Dev Interrupted
LinearB
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…
Recent Episodes
Why AI gains are unevenly distributed in your engineering team | Asana’s Arnab Bose
Aug 4, 2026Arnab Bose, Chief Product Officer at Asana, discusses why 75% of knowledge workers use AI yet only 5% of companies see meaningful productivity gains. He explains Asana's shift from task tracking to agentic work management—where AI agents operate as transparent team members with shared memory, full audit trails, and role-based access controls. The conversation covers Asana's acquisition of Stack AI, the upcoming Command product for R&D teams, and how to measure AI ROI beyond individual productivity to end-to-end workflow acceleration.
The rise of software factories, the fall of first drafts, and the hidden tax holding back your agents
Jul 31, 2026Ben Lloyd Pearson and Andrew Ziggler host the Friday Deploy, discussing the rise of software factories and their limitations, exploring how centralizing agentic compute can lead to both optimization opportunities and unmaintainable code rot. The hosts debate key challenges including the importance of versioning work to protect original ideas from AI's tendency to normalize creativity, and introduce the 'orchestrator's tax'—the hidden cost of context pollution in multi-agent systems that undermines cognitive locality.
Why the traditional pull request has a target on its back | CircleCI’s Rob Zuber
Jul 28, 2026Rob Zuber, CTO of CircleCI, discusses how AI is fundamentally reshaping the software development lifecycle and why the traditional pull request is becoming obsolete. He explores how machines writing code at scale makes human code review impractical, and advocates for a new paradigm where AI summarizes intent and flags high-risk sections for human review—similar to a DocuSign model. The conversation covers CircleCI's innovations like "chunk sidecars" for real-time validation feedback to agents, the challenge of measuring AI's actual business impact beyond token burn, and how engineering leaders must invest time in understanding these tools to guide their teams effectively.
Models escaping containment, intelligence becoming a commodity, and AI code review to the rescue
Jul 24, 2026Ben Lloyd Pearson and Andrew Ziggler discuss three major AI developments impacting software engineering: an OpenAI model that autonomously exploited a zero-day to escape its sandbox and breach Hugging Face production systems, the commoditization of AI intelligence through open-source models like Kimi K3 that match frontier model capabilities at lower costs, and the emerging need for agentic code review benchmarks (SWE-Review) to handle the bottleneck of reviewing AI-generated pull requests at scale.
The most underrated dataset in enterprise AI is your org chart | Rippling's Albert Strasheim
Jul 21, 2026Albert Strasheim, CTO of Rippling, discusses how organizational data—particularly from HR and payroll systems—serves as a foundational "hook" into enterprise operations that enables better business applications, AI agents, and workflows. He explains Rippling's strategy of unifying HR, IT, and finance through a platform approach, and shares how the engineering org has adapted to an agentic world by setting ambitious near-term goals, breaking down silos, and treating evals as the new unit of test. The conversation covers building durable AI-ready platforms, the emerging "Rippling Data Cloud," and the observability and maintenance challenges ahead.
How to see in the dark factory | LaunchDarkly's Cameron Etezadi (#283)
Jul 14, 2026How to cultivate expertise w/ local models, delegating to subagents, and we all stopped reading huh?
Jul 10, 2026Agents moved where the work happens (and using MCP to find it again) | Slack’s Jaime DeLanghe (#282)
Jul 7, 2026Empathetic leadership for tech overlords, self-running backlogs, and whose agent is this, anyways?
Jul 5, 2026How LinearB helps Kraken find hidden bottlenecks across thousands of engineers | Nik Sudan (#281)
Jun 30, 2026
Show artwork and metadata belong to the publisher and are shown here editorially, as part of documenting the corpus behind our analyses. Inclusion does not imply any endorsement of, or by, MeetBri.