The Stack Overflow Podcast

Tom Moor, Head of Engineering at Linear, dives into the dynamic world of AI agents in software development. He shares insights on how context enhances agent performance and discusses the balance between AI's hype and practical adoption. Tom highlights how junior developers can leverage AI to improve their skills while collaborating effectively with these tools. He also touches on the importance of creating workflows that allow for iterative feedback and quality improvement, showcasing Linear's innovative integration of agents within team environments.

Spiros Xanthos, CEO of Resolve AI, dives into the transformative role of AI agents in incident management. He discusses how traditional runbooks are becoming outdated and how AI agents can autonomously troubleshoot complex systems, potentially saving up to 70% of engineers' time. Spiros elaborates on agents acting as on-call responders, gathering evidence across various tools, and assisting with the increasing complexity of software systems. He also touches on the evolving role of developers in an AI-driven landscape and offers insights into the future of engineering.

Natalie Rotnov, Senior Product Marketing Manager at Stack Overflow, dives into the insights from the 2025 Developer Survey. She highlights a decline in developer trust towards AI due to frustrations over nearly accurate outputs and time spent debugging. The importance of community validation is emphasized, as 80% of developers still rely on platforms like Stack Overflow. Natalie advises leaders to foster collaborative knowledge-sharing spaces and leverage Retrieval-Augmented Generation to streamline developer workflows amid pervasive tool sprawl.

In a fascinating chat, John Dickerson, CEO of Mozilla.ai and expert in multi-agent systems, dives into the role of open source in the AI landscape. He explains how open standards can enhance interoperability among AI agents and the balance of trust and determinism in using them. John highlights the significance of user choice in an era of data privacy concerns and explores the implications of bot traffic on web creators. Additionally, he discusses the potential of low-resource AI and emphasizes the need for robust evaluation standards for agent systems.

Andrei Kvapil, the founder of Ænix and a core developer of CozyStack, shares his expertise in Kubernetes and virtualization. He discusses building a private cloud from scratch and highlights the advantages of Kubernetes' declarative API for simplifying cloud operations. Andrei explores the importance of open-source solutions in achieving digital sovereignty and delves into networking challenges in Kubernetes environments. He also touches on innovative storage options and the need for robust user management in cloud systems.

Dhruv Batra, co-founder and chief scientist at Yutori, dives into the fascinating world of AI agents and their potential to transform our digital tasks. He discusses proactive agents that automate mundane web activities, such as tracking reservations and price drops. Dhruv contrasts historical AI developments and critiques current definitions of AGI. He also shares insights on training agents using simulated environments, the challenges of integrating AI into workflows, and the future of personalized generative interfaces.

Evan You, the mastermind behind Vite and Vue.js, joins to explore the evolution of build tools in web development. He shares insights on Vite's innovative plugin system and the speed of its hot module replacement. Evan discusses the documentary about Vite, highlighting the power of open-source communities. The conversation also dives into the future of Vite, including its Rust integration and the vision for a unified toolchain. With humor and expertise, Evan illustrates how Vite is reshaping the frontend landscape.

Dimitri Stiliadis, CTO and co-founder of Endor Labs, dives into the evolving landscape of application security in the age of AI-generated code. He stresses the critical need for human oversight to manage vulnerabilities, highlighting the balance between security and efficiency. The conversation explores how AppSec scanning has adapted to handle the surge in AI code while also addressing the significance of context in vulnerability management. Dimitri advocates for integrating security at the platform level, ultimately ensuring safer AI adoption in software development.

Gil Feig, Co-founder and CTO of Merge, delves into the future of APIs by discussing how to streamline multiple third-party integrations into a single call. He emphasizes the importance of data normalization and shares insights on the role of AI in this process. Feig also explores the challenges of chaining agent calls and the necessity for human oversight in managing AI-generated code, all while highlighting the shift towards more efficient event mechanisms like webhooks. Expect a fascinating look at balancing innovation with practical engineering skills.

Ryan J. Salva, Senior Director of Product at Google, teams up with Peter O'Connor to dissect the evolving landscape of engineering teams amidst AI integration. They emphasize that quality documentation is crucial; poor documentation can lead AI astray. The duo advocates for standardized tools and hands-on practice to boost developer confidence in using AI. They also discuss fostering a culture that prioritizes learning over mere productivity. Leaders are encouraged to give teams the space to innovate and explore AI opportunities.