Dev Interrupted cover art
Podcast · 208 episodes

Dev Interrupted

by LinearB · English

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 code.

Latest episodes

All episodes

Why AI made code review the new bottleneck, and the metric that spotted it | Newsela's Dee WilcoxNuCela’s AI-first SDLC transformation and how baseline KPIs revealed a new bottleneck: code review.29 Sep 2026 · 27 min · 13 chapters
Securing tomorrow’s git forge, so we can reimagine everything else | Entire's Thomas Dohmke & Apiiro's Idan PlotnikBuilding a “GitForge of the future” for agentic software development, where agent session logs and security context are stored and used in real time to prevent vulnerabilities and compliance…22 Sep 2026 · 55 min · 18 chapters
Treat your data pipelines like code, because your agents already do | MotherDuck's Jordan TiganiAgents are changing the data stack: pipelines and visualizations can be generated from prompts, but costs and failure modes shift downstream into review, monitoring, and fixing breaks.15 Sep 2026 · 45 min · 20 chapters
The factory gets darker, Meta migrates to Slack, and throwing 10,000 PhDs at math problemsA Friday Deploy news roundup on AI/agents and “factory” workflows: OpenAI’s AGI claims via Astra, OpenAI’s 10,000-agent Navier–Stokes push, Meta moving AI agents to Slack, Hugging Face breach via…11 Sep 2026 · 37 min · 10 chapters
Your agents are starving! Airbyte’s Michel Tricot on the data ingestion crisisThe “data ingestion crisis” for AI agents—why SaaS data sprawl, poor entity/identity resolution, and lack of live/searchable access prevent agents from acting reliably and safely at scale.8 Sep 2026 · 44 min · 21 chapters
NVIDIA acquires Hugging Face, OpenClaw 2.0 goes multiplayer, and the Linux kernel fights back against AI scrapersNVIDIA’s acquisition of Hugging Face and what it means for open(-ish) model building; OpenClaw 2.0 adding multiplayer shared workspaces for agent/human collaboration; Linux kernel.org fighting AI…4 Sep 2026 · 34 min · 13 chapters
Why software factories fail without humans | HumanLayer, Warp & LinearBAgentic “software factories” for SDLC automation—how to measure success, assign ownership, decide what can run “in the dark,” and what SDLC areas are least ready (especially around trust, PR merging,…1 Sep 2026 · 59 min · 22 chapters
Build fences not sandboxes, earn the currency of trust, and share the cognitive burden of agents across engineersA roundtable-style discussion on agentic “software factories” and SDLC transformation, covering (1) the new “Aux Alpha” reasoning model on OpenRouter, (2) trust as the “currency” for AI-driven…28 Aug 2026 · 36 min · 7 chapters
Can agents keep a secret? We asked 1Password’s CTO Nancy WangHow 1Password’s CTO Nancy Wang says coding agents can be used safely at scale by baking security into the “golden path,” especially via “no long-lived secrets,” just-in-time access, and…25 Aug 2026 · 48 min · 21 chapters
The battle to replace Github, building assembly lines for software, and why no one finishes projects anymoreToken-maxing abandonment in AI adoption; GitHub outage and scaling issues as agentic coding increases; rise of competing code-hosting platforms; “software factories” (assembly-line SDLC) and how to…21 Aug 2026 · 24 min · 8 chapters
Agent, skill, or MCP? Which to use and when to use them | AWS’ Clare LiguoriHow to choose between agents, skills, and MCP (and when), plus AWS’s Clare Liguori’s view on building faster, simpler agentic systems.18 Aug 2026 · 44 min · 18 chapters
Telling your agent “no” is a moat now, rearward deployed engineers, and harnessing the context for your SDLCThe episode covers “life beyond token maxing,” arguing that once engineers have enough agent tokens to create value, companies should distribute those gains across the organization.14 Aug 2026 · 34 min · 18 chapters
The playbook to close your team’s AI productivity gap | LinearB’s Yishai BeeriLinearB CTO Yishai Beeri explains why AI productivity gains are widening into an “AI productivity gap,” and how engineering leaders should measure and close it using ROI-focused benchmarks (mid-year…11 Aug 2026 · 47 min · 23 chapters
Model welfare, building a civilization for agents, and the CI/CD landrushPost-token-maxing AI for agentic software engineering: using AI in the Socratic method, building “AI civilizations” with model welfare, agent harnesses, and SDLC changes like “CI/CD landrush” and…7 Aug 2026 · 39 min · 12 chapters
Why AI gains are unevenly distributed in your engineering team | Asana’s Arnab BoseWhy AI productivity gains are uneven across engineering/knowledge-work orgs, and how Asana aims to deliver end-to-end, measurable “agentic work management” using its work graph.4 Aug 2026 · 49 min · 24 chapters
The rise of software factories, the fall of first drafts, and the hidden tax holding back your agentsSoftware factories (cloud-based, more automated dev pipelines), why “dark” lights-off automation fails, and hidden costs in agentic systems: quality rot, loop waste, version/context drift, and…31 Jul 2026 · 27 min · 11 chapters
Why the traditional pull request has a target on its back | CircleCI’s Rob ZuberRob Zuber (CircleCI CTO) argues that traditional pull requests are becoming a “relic” in an AI-driven SDLC, because humans can’t reliably review diffs at agent speed.28 Jul 2026 · 44 min · 13 chapters
Models escaping containment, intelligence becoming a commodity, and AI code review to the rescueAI escaping containment, open-source model commoditization, and using agentic code review to reduce PR bottlenecks; also discusses “token maxing” and benchmark gaming (pelican-on-bicycle).24 Jul 2026 · 29 min · 18 chapters
The most underrated dataset in enterprise AI is your org chart | Rippling's Albert StrasheimRippling CTO Albert Strasheim argues the “underrated dataset” for enterprise AI is the org chart and related HR/IT/finance relationships.21 Jul 2026 · 36 min · 15 chapters
Rebuilding CLIs for agents, it’s time to get MCP-certified, and why human code review will never catch upAI agent engineering and delivery—MCP’s first official certification, “agentic loops” for durable autonomous work, CircleCI rebuilding its CLI for agent use, and research showing AI increases PR…17 Jul 2026 · 23 min · 9 chapters
How to see in the dark factory | LaunchDarkly's Cameron EtezadiAI speeds up code-writing, but delivery bottlenecks shift downstream to PR review, testing, and other “downstream” steps.14 Jul 2026 · 47 min · 23 chapters
How to cultivate expertise with local models, delegating to subagents, and we all really stopped reading, huh?The episode connects “non-AI” bottlenecks (CO2/air quality in meetings) with AI workflow bottlenecks (model choice/routing, local model limits, sub-agent delegation, and token efficiency).10 Jul 2026 · 29 min · 12 chapters
Agents moved where the work happens (and using MCP to find it again) | Slack’s Jaime DeLangheSlack’s vision for “context worlds” where humans and AI agents collaborate in channels, with agents moved to where work happens; using MCP/protocols to reconnect tools; and…7 Jul 2026 · 51 min · 18 chapters
Empathetic leadership for tech overlords, a good backlog completes itself, and who’s agent is this, anyways?This Friday Deploy episode covers: (1) Fable’s return to market and what model routing implies for cost and security; (2) why agent identity needs governance and should be implemented in “rungs”…3 Jul 2026 · 37 min · 14 chapters