Sloppypasta culprits, unpacking MCP’s spotlight, and Anthropic wants your agents to work the graveyard shift

Are rolling token blackouts and late-night AI coding shifts about to become the new normal for developers? This week on the Friday Deploy, Andrew and Ben explore the shifting economics of AI compute before debating whether the Model Context Protocol (MCP) was fundamentally overhyped. The hosts also dive into "context anchoring" to prevent model compaction during long coding sessions, why optimizing the wrong bottlenecks makes AI an amplifier for bad processes, and the nostalgic resurgence of the decentralized "small web." Finally, they break down the new rules of workplace AI etiquette to help you avoid serving your coworkers "sloppy pasta" disguised as real work.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:MCP is Dead; Long Live MCP!Context AnchoringIf you thought the speed of writing code was your problem - you have bigger problemsThe “small web” is bigger than you might thinkStop SloppypastaOFFERSStart 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.

Autonomous agents are pushing deployment speeds to the absolute limit, but is our security infrastructure ready for the consequences? Andrew sits down with Chainguard CEO Dan Lorenc to discuss the severe supply chain risks of this new frontier and what it takes to safely transition to an agent-first engineering model. They explore how engineering teams can safely accelerate deployments by turning restrictive guardrails into frictionless "guide rails" for their AI agents. Finally, the conversation unpacks the future of open source, detailing how AI might either spam projects into dormancy or solve the ecosystem's long-standing sustainability crisis by stepping in as automated, full-time maintainers.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:Chainguard: Learn more about how Dan and his team are securing the software supply chain.Dan Lorenc on LinkedIn: Connect with Dan to follow his predictions and insights.Gastown, and where software is going: Read Dan's article exploring the Brownian Ratchet principle, multi-Claude, and eventual determinism.EmeritOSS: Explore Chainguard's initiative to provide sustainable stewardship for mature, end-of-life open-source projects.Daniel Stenberg's Blog: Insights from the Curl creator regarding the influx of AI-generated vulnerability reports.Chainguard Assemble: Catch up on the latest announcements from Chainguard's user conference.OFFERS Start 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 LINEARB AI 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 we heading toward a bizarre future where your engineering salary is paid in AI compute tokens instead of cash? Andrew and Ben tackle the latest tech industry shakeups, starting with Meta's acquisition of Moltbook and the controversial idea of making inference limits a core employee benefit. They also break down Charlie Guo's harness engineering playbook, the growing pains behind recent AWS AI-driven outages, and the toxic pressure to constantly run dozens of autonomous agents. Finally, they wrap up by sharing their own agentic weekend projects and debating the catastrophic risks of vibe-coding your laptop's file permissions.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:Silicon Valley is buzzing about this new idea: AI compute as compensationThe Emerging "Harness Engineering" PlaybookMeta acquired Moltbook, the AI agent social network that went viral because of fake posts“A spate of outages, including incidents tied to the use of AI coding tools”, right on scheduleEvery minute you aren't running 69 agents, you are falling behindOFFERS Start 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 LINEARB AI 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.

Right now, a lot of engineering leaders are stuck in the same loop: rolling out AI tools only to watch their teams quietly drift back to business as usual. Andrew sits down with James Everingham, former Head of Dev Infra at Meta and current CEO of guild.ai, to discuss how to break this cycle by treating AI not just as an autocomplete tool, but as a "sentient fabric" woven directly into your software development lifecycle.  They explore how replacing top-down AI mandates with impossible business challenges—like eliminating code freezes entirely—empowers developers to organically build game-changing tools like conversational onboarding agents. Finally, James breaks down why 2026 is the year of the agent and how his team is building the enterprise infrastructure needed to safely govern, audit, and scale collaborative agent workflows.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:Learn more about Guild: guild.aiFollow James Everingham: 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.

Has the cost of software development officially dropped below the minimum wage? Andrew and Ben examine this economic shift alongside the rapid open-source growth and security implications of the OpenClaw project. They also explore Steve Yegge's concept of a federated wasteland for orchestrators and how the new Perplexity Computer is stepping up to act as a persistent, always-on digital coworker.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:OpenClaw rocks to GitHub’s most-starred status, but is it safe?Welcome to the Wasteland: A Thousand Gas TownsIntroducing Perplexity ComputerSoftware development now costs less than than the wage of a minimum wage workerScott Werner’s Works on My machineTraffic Jam ExplorerOFFERSStart 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.

Pausing a product roadmap for an entire month to point 700 engineers at a single goal is a significant structural shift, but it transformed monday.com. Andrew sits down with VP of R&D Sergei Liakhovetsky to uncover how fixing core infrastructure and adopting a cell-based architecture paved the way for platform scale. Sergei details the exact framework his leadership team used during their 30-day pause to launch user solutions while maintaining a strict zero-bureaucracy policy. The conversation also explores the new realities of reliability as platforms transition from being CPU-bound to heavily GPU-bound under the weight of automated agents.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:monday magic: A tool for generating initial work solutions and boards using simple prompts.monday vibe: An app builder that allows users to create custom applications on top of the monday.com platform.Sidekick: The horizontal AI assistant/copilot that works across the entire platform to help with tasks like data management and content generation.Agent Factory: A platform for building vertical, specialized agents that can handle specific workflows and roles.Connect with Sergei Liakhovetsky 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 break down a busy week on the Friday Deploy, starting with the market reaction to new COBOL tools and the permissions oversights that led to recent outages at AWS. They also explore the shifting landscape of developer productivity studies, the security risks of cloud-hosted agents, and the latest cybersecurity takeaways from the International AI Safety report. Finally, they close out the episode by checking in on a retired Claude model that was given a blog.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:IBM Didn’t Lose 13% Because COBOL DiedAWS suffered ‘at least two outages’ caused by AI tools, and now I’m convinced we’re living inside a ‘Silicon Valley’ episodeWe are Changing our Developer Productivity Experiment DesignDeepfakes spreading and more AI companions’: seven takeaways from the latest artificial intelligence safety reportGreetings from the Other Side (of the AI Frontier)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.

Your keyboard is the biggest bottleneck in your engineering workflow. This week, Andrew sits down with Wispr co-founder and CTO Sahaj Garg to discuss why traditional voice dictation failed us, and how his team is rebuilding trust by using contextual models to capture a developer's raw intent rather than treating speech models as "dumb" tools that just produce literal transcripts. Together, they explore the engineering hurdles of translating a messy stream of consciousness into perfectly formatted, zero-edit artifacts that can be instantly understood by both AI coding agents and human coworkers. Finally, Sahaj shares his framework for experimenting with new tools and why surviving this era of software development requires completely reinventing yourself and your organization every three months.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:Try Wispr FlowNow on Android Connect with Sahaj 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.

Is the traditional engineering backlog officially a thing of the past? Andrew and Ben explore the principles of outcome engineering and how continuous productivity is permanently changing how software gets built. They also examine a busy week of industry news, from Peter Steinberger joining OpenAI to the amusing and bewildering story of a hit piece written by an autonomous AI agent. Finally, the hosts break down the existential crises of Gemini 3 Pro inside a virtual village and why Meta product managers are rebranding themselves as AI builders.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:OpenAI's acquisition of OpenClaw signals the beginning of the end of the ChatGPT eraAn AI Agent Published a Hit Piece on MeOutcome EngineeringThe Drama and Dysfunction of Gemini 2.5 and 3 ProSeveral Meta employees have started calling themselves 'AI builders'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 the Ralph autonomous loop was born, Dex Horthy was "in the garden," witnessing the spark that set the AI engineering community on fire. Andrew sits down with the HumanLayer founder to discuss how to escape the "Dumb Zone" by applying his strict RPI (Research, Plan, Implement) methodology - a process that forces agents to generate intermediate design artifacts and align on architectural decisions before writing a single line of code. They also break down the brutal economics of agentic coding, recounting how Dex’s team used autonomous loops to clone six sponsor products overnight at a hackathon.Follow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanArticles & Talks:No Vibes Allowed: Solving Hard Problems in Complex Codebases: Dex’s viral talk from the AI Engineer World’s Fair that introduced the "Dumb Zone" concept.The AI Vampire: Steve Yegge’s reflection on burnout and agentic economics.12-Factor Agents: Human Layer’s methodology for building reliable agentic systems.Follow today's guest:Website: humanlayer.devTwitter: @dexhorthyLinkedIn: Dexter HorthyOFFERSStart 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.