Dev Interrupted

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 30
Follow the show:
Subscribe to our Substack 
Follow us on LinkedIn
Subscribe to our YouTube Channel
Leave us a Review
Follow the hosts:
Follow Andrew
Follow Ben
Follow Dan
Follow today's guest:
CircleCI: Explore the leading continuous integration and delivery platform at circleci.com
The Confident Commit: Subscribe to Rob's newsletter and podcast for data-backed software delivery insights on CircleCI's website
The Confident Commit Podcast: Listen to Rob’s podcast
State of Software Delivery: Read CircleCI's annual report analyzing millions of CI workflows to benchmark your team's performance
Gather.dev: Apply to join the curated, invite-only community for senior engineering leaders at gather.dev
Follow Rob: LinkedIn
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.

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 London
Follow the show:
Subscribe to our Substack 
Follow us on LinkedIn
Subscribe to our YouTube Channel
Leave us a Review
Follow the hosts:
Follow Andrew
Follow Ben
Follow Dan
Follow today's stories:
Are AI labs pelicanmaxxing?
OpenAI and Hugging Face partner to address security incident during model evaluation
China'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 limits
Who’s Afraid of Chinese Models?
SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review
The Army Is Burning Through Its AI Tokens
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.

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 30
Follow the show:
Subscribe to our Substack 
Follow us on LinkedIn
Subscribe to our YouTube Channel
Leave us a Review
Follow the hosts:
Follow Andrew
Follow Ben
Follow Dan
Follow today's guest:
Rippling: Explore the workforce management platform at rippling.com 
Introducing Rippling Data Cloud: AI-powered BI that understands your workforce
Follow Albert: LinkedIn 
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.

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 30
Follow the show:
Subscribe to our Substack 
Follow us on LinkedIn
Subscribe to our YouTube Channel
Leave us a Review
Follow the hosts:
Follow Andrew
Follow Ben
Follow Dan
Follow today's stories:
I'm pretty sure isRecord is our fault
Introducing the MCPA: the First Official Certification for the Model Context Protocol
If you give a Goose an MCP server
What the hell is a loop, anyway?
Rebuilding the CircleCI CLI from scratch
AI Writes Faster Than Humans Can Review: A Longitudinal Study of an Enterprise 2x Mandate
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.

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 LinkedIn
Subscribe to our YouTube Channel
Leave us a Review
Follow the hosts:
Follow Andrew
Follow Ben
Follow Dan
Follow today's guest:
LaunchDarkly AgentControl: Learn how to govern your probabilistic AI with runtime agent frameworks at launchdarkly.com/platform/agent-control
The Goal by Eliyahu M. Goldratt: Read the quintessential business novel on the theory of constraints at Amazon
The Phoenix Project by Gene Kim: Explore the seminal book on IT, DevOps, and business success at IT Revolution
SimAnt: Dive into the history of the 1991 classic electronic ant colony simulation at Wikipedia.
Follow Cameron: LinkedIn
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.