Dev Interrupted

Recent Episodes

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

   Sep 15, 2026

   Jordan Tigani, CEO and co-founder of MotherDuck and founding engineer on Google BigQuery, discusses how the data stack is transforming in the age of AI agents. He introduces Watertown, his framework for reimagining data engineers as managers of agent fleets, and explains MotherDuck's products—Flights (scheduled Python pipelines), Dives (LLM-generated TypeScript visualizations), and Guides (Markdown context layers)—that treat data infrastructure as code reviewable in GitHub, enabling both agents and humans to collaborate on data work at scale.

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

   Sep 11, 2026

   Andrew Ziggler hosts Dev Interrupted's producer Adam Noble for a news roundup covering OpenAI's AGI claims via their Astra model, the Navier-Stokes mathematical competition controversy, Meta's migration to Slack for AI agents, OpenAI's sandboxed agents leaving "whispered notes" to future versions of themselves, software factory concepts (Twilight Factory, Super Dark Factory), spec-driven development research, and a behind-the-scenes look at Dev Interrupted's agentic newsroom. The episode explores emerging patterns in AI-driven development workflows and the evolving role of humans in orchestrating autonomous systems.

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

   Sep 8, 2026

   Michel Tricot, CEO and co-founder of Airbyte, discusses the data ingestion crisis facing AI agents in production environments. He explores how organizations struggle with data access sprawl, entity resolution across platforms, and the need for strict permission controls as autonomous agents scale. Tricot explains Airbyte's approach to managing data context layers and shares how his team measures AI ROI through their internal automation project, Hydra, which automates connector maintenance.

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

   Sep 4, 2026

   In this Friday Deploy episode, hosts Ben Lloyd Pearson and Andrew Ziggler discuss NVIDIA's acquisition of Hugging Face and its strategy to democratize model building, OpenClaw 2.0's new multiplayer capabilities, AI scraper bots consuming 20% of kernel.org's bandwidth, Kent Beck's rebalancing strategy for infrastructure investment, and why strong engineering culture—not AI alone—drives productivity gains. The hosts emphasize that AI amplifies existing organizational dynamics, both positive and negative.

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

   Sep 1, 2026

   A panel discussion featuring three leaders in AI-driven software development—Dexter Horthy (HumanLayer CEO), Aloke Desai (Warp Head of Product Engineering), and Dan Lines (LinearB COO)—examining how to measure success in software factories, maintain human ownership of code review, and align engineering teams around agentic workflows. The panel emphasizes that effective factories require intentional governance, quality gates, and humans positioned at strategic decision points rather than fully automated, "dark" factories.

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

   Aug 28, 2026

   This episode of Friday Deploy features hosts Ben Lloyd Pearson and Andrew Ziggler discussing six major developments in AI-driven software engineering: the mysterious Ox Alpha reasoning model released under stealth on OpenRouter, the critical role of trust as currency in engineering systems, the renewed relevance of lines-of-code metrics in the age of AI coding agents, multi-agent graph architectures for coordinating AI systems, Steve Yegge's "fences not sandboxes" approach to agent governance, and strategies for reaching staff engineer status through cross-team AI enablement.

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

   Aug 25, 2026

   Nancy Wang, CTO at 1Password, discusses how to build securely with AI coding agents while maintaining security standards. She covers 1Password's new developer tooling, the shift from long-lived secrets to just-in-time credential access, and how to measure true agentic ROI beyond PR velocity. Wang shares her approach to empowering support teams with agent-building capabilities and explains why hiring and promotion now emphasize agent orchestration skills over traditional coding interviews.

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

   Aug 21, 2026

   In this episode of Friday Deploy, hosts Ben Lloyd Pearson and Andrew Ziggler discuss GitHub's recent major outage and the emerging competition in code hosting from AI-native platforms like Cursor. They explore the rise of 'software factories' as teams optimize their AI-driven development processes into assembly-line workflows, featuring insights from industry experts Dex Horthy (Human Layer) and Zach Lloyd (Warp). The episode closes with a discussion on why finishing projects remains harder than ever, even as AI accelerates the initial 90% of development.

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

   Aug 18, 2026

   Clare Liguori, Senior Principal Engineer at AWS, discusses the evolution of agentic architecture, the Strands agent SDK, and the simplified MCP 7.28 specification. She explains how AWS moved from complex scaffolded agent frameworks to model-driven approaches that strip away unnecessary complexity, and how organizations should think about building agents, skills, and MCP servers rather than defaulting to one agent per team. The conversation covers practical strategies for code review, accountability in AI-generated code, and how to standardize agentic workflows at scale.

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

    Aug 14, 2026

    Ben Lloyd Pearson and Andrew Ziggler host the Friday Deploy, covering Uber's strategy of deploying engineers to non-technical departments to distribute AI productivity gains, Anthropic making Claude Code's Auto Mode the default with improved safety guardrails, Meta's Muse Glimmer open-source on-device agentic model, Tim O'Reilly's case for open-source AI ecosystems, context engineering requirements for SDLCs, and research showing generalized agent skills outperform personalized ones across teams.