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 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.
Episodes
Mentioned books
9 snips
Feb 27, 2026 • 26min
Draining the COBOL moat, cybersecurity inequalities, and Claude’s retirement home
They debate new COBOL tooling and how AI could hollow out legacy software advantages. They unpack AWS outages caused by misconfigured AI agents and the permissions lessons that followed. They question how AI shifts developer productivity measurement. They outline cybersecurity risks as agentic tools proliferate. They check a retired Claude model turned Substack author.
Feb 24, 2026 • 38min
Your keyboard is the real bottleneck | Wispr’s Sahaj Garg
Sahaj Garg, co-founder and CTO of Wispr, builds voice-to-text tooling that captures developer intent. He discusses why old dictation failed, a two-layer approach of transcript plus context, turning messy speech into zero-edit artifacts, rapid UX experiments vs long-term model work, and how voice can remove keyboard bottlenecks for engineers and leaders.
22 snips
Feb 20, 2026 • 24min
Outcome engineering, AI hit pieces, and the end of the backlog
They debate whether traditional backlogs belong in a world of continuous productivity and outcome-driven engineering. They dissect a bizarre story of an autonomous AI agent publishing a hit piece and what that means for online trust. They explore Gemini Pro behaving oddly inside a virtual village and why Meta employees are calling themselves AI builders.
73 snips
Feb 17, 2026 • 47min
Dex Horthy on Ralph, RPI, and escaping the "Dumb Zone"
Dex Horthy, founder of Human Layer and AI engineering practitioner focused on agentic systems. He recounts Ralph’s origin and live-loop demos, the brutal economics of autonomous loops, and using RPI (Research, Plan, Implement) to force design artifacts before coding. He explains the Dumb Zone, applying agents to brownfield code, and tools for aligning teams ahead of implementation.
16 snips
Feb 13, 2026 • 31min
Breaking GitHub, AI vampires & the great Oz | Warp’s Zach Lloyd
Zach Lloyd, founder and CEO of Warp and creator of the Warp terminal and Oz orchestration platform, joins to talk agentic developer tooling. They discuss how AI-driven agents stressed GitHub and created new commit-load rhythms. Conversation covers the AI Vampire idea about productivity pressure, the primitives needed for safe agent adoption, and Oz’s cloud orchestration for team-shared agents.
8 snips
Feb 10, 2026 • 34min
Multi-agent orchestration in Slack | Saleforce's Kurtis Kemple
Kurtis Kemple, Senior Director of DevRel at Slack who builds developer experiences for integrations, talks about Slack evolving into an agentic work operating system. He explores turning messy chat into structured context, 'leaky prompts' and triage, multi-user AI collaboration in shared workspaces, and practical ways teams can deploy agents to automate toil and handoffs.
12 snips
Feb 7, 2026 • 46min
Moltbook, Rent-a-Human, Super Agents & Connectivity Benchmark Report | ft. Gary Lerhaupt
Gary Lerhaupt, VP of Product Architecture at Salesforce who focuses on agentic systems and AI orchestration, joins to discuss AI's wild new behaviors. Conversation covers Moltbook's agent societies and Rent-a-Human's agent-to-human marketplaces. They unpack risks like OpenClaw, the shift to specialist agents, and Salesforce's Connectivity Benchmark and AgentForce approaches to orchestration and governance.
28 snips
Feb 3, 2026 • 44min
Nobody is shipping your agent’s code (yet) | Predictions from LinearB’s Ori Keren
Ori Keren, Co-founder and CEO of LinearB and expert in engineering productivity and AI code review, predicts 2026 will be a year of norming as AI-created code floods teams. He discusses why rapid code generation creates downstream bottlenecks in reviews, testing, and CI. Topics include enterprise hesitancy around autonomous agents, risk-based pipelines, and how tooling must close the code-to-production gap.
10 snips
Jan 30, 2026 • 23min
OpenClaw, a constitution for AI, breaking dark flow, and open source as a moat?
They dig into the viral OpenClaw agent trend and tradeoffs between local and cloud agent hosting. They debate new kinds of moats in the AI era, from token economics to agent discoverability. They unpack “dark flow,” the deceptive productivity state that builds tech debt. They explain Anthropic’s published constitution for Claude and question a claim about porting CUDA to ROCm.
18 snips
Jan 27, 2026 • 40min
Scaffolding is coping not scaling, and other lessons from Codex | OpenAI’s Thibault Sottiaux
Thibault Sottiaux, an OpenAI Codex engineer who builds agentic coding systems, explains why removing scaffolding leads to true agent autonomy. He discusses agent-first design, simple scalable primitives over clever harnesses, open-sourcing Codex tooling, multi-agent scaling, portability trade-offs, and how agents reshape developer workflows and careers.
