Dev Interrupted

LinearB

266 episodes listed below

Listen to the show on

Apple Podcasts Spotify

AI-era engineering, measured against real workflow.

The gist

Dev Interrupted follows the fast-moving edge of software development, especially agentic coding, AI tools, and engineering productivity. Its best moments turn noisy tech stories into concrete consequences for teams, code review, infrastructure, and developer trust.

PRESS PLAY

Find your next episode

All episodes

About Dev Interrupted

Dev Interrupted is a technically fluent software-development show focused on the AI turn in engineering. It watches the space where developer tools, model capabilities, organizational pressure, and day-to-day workflow collide. The pace is fast. Episodes often begin with a current story, then widen into the operational question beneath it: what this means for pull requests, security, review quality, platform reliability, or the developer experience. The show gives special attention to agentic coding and orchestration. Google cracking down on back-button hijacking becomes a way to talk about spammy web behavior and agents navigating an internet that was not built for them. Obsidian, Claude desktop, Git repos, and personal artifacts become a discussion about memory, retrieval, and the risk of trusting an assistant that only appears to understand a person's whole context. Model news gets similar treatment. Talk of Claude Mythos leads into benchmark literacy, cybersecurity concerns, and the shrinking time between frontier-model leaps. The show also tracks the commercial and social texture of AI tooling. Ads or tips appearing near pull requests are treated as a trust problem, not just a product hiccup. Token pricing, off-hours compute, outages, and overloaded platforms become signs of a new infrastructure rhythm around AI-assisted work. Interviews give the analysis a builder's frame. Matt Boyle's appearance centers on agent-ready workspaces, enterprise environments, and the idea of safe, disposable places for AI to operate. Zach Lloyd's return brings terminal workflows, Warp, Oz, GitHub strain, and orchestration into the same conversation. Benchmark episodes connect AI adoption to engineering productivity and delivery outcomes, especially through LinearBee's report and pull-request-level measurement. The show can be playful, but its questions stay practical. It is interested in where AI helps, where it shifts the bottleneck, and where teams may fool themselves with usage metrics instead of real delivery signals. That makes Dev Interrupted especially useful for developers, engineering leaders, and tool builders who already understand the vocabulary but want sharper judgment about what the new stack is doing to the craft.

Made for: For software developers, engineering leaders, DevEx teams, and tool builders tracking AI-assisted coding, orchestration, benchmarks, and productivity. It assumes comfort with modern software culture while still explaining emerging ideas clearly.

What sets it apart: Dev Interrupted stands out by translating fast AI-tooling news into engineering consequences: pull requests, review trust, workspace design, security, and team metrics. It blends news-roundup urgency with interviews from people building the tools under discussion.

In their own words

Software itself is fundamentally changing. We explore the transition to agentic orchestration, vibe coding, and AI-native development, grounding the conversation in the principles that have always defined great engineering.On Tuesdays, we interview the founders, architects, and builders of the world’s most impactful tech to uncover the timeless engineering principles and strategies shaping the next era of development.And on Fridays, we drop an end-of-week roundup of the biggest news in AI and software, and what it actually means for your career, your craft, and your life as a developer.Subscribe to stay ahead of the next era of co...

As heard by us

Based on 6 episodes we listened to · September 2026

Dev Interrupted connects AI-era software changes to the practical decisions, team dynamics, and career pressures shaping engineering work.

Dev Interrupted treats software work as a management problem as much as a coding one. Ben Lloyd Pearson and Andrew Ziegler move from lively technology news into guest conversations, using AI tools and changing development practices to examine team structure and engineering…

Read our full review in PlayNext →

Why you'd press play

A calculator's hidden complexity shares the bill with pull-request politics, if that's your kind of happy hour.

Press play if you want

engineering advice that connects PR size and documentation to the culture you are trying to build
AI workplace predictions tested against what small teams and working developers actually trust

Read the full recommendation in PlayNext →

agentic coding workflowsAI model benchmarksengineering productivity metricsdeveloper environmentspull request qualityGitHub and platform reliabilityAI tooling trustcybersecurity implications

Talks about

Technology Artificial Intelligence

Podcasts like Dev Interrupted

The Reasoning ShowMassive Studios
Clear thinking for production AI.
Ctrl+Alt+AzureTobias Zimmergren, Jussi Roine
Azure talk with operational weight.
The New Stack PodcastThe New Stack
Cloud-native infrastructure, questioned in practical detail.
AI & IDan Shipper
AI work, explained from the inside.
Power Platform Boost PodcastUlrikke Akerbæk and Nick Doelman
Power Platform news with practical static.
Digital AccessibilityJoe Welinske
Accessibility as daily practice, not afterthought.

Find your next episode

About Dev Interrupted

In their own words

As heard by us

Why you'd press play

Talks about

Podcasts like Dev Interrupted

Episodes

A neutral home for MCP, A2A, goose, and more | AAIF co-founder Manik Surtani

Why AI made code review the new bottleneck, and the metric that spotted it | Newsela's Dee Wilcox

Securing tomorrow’s git forge, so we can reimagine everything else | Entire's Thomas Dohmke & Apiiro's Idan Plotnik

Treat your data pipelines like code, because your agents already do | MotherDuck's Jordan Tigani

The factory gets darker, Meta migrates to Slack, and throwing 10,000 PhDs at math problems

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

NVIDIA acquires Hugging Face, OpenClaw 2.0 goes multiplayer, and the Linux kernel fights back against AI scrapers

Why software factories fail without humans | HumanLayer, Warp & LinearB

Build fences not sandboxes, earn the currency of trust, and share the cognitive burden of agents across engineers

Can agents keep a secret? We asked 1Password’s CTO Nancy Wang

The battle to replace Github, building assembly lines for software, and why no one finishes projects anymore

Agent, skill, or MCP? Which to use and when to use them | AWS’ Clare Liguori

Telling your agent “no” is a moat now, rearward deployed engineers, and harnessing the context for your SDLC

The playbook to close your team’s AI productivity gap | LinearB’s Yishai Beeri

Model welfare, building a civilization for agents, and the CI/CD landrush

Why AI gains are unevenly distributed in your engineering team | Asana’s Arnab Bose

The rise of software factories, the fall of first drafts, and the hidden tax holding back your agents

Why the traditional pull request has a target on its back | CircleCI’s Rob Zuber

Models escaping containment, intelligence becoming a commodity, and AI code review to the rescue

The most underrated dataset in enterprise AI is your org chart | Rippling's Albert Strasheim

Rebuilding CLIs for agents, it’s time to get MCP-certified, and why human code review will never catch up

How to see in the dark factory | LaunchDarkly's Cameron Etezadi

How to cultivate expertise with local models, delegating to subagents, and we all really stopped reading, huh?

Agents moved where the work happens (and using MCP to find it again) | Slack’s Jaime DeLanghe

Empathetic leadership for tech overlords, a good backlog completes itself, and who’s agent is this, anyways?

How LinearB helps Kraken find hidden bottlenecks across thousands of engineers | Nik Sudan

The discernment horizon, loop-driven development, and a wizard’s very defensible pond

Your developers are the attack surface now and vibe coding as a vulnerability | Tanya Janca

Microsoft’s wandering eyes, data labeling duties for senior devs at Meta, and prod is the new source code

Your SDLC needs a productivity context engine

How to harness your dragon with Fable, tech leaders turn to model routing, and coping with AI rockstars

All software is an optimization of tokens and time (and speed is still the moat) | AMD’s Anush Elangovan

Microsoft breaks free from OpenAI, using your harness to add drag instead of velocity, and the Linux built-ins you're sleeping on

How to turn your 1000x engineer into a 10x everyone | LinkedIn’s Karthik Ramgopal

The cost of intelligence will never be this cheap again, the failure of intensive specs, and how bots disguise inefficient workflows

Observability is your profit center now | Honeycomb’s Christine Yen

What Google didn’t announce at I/O, defining “dark flow” and ignoring your first brain to build your second one

Android is the frontier for agents and other lessons from Google I/O | Matthew McCullough

Agents get their own AOL, Andrew gets published, and vibe coding is actually good?

It’s Tuesday and your tech stack is obsolete (again). Now what? | Theory Venture’s Bryan Bischof

Goblins in prod, the messy middle of AI adoption, and everything is a harness now

Teach the primitives or watch your competitor define them | Baseten’s Philip Kiely

Tokenmaxxing scoreboards, the vegan LLM from before 1931, and 30% of the web is now AI-generated

Giving robots a brain | Intrinsic’s Brian Gerkey

The harness is the showdown, the humans are the tool calls, and have you seen my Claude Code buddy?

The best model for your team? You haven’t invented it yet. | Ai2’s Tim Dettmers

The guardian in the machine | Wayfound’s Tatyana Mamut

Reading model benchmarks like a pro, Mythos is looming, and Claude talk caveman, save big token

Stop measuring AI adoption. Start measuring AI impact. | LinearB’s APEX framework

Virtual pets in your terminal, ads in your pull request, & no more CSS in your browser?

Retrofit or reimagine? Developer environments for humans and agents | Ona’s Matt Boyle

The T-shaped leader, Disney can’t catch a break, and will you trust Auto mode?

Why AI-assisted PRs merge at half the rate of human code | LinearB’s 2026 Benchmarks

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

Many tokens make all bugs shallow & open source’s new maintainers | Chainguard's Dan Lorenc

Inference is the new 401k matching and what we’re learning from AI-related outages

Your engineers need an AI control plane, not more tools | Guild.ai’s James Everingham

The agent wasteland, federated workflows, and a computer for computers

How monday.com paused its roadmap for 30 days to hit AI escape velocity | Sergei Liakhovetsky

Draining the COBOL moat, cybersecurity inequalities, and Claude’s retirement home

Your keyboard is the real bottleneck | Wispr’s Sahaj Garg

Outcome engineering, AI hit pieces, and the end of the backlog

Dex Horthy on Ralph, RPI, and escaping the "Dumb Zone"

Breaking GitHub, AI vampires & the great Oz | Warp’s Zach Lloyd

Multi-agent orchestration in Slack | Saleforce's Kurtis Kemple

Moltbook, Rent-a-Human, Super Agents & Connectivity Benchmark Report | ft. Gary Lerhaupt

Nobody is shipping your agent’s code (yet) | Predictions from LinearB’s Ori Keren

OpenClaw, a constitution for AI, breaking dark flow, and open source as a moat?

Scaffolding is coping not scaling, and other lessons from Codex | OpenAI’s Thibault Sottiaux

Angie Jones on Ralphing 25k repos at Block, GPT-5.2 Codex, and CES weirdness

Backstage’s journey from spreadsheets to global IDP standard | Spotify’s Tyson Singer

Ralph Wiggum goes to Gas Town and the death of the IC