Your agents are starving! Airbyte’s Michel Tricot on the data ingestion crisis

If your AI agents are starving for accurate context, or breaking production because they have way too much access, you are officially in the middle of the data ingestion crisis. This week, Airbyte CEO and co-founder Michel Tricot unpacks the massive data access and context sprawl challenges that are crippling AI workflows in production. He and Andrew dive into the critical need for strict data permissions, automated entity resolution, and why the transition to agentic workflows perfectly mirrors the paradigm-shifting migration from bare-metal servers to the cloud. Finally, Michel explains why obsessing over short-term AI ROI is a massive mistake, revealing how Airbyte measures true success with their internal automation project, Hydra.Get the guide: Your software factory needs a context layerFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's guest:Airbyte: Explore the open-source data integration platform powering AI context at airbyte.comAgent Blueprint: Read Michel Tricot's newsletter on building agentic data infrastructure on SubstackConnect with Michel: 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 unpack Nvidia's massive acquisition of Hugging Face and what it means for the future of localized models. They also explore the multiplayer updates in OpenClaw 2.0, how relentless AI scraper bots are overwhelming kernel.org, and how engineering leaders can continuously balance safe infrastructure investments against volatile technology bets. Finally, they discuss why a strong engineering culture remains the ultimate productivity hack and how autonomous agents will only amplify existing organizational dysfunction. 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:NVIDIA to Acquire Hugging FaceTeaching Everyone to Fish for TokensOpenClaw 2.0, AccidentallyCreepy crawliesReject Change, SometimesGood Culture is the Biggest Productivity Hack, Not AIOFFERSStart 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 special episode, Andrew hosts HumanLayer CEO Dexter Horthy, Warp Head of Product Engineering Aloke Desai, and LinearB COO Dan Lines. They debate why human ownership of pull requests remains nonnegotiable and how to implement "night vision" observability across automated workflows. The panel also explores why incident management is the final frontier for AI and how to get your team excited about building the factory instead of fighting it.Get the guide: Your software factory needs a context layerFollow 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.

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.