaime DeLanghe, joins the show to explain why enterprise AI value depends on embedding custom bots directly into your existing team communication loops rather than deploying them inside isolated, single-player chat silos. She breaks down the platform's shift toward open ecosystem standards like the Model Context Protocol (MCP) and how dynamic UI frameworks are transforming standard channels into active execution environments. Jaime details the operational realities of managing autonomous software fleets, including a striking look at how leading companies are placing hundreds of custom agents directly onto their corporate org charts.Life Beyond Tokenmaxxing Workshop: Watch the full replay on demand at linearb.io Follow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's guest:Slackbot MCP Client: Learn more about connecting your tools to Slackbot via the Model Context Protocol at the Slack BlogSlack Developer Hub: Start building your own agentic workflows and explore the latest tools at slack.devConnect with Jaime: LinkedInOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

This week on the Friday Deploy, Andrew Zigler is joined by Zapier's Kelly Vaughn to dive into the sudden return of Anthropic's Fable model, the realities of multi-threaded agentic engineering, and why the lowly engineering backlog is finally having its moment. To wrap things up, they review Charity Majors' latest advice on empathetic leadership and explore why the best way to win a workplace disagreement is to stop arguing and let an AI build the proof of concept.Life Beyond Tokenmaxxing Workshop: Watch the full replay on demand at linearb.io Follow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's guest:Follow Kelly on LinkedInFollow Kelly on SubstackCheck out Kelly's website kvlly.comFollow today's stories:Redeploying Fable 5It's Time To Put Humans Back In The SoftwareThree Ways to Give an AI Agent an IdentityBenchmarking AI Agents for Real Data ScienceWhy I Stopped Arguing With PeoplePaging Charity! How can engineering leaders avoid becoming Bond villains?The backlog is finally getting its momentOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

This week we discuss Jeremy Lewin's departure from the U.S. State Department's foreign aid bureau to the White House. His transition to the National Security Council ends a controversial leadership marked by the retreat of the U.S. from its long-held role as the world's leading bilateral donor. He is expected to be replaced by Andrew Veprek, who has pushed immigration and refugee restrictions at the State Department. As the United Nations continues to face budgetary constraints, we also analyze the potential merger of two major U.N. development agencies: the U.N. Development Programme, or UNDP, and UNOPS. While Secretary-General António Guterres sees this ambitious development reform as a way to overcome a yawning funding gap, UNDP chief Alexander De Croo and UNOPS Executive Director Jorge Moreira da Silva have butted heads over their vastly different visions for the future. During the conversation we also discuss our key takeaways from the Hamburg Sustainability Conference, including a new initiative that is designed to tackle debt, trade, climate finance, and multilateral reform to help reset the terms of global cooperation. To dig into these stories and others, Senior Reporter Adva Saldinger sits down with U.N. correspondent Colum Lynch and reporter Jesse Chase-Lubitz for the latest episode of our weekly podcast series. How can climate and nature investments move from ambition to action? In the sponsored segment of the episode, recorded live at Devex Impact House during London Climate Action Week, Kate Warren, Executive Editor and Executive Vice President at Devex, speaks with Waqas Batley, Senior Director, Conservation and Climate Finance Policy at The Nature Conservancy. Together, they explore how policy advocacy can help countries develop the plans, financial roadmaps, and regulatory systems needed to attract investment in nature and climate. The conversation looks at why nature should be understood as economic infrastructure, what finance ministries can do to send clearer signals to investors, and how approaches such as country platforms can help turn national climate and biodiversity priorities into investable pipelines. Sign up to Devex Invested: https://www.devex.com/newsletters/invested

Are you confusing a skyrocketing AI token bill with actual engineering value? This week on Dev Interrupted, Kraken's Engineering Operations Lead, Nik Sudan, joins the show to break down the harsh realities of moving agentic AI projects from pilot to production without compromising code health. He unpacks why raw AI adoption is a flawed vanity metric, detailing how his team uses tools like the LinearB MCP server to combine high-level engineering metrics with granular repository data to uncover hidden workflow bottlenecks. Finally, Nik reveals his exact playbook for translating complex data, like P90 cycle times, into a clear, business-driven narrative that secures vital buy-in from non-technical stakeholders. Life Beyond Tokenmaxxing Workshop: Watch the full replay on demand at linearb.io Follow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's guest:LinearB MCP Server: Learn how to chat with your engineering data and uncover hidden bottlenecks at linearb.io/platform/mcp-serverThe APEX Framework: Read LinearB's guide on the operating model for AI-era engineering teams at linearb.io/resources/apex-frameworkKraken: Learn more at www.kraken.comWebsite / Follow Nik:niks.space OFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

In a special edition of the This Week in Global Development podcast, Devex cofounder and Executive Vice President Alan Robbins sits down with Brazilian thoracic surgeon Dr. Ricardo Sales do Santos to discuss a revolutionary approach to tackling lung cancer in medically underserved communities in Brazil. As the most lethal form of cancer globally, lung cancer often goes undetected until its final stages, but Dr. Santos and the Bristol Myers Squibb Foundation are working to change that narrative through a combination of mobile technology and local capacity building. By bringing advanced CT scanning units directly into high-risk, low-income communities, they are catching tumors when they are small and potentially curable, fundamentally shifting the odds for thousands of patients. The conversation also touches on the logistical and cultural hurdles of delivering specialized oncology care to remote areas. Dr. Santos highlights the importance of “bringing the clinic to the patient,” utilizing mobile CT units and telemedicine to bridge the gap in healthcare access. Beyond the technology, the success of the program relies heavily on empowering local health workers and community members to recognize early cancer warning signs and overcome the stigma associated with a cancer diagnosis. This approach not only improves individual health outcomes but also strengthens the broader healthcare system, offering a scalable model for global health initiatives. To learn more about sustainable improvements in cancer care and get a compelling look at how local solutions can drive global change, listen to this special edition of This Week in Global Development. For more international development news, visit: http://www.devex.com Visit Strengthening Care Systems — a series raising awareness of the scale of the global lung cancer burden and the systems-level changes required to address it: https://pages.devex.com/strengtheningcaresystems.html

Is the golden age of exponential AI growth already flattening out? This week on the Friday Deploy, Ben and Andrew unpack Steve Yegge's "Flat Curve Society" theory to explore what happens when frontier models stop getting exponentially better. The hosts also dive into the evolution of loop-driven development, the value of markdown based local knowledge bases, and why comparing different AI models usually just exposes the flaws in your own prompts. Finally, they review Midjourney's bizarre new echolocation spa concept and explore the true limits of AI disruption through the hilarious allegory of "The Wizard with the Very Defensible Pond." Life Beyond Tokenmaxxing Workshop: Watch the full replay on demand at linearb.io Follow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:A New Era of MidjourneyThe Flat Curve SocietyFrom Test-Driven to Loop-Driven DevelopmentA failed universal language explains why you keep picking the wrong AI outputBuilding a Local Knowledge Base in Google's Open Knowledge Format (OKF)The Wizard With the Very Defensible PondOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

Developers are like water: if you make your security protocols too difficult, they will find a way to flow right around them. This week on Dev Interrupted, bestselling author and OWASP Top 10 Project Leader Tanya Janca returns to unpack why vibe coding has officially made the list of the most critical security risks in software development. Tanya breaks down the psychology of bad code, explains why the modern software engineer has become the primary attack surface, and shares actionable strategies for shifting security left directly into your AI prompts. Finally, she provides practical, behavioral solutions for building a golden path that makes secure coding the easy choice for your engineering team. Register here: for the June 25th workshop, Life Beyond Tokenmaxxing, to learn how to measure real AI impact and ROI across the SDLC.Follow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's guest:SheHacksPurple: Learn secure coding from Tanya at shehackspurple.caDevSec Station: Listen to Tanya's bite-sized security podcast for developers at devsecstation.comSecure My Vibe: Download Tanya's free AI secure coding prompt library at securemyvibe.ca The Psychology of Bad Code: Read Tanya's insightful blog series on behavioral economics and application security on the SheHacksPurple BlogOWASP Top 10: Learn more about the most critical security risks to web applications at owasp.orgTanya's Newsletter: Sign up for Tanya's newsletter at  newsletter.shehackspurple.ca  Connect with Tanya: LinkedIn | Twitter/XOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

This week on the Friday Deploy, Ben and Andrew unpack the sudden disappearance of Fable 5 and discuss whether Meta's aggressive pivot to AI data labeling is destroying its legendary engineering culture. The hosts also explore the rise of highly capable open source Chinese models like GLM 5.2 and why tech giants are considering them to slash skyrocketing inference bills. Finally, they dive into new research proving that as AI execution takes over, human domain expertise and strict production observability are more critical than ever. Register here: for the June 25th workshop, Life Beyond Tokenmaxxing, to learn how to measure real AI impact and ROI across the SDLC.Follow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:KayfableWhy is Meta destroying its engineering organization?AI demands more engineering discipline. Not lessZ.ai's open-weights GLM-5.2 beats GPT-5.5 on multiple long-horizon coding benchmarks for 1/6th the costMicrosoft Mulls China's DeepSeek for Copilot, Probably to Trump's ChagrinAgentic coding and persistent returns to expertiseOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

What if the secret to fixing your overwhelmed SDLC is not a better AI coding model, but a smarter productivity context engine? This week on Dev Interrupted, LinearB founders Ori Keren and Dan Lines join the show to discuss the messy middle of AI adoption and the painful transition from the traditional SDLC to the Agentic Development Life Cycle. They unpack why the era of cheap AI experimentation is over, how rising token costs are forcing engineering leaders to prioritize strict business ROI, and how autonomous tools are fundamentally changing the daily workflow of developers.Register here: for the June 25th workshop, Life Beyond Tokenmaxxing, to learn how to measure real AI impact and ROI across the SDLC.Follow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's guest:LinearB: Learn how to transform your SDLC and build an engineering context engine at linearb.iogitStream: Explore LinearB's workflow automation tool for routing pull requests at linearb.io/platform/gitstreamFollow Ori and Dan on LinkedIn: Ori Keren | Dan LinesOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

Anthropic just dropped a dragon-class model on our laps, but can you steer it without torching your codebase in the process? This week on the Friday Deploy, Ben and Andrew unpack the sudden arrival of Fable 5 and how to leverage it to scrutinize your systems before the massive API paywall hits. They also take aim at the unsustainable trend of tokenmaxxing and explore how intelligent model routing can drastically cut your AI spend. Finally, they tackle the unmaintainable mess left behind by AI rockstar developers and share how they are orchestrating their own agent-to-agent collaboration.OFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

In this episode of Elixir Wizards, Charles Suggs and Emma Whamond are joined by Ellyse Cedeno, founder of Heuristic Salvo and a software engineer and product leader with more than 25 years of experience across early internet platforms, gaming, health tech, and distributed systems. Ellyse shares the winding path that took her from early search engines and Netscape to game development, medical research at Mount Sinai, and eventually to Elixir. Along the way, she talks about staying curious over a long technical career, rediscovering joy through side projects, and why being willing to feel like a beginner again can be one of the most useful skills a developer can build. The conversation explores what it means to grow as an engineer in a world where AI tooling is becoming part of the everyday workflow. Ellyse makes the case that technical skill still matters, but the human parts of software development (like judgment, curiosity, communication, trust, and influence) are becoming increasingly important. We also talk about soft influence and how developers can create change inside organizations without relying on hard authority. Key Topics Discussed in this Episode: Ellyse's career path through early internet platforms, gaming, health tech, and distributed systems Moving from Netscape and search engines to medical research and software consulting Discovering Elixir through an interest in concurrent and distributed systems Why beginner's mindset still matters after decades in tech How neurodivergence, curiosity, and deep focus shape Ellyse's approach to programming Rediscovering joy in programming through side projects and experimentation Building an MMORPG game server in Elixir Exploring hardware, Nerves, and live theremin demos The role of passion projects in professional growth Protecting time for learning in productivity-focused environments Work-life balance differences between the U.S. and Europe How AI tools are changing expectations for modern developers Why AI does not replace judgment, taste, or technical understanding Understanding business needs instead of only focusing on technical preferences Introducing Elixir into a TypeScript-heavy organization Using Elixir microservices to solve specific technical problems What “soft influence” looks like in engineering teams Building trust through one-on-one conversations Knowing when influence is working and when it is not Negotiating technical decisions without turning them into power struggles The relationship between technical competence and interpersonal skill Managing imposter syndrome during pair programming and collaborative work Documentation as a visibility and ownership tool Community involvement, conference speaking, and finding your people Staying curious without burning out Why the human side of software development still matters Links Mentioned: https://en.wikipedia.org/wiki/Netscape Icahn School of Medicine at Mt. Sinai https://icahn.mssm.edu/ Evernote https://evernote.com/ Joplin https://joplinapp.org/ Book: Elixir in Action by Saša Jurić https://www.manning.com/books/elixir-in-action-third-edition Book: The Little LISPer https://www.scribd.com/doc/263131641/The-Little-Lisper Ellyse's Goatmire Talk https://goatmire.com/speaker/ellyse-cedeno Nerves https://nerves-project.org/ xHain Hack & Makespace in Berlin https://x-hain.de/en/ https://cursor.com/ Haskell Programming Language https://www.haskell.org/ Java Programming Language https://www.java.com/en/ Clojure Programming Language https://clojure.org/ Scheme Programming Language https://www.scheme.org/ TypeScript Programming Language https://www.typescriptlang.org/ Nostrum Library https://hexdocs.pm/nostrum/intro.html Gleam Programming Language https://gleam.run/ Book: Getting Past No by William Ury https://www.williamury.com/getting-past-no/ “The Gambler” by Kenny Rogers https://www.youtube.com/watch?v=7hx4gdlfamo Ted Talk: Do schools kill creativity? | Sir Ken Robinson https://youtu.be/iG9CE55wbtY Ellyse's Codeberg https://codeberg.org/ellyxir Ellyse's Game Server Repo https://codeberg.org/ellyxir/gameserver Goatmire Elixir & NervesConf 2026 https://www.goatmire.com/

What happens when you strip away decades of engineering abstractions and let AI navigate the wild west between your initial intent and the final outcome? This week on Dev Interrupted, Anush Elangovan, VP of AI Software at AMD, returns to unpack the rapid shift toward an agentic software development lifecycle. Anush introduces the concept of "Agentic IO," a workflow where engineers focus strictly on high-level goals while AI handles the complex implementation. The conversation also highlights the expanding productivity wingspan of modern developers, the power of local open source models, and why speed remains the ultimate competitive moat. Learn why: LinearB is a Leader in the 2026 Gartner® Magic Quadrant™ for Developer Productivity Insight PlatformsFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's guest:AMD ROCm: Learn more about AMD's open-source software stack for AI at rocm.docs.amd.com and on GitHub.AMD Advancing AI 2026: Register for AMD's flagship global AI event taking place July 22-23 in San Francisco at amd.com/advancing-ai.Follow Anush on LinkedIn: Anush Elangovan | AMD blogOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

Much of Seth Berkley's career has been an attempt to answer the question: How do you get vaccines to people who aren't well-served by an inequitable global health system? When the COVID-19 outbreak exploded in early 2020, that question took on new urgency — along with a mind-spinning slew of political, economic, technological, and cultural complications. Berkley, then the CEO of Gavi, the Vaccine Alliance, had a pretty good idea what was coming. As early as February 2020 he was warning publicly that if researchers were successful in developing a COVID-19 vaccine, lower-income countries would struggle to access them. That is exactly what happened. It is also what led Berkley to help launch COVAX, the global initiative to deliver COVID-19 vaccines around the world. In the wake of the pandemic, the relationships between politics, society, and vaccines have only grown more fraught. One example: Secretary of Health and Human Services Secretary Robert F. Kennedy Jr. has personally intervened to block U.S. funding to Gavi. Berkley, a physician and infectious disease epidemiologist, joined Devex's Theory of Change podcast to discuss the lessons of the COVID-19 response, the long and complicated history of humanity's relationships with vaccines, the incredible potential of new technologies — and the deeply troubling risks that some of them pose. His new book is called “Fair Doses: An Insider's Story of the Pandemic and the Global Fight for Vaccine Equity.”

Jason Valentino is Head of Software Engineering Strategy at BNY, where he oversees developer tooling, DevEx, platform workflows, and software delivery governance across more than 8,000 engineers.In this session from DX Annual, Jason shares how BNY moved beyond AI coding assistants to rethink the entire software delivery lifecycle. He explains how his team identified bottlenecks across the SDLC, prioritized automation opportunities, and applied AI to planning, peer review, testing, change management, and compliance workflows.Jason also discusses what it takes to scale AI inside a highly regulated enterprise, including rewriting policies, partnering closely with risk and audit teams, and building a culture that encourages experimentation and rapid sharing of ideas.Where to find Jason Valentino:• LinkedIn: https://www.linkedin.com/in/jasonvalentinoIn this episode, we cover:(00:00) Intro (01:20) Early results from AI coding tools at BNY(04:08) The 3X stress test: What breaks if engineering throughput triples?(06:56) Three ways to apply AI across the SDLC: IDE and CLI tools(08:07) Using autonomous AI agents for repetitive engineering tasks(09:16) Embedding AI directly into SDLC workflows(12:27) Why leaders should encourage experimentation and “start saying yes”(15:00) Q&A: How platform and productivity teams are evolving to support AI(16:33) Q&A: Rewriting policies and controls for AI-assisted software delivery(17:52) Q&A: How AI is affecting software quality and test ownership(19:00) Q&A: What Jason is most proud of: Practical examples of AI across the SDLC(20:30) Q&A: How BNY handles duplicated work across AI initiatives(22:30) Q&A: How BNY uses AI to support regulatory and compliance work(23:30) Q&A: Automating code reviews and change tickets(25:55) Q&A: How increased AI-driven throughput is affecting on-call and reliability(27:11) Q&A: How BNY works with risk and audit partners to move quickly with AI(29:01) Q&A: How BNY scales successful AI use cases across the organization(30:42) Q&A: What Jason is most proud of after BNY's busiest year with AIReferenced:• AI-assisted engineering: Q4 impact report• Measuring AI code assistants and agents• Measuring developer productivity with the DX Core 4• Windsurf• Claude Code by Anthropic | AI Coding Agent, Terminal, IDE• Codex | AI Coding Agent

This week on the Friday Deploy, Ben and Andrew unpack the AI build-versus-buy debate, Microsoft's new independent foundation models, and the growing revolt of mathematicians against unsubstantiated AI-generated proofs. The hosts also explore Stanford's Socratic rulebook for AI coding assistants and discuss Kent Beck's warning that engineering teams need to build "trust factories" to counter the rapid chaos of AI-assisted development. Finally, they close with a defense of Linux primitives and why you should probably be using a systemd timer instead of the latest shiny AI tool. Learn why: LinearB is a Leader in the 2026 Gartner® Magic Quadrant™ for Developer Productivity Insight PlatformsFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:The AI SaaSpocalypse is a mirageMathematicians warn of AI threats to profession as industry encroachesIntroducing MAI-Code-1-FlashAI Agent Guidelines for CS336 at StanfordTrust FactoryYou Don't Love systemd Timers EnoughOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

This week, we unpack the latest on the Ebola outbreak in the Democratic Republic of Congo and Uganda. With no approved vaccines or treatments for the Bundibugyo species driving the spread, we dive into the race to develop a vaccine and the critical funding shortfalls standing in the way. While pledges have been made, much of that support has yet to reach those affected on the ground. We also discuss the congressional hearings on Trump's fiscal year 2027 foreign affairs budget request, which featured a debate on the Ebola crisis. With this being the first outbreak since the dismantling of USAID, we break down the United States' approach to the health emergency. To dig into these stories and others, Business Editor David Ainsworth sits down with Senior Reporters Sara Jerving and Michael Igoe for the latest episode of our weekly podcast series. Check out Devex's new podcast series Theory of Change: https://www.devex.com/focus/theory_of_change

This week, Andrew sits down with LinkedIn Distinguished Engineer Karthik Ramgopal to explore the reality of deploying agentic platforms across a massive organization. Karthik unpacks the mechanics of AI memory, spanning procedural and episodic structures, and explains how to build durable engineering primitives that actually last. Finally, the two discuss the enduring importance of system fundamentals and why LinkedIn is restructuring its internship program into AI-native pods to foster a new culture of two-way mentorship. Learn why: LinearB is a Leader in the 2026 Gartner® Magic Quadrant™ for Developer Productivity Insight PlatformsFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:Follow Karthik on LinkedIn: Karthik Ramgopal OFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

Coefficient Giving, one of the world's largest effective-giving funders, is about to go even bigger. On the heels of its biggest funding year ever in 2025 — in which it channeled over $1 billion to highest-impact causes — the organization formerly known as Open Philanthropy and funded by Facebook cofounder Dustin Moskovitz and his wife Cari Tuna is eyeing annual growth upward of 50% and bringing on more staff to get it done. The person behind that vision is Alexander Berger, Coefficient Giving's cofounder and CEO. Berger is in charge of turning Facebook wealth — and, increasingly, funds from other donors — into as many lives saved and improved as possible. The organization is a major funder in global health and development, catastrophic risk, research and innovation, and even farm animal welfare. Last week, Coefficient Giving launched a new pooled fund to tackle Group A Streptococcus — an easily treated disease that is still responsible for nearly 700,000 deaths a year — a cause that reflects the organization's framework for tackling problems that are important, neglected, and tractable. In a rare, in-depth interview with Devex Senior Reporter Michael Igoe, Berger sheds light on Coefficient Giving's rapid growth plans, its strategy for choosing high-impact causes, the rise of artificial intelligence philanthropy, and his own approach to affecting change in an uncertain world. This is the first episode of Theory of Change, a new podcast series from Devex featuring candid interviews with leaders shaping the future of global development.

Are we officially entering the "Eternal Sloptember"? This week on the Friday Deploy, Ben and Andrew unpack the quiet rebellion against skyrocketing API costs as teams transition to fine-tuned local models. They also explore the changing physical architecture of AI data centers, the dangers of using autonomous tools as a crutch for broken workflows, and why spec-driven development is critical for keeping agentic code in check. Finally, the hosts share their latest personal agent experiments, from benchmarking open-source models on a local Mac Studio to taming an AI-generated second brain.Learn why: LinearB is a Leader in the 2026 Gartner® Magic Quadrant™ for Developer Productivity Insight PlatformsFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:Outsourcing plus LocalAI will soon become more economical vs Frontier labsAI Datacenters Were Built for GPUs. What Happens When You Remove the GPUs?"The AI Can Do It" Is Not an Excuse To Tolerate a MessThe Eternal SloptemberI'm tired of talking to AIIf you let AI do your writing, I will come to your house and kill youA Blast from the Past: SDD and the Illusion of Known ScopeAndrew's paper: Mise en Place for Agentic Coding: Deliberate Preparation as Context Engineering MethodologyOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

What if you stopped treating observability as a simple insurance policy and started viewing it as a profit center? This week, Andrew sits down with Honeycomb CEO Christine Yen to explore how observability, data science, and product development are colliding in the agentic era. Christine explains why production signals must become compiler inputs for autonomous agents and how MCP tools are democratizing telemetry for entire organizations. Finally, the two discuss Honeycomb's latest Innovation Week announcements and the exact strategy for reframing observability from basic risk mitigation into a clear revenue accelerant.Learn why: LinearB is a Leader in the 2026 Gartner® Magic Quadrant™ for Developer Productivity Insight PlatformsFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:Honeycomb Blog: Read deep dives on SLOs at honeycomb.io/blogHoneycomb Innovation Week: Explore the latest announcementsRequired Reading: Check out the book Observability Engineering by Charity Majors, Liz Fong-Jones, and George Miranda.HumanX Interview: A Codebase Is No Longer the Source of Truth"Production is a Compiler Input": Chad Fowler's take on the future of code generation. Follow Christine on LinkedInOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

Andrew and Ben recap the biggest announcements from Google I/O, breaking down everything from the new Gemini Spark agent to Gemini 3.5 Flash. They also explore how leaders can distill their management style using AI, debate whether complex note-taking apps are a form of procrastination, and call on listeners to participate in a new vibe coding research study. Finally, Andrew shares his "Skills Olympics" methodology for stress-testing and managing his own personal fleet of AI agents. Learn why: LinearB is a Leader in the 2026 Gartner® Magic Quadrant™ for Developer Productivity Insight PlatformsFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:PollyReach: Give your agent a real number and voice to make calls.Google is launching its own version of OpenClawGoogle touts its tokenmaxxing and capex spending amid AI orgyVibe Coding Experience SurveyDistilling yourselfOpen-source alternative to ObsidianOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

With Google I/O 2026 underway this week, Andrew sits down with Matthew McCullough, VP of Android Development Experiences at Google, to talk about the AI evolution happening across the Android ecosystem. Matthew shares his insights on why developers are rapidly transitioning into agent orchestrators, why CLIs are cool again, and how tools like AI Studio have rolled out a massive welcome banner for anyone to actively participate in the creation process. Finally, the two explore the future of mobile user interfaces and how the latest Android 17 developments are stripping away legacy friction to seamlessly get users straight to the good part.OFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

In a special edition of the This Week in Global Development podcast, Devex cofounder and Executive Vice President Alan Robbins sits down with Brazilian thoracic surgeon Dr. Ricardo Sales do Santos to discuss a revolutionary approach to tackling lung cancer in medically underserved communities in Brazil.   As the most lethal form of cancer globally, lung cancer often goes undetected until its final stages, but Dr. Santos and the Bristol Myers Squibb Foundation (are working to change that narrative through a combination of mobile technology and local capacity building. By bringing advanced CT scanning units directly into high-risk, low-income communities, they are catching tumors when they are small and potentially curable, fundamentally shifting the odds for thousands of patients.   The conversation also touches on the logistical and cultural hurdles of delivering specialized oncology care to remote areas. Dr. Santos highlights the importance of “bringing the clinic to the patient,” utilizing mobile CT units and telemedicine to bridge the gap in healthcare access. Beyond the technology, the success of the program relies heavily on empowering local health workers and community members to recognize early cancer warning signs and overcome the stigma associated with a cancer diagnosis. This approach not only improves individual health outcomes but also strengthens the broader healthcare system, offering a scalable model for global health initiatives.   To learn more about sustainable improvements in cancer care and get a compelling look at how local solutions can drive global change, listen to this special edition of This Week in Global Development. For more international development news, visit: http://www.devex.com Visit  Strengthening Care Systems — a series raising awareness of the scale of the global lung cancer burden and the systems-level changes required to address it: https://pages.devex.com/strengtheningcaresystems.html

Is vibe coding actually good now? This week on The Friday Deploy, Andrew and Ben explore the convergence of vibe coding and agentic engineering, unpack the decline of the traditional technical interview, and discuss why companies like Warp are prioritizing AI prototypes over planning meetings. They also celebrate Andrew's newly published research on "mise en place" context engineering. Finally, they break down the enterprise AI "last mile" crisis and share how they are using personal knowledge graphs to upskill their own agents.Read the guide: The APEX FrameworkFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:AOL for agentsVibe coding and agentic engineering are getting closer than I'd likeMise en Place for Agentic Coding: Deliberate Preparation as Context Engineering MethodologyBuild, then alignThink the technical interview is dead? Think againThe last mile is where enterprise AI actually diesOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

This week, we look ahead to the key talking points at the 79th World Health Assembly, where the Devex team will be reporting from next week. As the World Health Organization continues to operate on a deficit, and with the U.S. withdrawal from the agency, we dig into what the future holds for WHO and how this shifting financial landscape will reshape the global health architecture. With WHO facing funding constraints, we explore how this financial shortfall could impact the agency's response to the new hantavirus outbreak and its ongoing fight against HIV. During the episode, we also highlight the sessions we are most looking forward to at Devex Impact House, happening on the sidelines of WHA. Secure your spot by registering here: https://pages.devex.com/devex-at-wha-79.html To offer a preview of the 79th WHA, Senior Editor Rumbi Chakamba sits down with reporters Jenny Lei Ravelo and Andrew Green for the latest episode of our weekly podcast series. You can now also request an in-person invite or register for on-demand content for our upcoming Devex Impact House @ London Climate Action Week here: https://pages.devex.com/devex-at-london-climate-action-week.html

Does it feel like your favorite AI tool is declared dead one week, only to be resurrected the next? This week, Andrew sits down with Bryan Bischof, Head of AI at Theory Ventures, to explore the hidden levers of inference systems and the industry's obsession with prematurely writing off useful tools. Bryan shares his experiences with why prompt optimization is mostly a dead end, the secret to building high-performing data agents, and how his team builds operational software for VCs. The two also break down the origins of the satirical rip-grep.com and drop hints about Bryan's highly anticipated next AI game show experiment. AI Council 2026: Catch Bryan's track on inference systems and get tickets.Read the guide: The APEX FrameworkFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:Events: Catch Bryan's track live at the AI Council Conference.Writing: Check out the April Fools manifesto at rip-grep.comTheory Ventures: Learn more about the work happening at Theory Ventures.X/Twitter: @BEBischofLinkedIn: Bryan BischofOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

Are you stuck in the "messy middle" of AI adoption where individual productivity doesn't actually translate to organizational impact? This week on the Friday Deploy, Andrew and Ben break down the hilarious and terrifying realities of agentic intention drift, exploring how a "goblin" invasion in ChatGPT and poorly scoped tokens are wreaking havoc on production environments. They also navigate this messy organizational adoption phase, discussing why senior developers are accelerating while juniors stall out on the K-shaped productivity curve. Finally, the hosts wrap up with a look at the open-source renaissance of agentic harnesses like Lattice and Pi.dev.Read the guide: The APEX FrameworkFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:Where the goblins came fromAI didn't delete your database, you didWhen everyone has AI and the company still learns nothingFragments: May 5Specsmaxxingclaude code is not making your product betterOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

If you aren't the one educating your users on the fundamentals of AI, your competitors will happily do it for you. This week on Dev Interrupted, Andrew sits down with Philip Kiely, Head of AI Education at Baseten and author of Inference Engineering, to discuss why the secret to winning the AI market is owning the educational narrative through active market development. They explore the rise of the "Double-T" shaped engineer, the hidden complexities of scaling the inference stack, and why the most successful AI companies treat developer education as a mission-critical go-to-market motion.Read the guide: The APEX FrameworkFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:Baseten: Explore the inference platform where Philip serves as Head of AI Education.Inference Engineering: Download the free PDF or order a paper copy of Philip's comprehensive guide to the AI infrastructure stack.LinkedIn: Philip Kiely X/Twitter: @philipkiely Website: philipkiely.com OFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

Are you at the top of your company's tokenmaxxing leaderboard yet? This week on the Friday Deploy, Andrew and Ben explore the controversial trend of "tokenmaxxing" sweeping through tech giants like Meta and Disney, as well as GitHub Copilot's shift to usage-based pricing that signals the end of the cheap AI era. The hosts also break down a terrifying incident where a rogue AI agent wiped out a production database and examine a new "vegan" language model trained exclusively on pre-1931 historical data. Finally, they react to a study revealing that 35% of all new websites are now AI-generated and close out the show with the drunk musings of a senior engineer. Read the guide: The APEX FrameworkFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:An AI Agent Just Destroyed Our Production Data. It Confessed in Writing.Tokenmaxxing Is The Dumbest Metric In Tech Right NowIntroducing talkie: a 13B vintage language model from 1930Study Finds A Third of New Websites are AI-GeneratedFlipbook is an infinite visual browser generated entirely on demand in real time.Drunk Post: Things I've Learned as a Senior EngineerOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

What if deploying a new capability to an industrial robot arm was as seamless as pushing an update to a web app? This week, Andrew sits down with Brian Gerkey, CTO of Intrinsic and a titan of the open-source robotics community, to discuss how modern AI is finally giving robotics the "brains" to handle the unpredictable physical world. Brian breaks down how to move away from rigid, monolithic automation toward software-defined, modular robotics using tools like ROS (Robot Operating System) and digital twins. Finally, Brian invites developers of all backgrounds to test their skills in Intrinsic's new AI for Industry Challenge by using AI to solve one of the hardest problems in manufacturing: plugging in a tangled cable. Read the guide: The APEX FrameworkFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:Brian's Website: Learn more about Brian's work, research, and history in the open-source robotics community. Intrinsic: Explore the robotics software company led by Brian, which provides tools like Flowstate to build and deploy intelligent robotic solutions.AI for Industry Challenge: Get the toolkit and register to compete in Intrinsic's new challenge to solve complex dexterous manipulation and cable routing.ROS (Robot Operating System): The open-source middleware suite that has become the global standard for robotics software development.OFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

Is the era of cheap, unlimited AI tokens officially over? This week on the Friday Deploy, Andrew and Ben walk through the sudden wave of AI pricing chaos—from GitHub Copilot's panic-paused signups to Anthropic's confusing pricing tests—and break down the terrifying Vercel security breach caused by a single over-permissioned AI tool. They also examine 12 game-changing architecture patterns exposed in the Claude Code leak to help you safely orchestrate your own agentic workflows. Finally, they discuss how to avoid the lethal trifecta of agentic security risks before mourning the tragic deletion of their Claude Code buddies.Read the guide: The APEX FrameworkFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:Changes to GitHub Copilot Individual plansIs Claude Code going to cost $100/month? Probably not—it's all very confusingAnthropic, OpenAI, Google, and Microsoft agree that the harness is the product. They disagree on the price.12 Agentic Harness Patterns from Claude CodeVercel April 2026 security incidentFragments: April 21Claude Managed Agents: get to production 10x fasterOFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

Forget the massive GPU clusters. According to Tim Dettmers, research scientist at Ai2, you can build a state-of-the-art AI coding agent with what he calls a "hot plate and a frying pan." This week on Dev Interrupted, Andrew sits down with Tim to unpack how his resource-strapped team built the SERA model using a fraction of the compute power of major labs. They explore the tactical engineering behind synthesizing training data from private codebases without verification tests, proving that the open-source community is uniquely positioned to out-specialize frontier models. Finally, Tim shares his contrarian take on the future of token economics, explaining why the cost of AI might actually spike as compute efficiency hits a physical wall.OFFERSStart Free Trial: Get started with LinearB's AI productivity platform for free.Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era.LEARN ABOUT LINEARBAI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production.AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance.AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil.MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.