TechnologySociety & CultureBusiness

The Stack Overflow Podcast

For well over a decade, the Stack Overflow Podcast has been exploring what it means to be a developer and how the art and practice of software engineering is changing our world. From creating code to running it in production, we host important conversations and fascinating guests that will help you understand how technology is made and where it’s headed. Hosted by Ryan Donovan, the Stack Overflow Podcast is your home for all things software.

Play

Open in

27 episodes
a few times a week
Avg 29 min
English

Episodes 27

Newest Oldest Longest

All20 Unplayed20 In progress0 Played0

Counted on this page — what you have heard stays on this device, so it is not something the list can be paged by.

#983
Friday · 25 min
When you keep AI Lean, you keep AI correct
Ryan chats with Leo de Moura, Senior Principal Applied Scientist at AWS and the creator of the Lean language, about proving correctness in AI agents with the Lean language, how automated reasoning complements probabilistic AI models, and the use of AI for continuous code optimization. Episode notes: Lean is a functional programming language and proof assistant that allows developers to write programs and verify their mathematical correctness within the exact same system. Connect with Leo on LinkedIn and check out his many badges on Stack Overflow. Congrats to Populist badge winner Peter Lawrey for winning the badge on their answer to Check two float/double values for exact equality. See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.
#982
Tuesday · 32 min
Inside LinkedIn's cognitive memory agent for agentic personalization
Ryan is joined by Praveen Bodigutla, Principal AI Researcher at LinkedIn, to chat about the four-layer memory system his team built to give LinkedIn's hiring assistant a persistent, personalized state. Praveen explains why his team moved off GraphRAG in favor of a tree-structured memory for faster incremental updates and how they balance retrieval freshness, latency budgets, and access control at LinkedIn's scale. Connect with Praveen on LinkedIn. Congrats to Populist badge winner Luka Ganić, who answered SVG image as button in Flutter so well it outscored the accepted answer! See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.
#980
August 21 · 25 min
From PHP to team lead of agents: rethinking judgment, review, and data with Google's Andi Gutmans (Part 1)
Andi Gutmans, head of Agentic Data Cloud at Google and co-creator of PHP, joins Leaders of Code to talk about why agentic development feels less like a break from the past and more like the next chapter of the same story. This is part one of a two-part conversation. In this episode, Eira May and Stack Overflow Director of Platform Engineering Peter O'Connor talk with Andi Gutmans about the throughline between democratizing web development with PHP and democratizing software development with agents today. Andi makes the case that every individual contributor is becoming “a team lead of agents” and walks through how that reshapes code review, interviewing, and the balance of human versus agent judgment. He also explains why he thinks the biggest bottleneck left isn't the models, but the challenge of getting an organization's data into a state where agents can actually reason over it. The discussion also: Covers how Google is changing its own interview process to evaluate how candidates reason with and guide agents, rather than how well they can hand-code a solution alone. Explores the "human in the loop, agent in the loop, agent on the loop" framework for deciding where review actually needs to happen — and why that's fundamentally a risk-management question, not a trust-in-AI question. Uses the Waymo safety-data-versus-perception gap as an analogy for why organizations (and individuals) sometimes resist agent autonomy even when the numbers favor it. Introduces Google's "borderless lakehouse" concept and the shift from human data stewardship to agent-driven ontology building. Notes: Connect with Andi Gutmans on LinkedIn. Connect with Peter O'Connor on LinkedIn. See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.
#981
August 21 · 32 min
Get rid of your CAPTCHA, the future of the web is bots
See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.
#979
August 18 · 28 min
Building an agentic SDLC with a QA engineering mindset
Ryan welcomes Suneet Malhotra, Senior Manager of Test Engineering at Motorola Solutions, to chat about building end-to-end agentic SDLC pipelines using MCPs, using Cohen’s kappa to evaluate multiple LLMs-as-judges, and how you can improve requirements by shifting QA left through a specification enrichment stage immediately after the design phase. Episode notes: You can learn more about Suneet’s five-agent SDLC (and see the companion code) on his GitHub. Read the papers discussed: Cross-Layer Observability for LLM-Assisted Test Automation: A Reference Architecture and Web Feasibility Study and Cross-Layer Observability for LLM-Assisted Test Automation — Reference Implementation and Evaluation Data (v1.5.2, JSS In-Practice). Connect with Suneet on LinkedIn and see more of his work on his website. Congrats to user Sanjay for winning a Great Question badge for asking What does it mean to fork on GitHub?. See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.
#978
August 14 · 28 min
Solving integration woes with a hackathon
Ryan welcomes Meryll Blanchet, Director of Engineering for Adobe Brand Visibility, to chat about Adobe’s recent acquisition of Semrush, how Adobe Brand Visibility was born from Semrush’s AI visibility product and Adobe’s LLM Optimizer, and how Adobe used a three-day internal hackathon instead of a large-scale infrastructure integration to quickly deliver value to customers. Episode notes: Adobe Brand Visibility is a GEO software that helps companies improve their AI visibility, citations, and share of voice. You can preview the new product here. Connect with Meryll on LinkedIn. Congratulations to user patti_jane, who won a Stellar Question badge for asking Setting PATH environment variable in macOS permanently. See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.
#977
August 11 · 29 min
Your tokenmaxxing is not valuemaxxing
Ryan is joined by Coder’s Rob Whiteley to chat about why tokenmaxxing isn’t proving real value and just triggering Goodhart’s Law, how release speed and PR merges can help you measure agentic outcomes with or without a human-in-the-loop, and what the democratization of skills means for junior developers and the talent pipeline. Episode notes: Coder is a self-hosted platform that lets you securely run cloud development environments and AI coding agents on your own internal infrastructure. Connect with Rob on LinkedIn. Today’s shoutout goes to an Unsung Hero badge winner, user Red.Wave! See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.
#976
August 7 · 40 min
How to be fearlessly AI native
Ryan welcomes McLaren Stanley, Senior Principal Engineer for Amazon Stores, to discuss what it actually takes to make teams AI native, why agentic engineering is shifting code bottlenecks downstream to testing and deployment, and why robust validation is essential to build trust and enable “fearless commits.” Episode notes: You can learn more about how Amazon’s frontier teams became AI native on the AWS blog. Connect with McLaren on LinkedIn. Congrats to user o11c for winning a Populist badge for answering Pythonic way to count the number of trailing zeros in base 2. See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.
#975
August 4 · 31 min
Your MVP doesn’t need a Kubernetes cluster
Ryan welcomes Anurag Goel, CEO and co-founder of Render, to discuss why most startups shouldn’t start by managing their Kubernetes and cloud infrastructure. They discuss how frustration with spinning up nodes at Stripes led him to build a company, a future where your application itself may allocate its own compute, and why DevOps jobs aren’t going anywhere. Episode notes Render calls itself the cloud for builders, intuitive infrastructure for scale. Connect with Anurag at anurag@render.com. Congrats to Populist badge winner Hovercraft Full Of Eels for bringing the knowledge to How can I disable System.out for speed in Java. See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.
#974
July 31 · 30 min
What happens to the internet when robots act like humans?
Ryan welcomes WPEngine CTO Ramadass Prabakar to the show to chat about what happens—and what we should do—when agents start acting like humans online, how our internet is evolving to serve both human and agentic experiences from the same interface, and what we can do to differentiate and protect human actions online from malicious bot activity. Episode notes: WP Engine hosts and manages over 5 million WordPress sites, combining enterprise-grade software, developer tools, and cutting-edge AI to support your website. Connect with Ramadass on LinkedIn or Twitter. Congrats to user Nama on winning a Famous Question badge for asking how to store the spinner values into database? See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.
#973
July 28 · 26 min
You need reliable AI context for your site reliability
Ryan is joined by Asaf Savich, Komodor’s AI Engineering Group Manager, to discuss why modern reliability work requires navigating massive cross-service context, what good context engineering actually likes when AI is integrated into site reliability, and how the work of human SREs is shifting towards strategy and AI agent management. Episode notes: Komodor is an autonomous AI SRE platform designed to troubleshoot, manage, and optimize Kubernetes-based cloud-native infrastructure. Connect with Asaf on LinkedIn. Congrats to Populist badge winner joemaller, who won the badge for answering Is there a Python equivalent to the 'which' command. See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.
#972
July 24 · 26 min
Partnerships can keep open source sustainable
Ryan welcomes VoidZero’s Evan You and Cloudflare’s Dane Knecht back to the show to discuss Cloudflare’s recent acquisition of VoidZero and what it means for JavaScript development, how partnerships like theirs can help open-source projects stay maintained and sustainably monetized, and how Cloudflare’s distributed systems are helping to improve developer experience in Vite and beyond. Episode notes: VoidZero is now officially a part of Cloudflare. You can read more about the recent acquisition here. Connect with Evan on LinkedIn and X. Check out Evan’s previous episodes on the pod for a deep dive on the evolutions of Vite and Vue.js. Connect with Dane on LinkedIn and X. Listen to Dane’s previous episode of Leaders of Code to learn how Cloudflare is building a better internet. Congrats to user Luis Sieira, who won a Stellar Answer badge for answering How to get the difference between two arrays in JavaScript?. See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.
#971
July 21 · 25 min
The future of development is full-stack
Live from Snowflake Summit, Ryan talks with Snowflake’s Head of Developer Experience Umesh Unnikrishnan about the industry-wide shift from “vibe coding” for quick prototypes to agentic engineering for enterprise-ready software, how enterprises can scale governance with guardrails like human-in-the-loop approval and control layers that go beyond the underlying LLM, and why Umesh predicts all developers will become someday become full-stack builders. Episode notes: This episode was recorded at Snowflake Summit. You can learn more about CoCo and Snowflake’s other new releases on their website. Connect with Umesh on LinkedIn or reach out to him at Umesh.Unnikrishnan@snowflake.com Vivek Raghunathan, SVP of engineering at Snowflake, also sat down this us at this year’s Snowflake Summit to break down the five-stage framework his org used to go from "let chaos reign" to a repeatable, org-wide system for AI-assisted engineering. Listen to his episode of Leaders of Code. Our sixteenth Annual Developer Survey is now open and we want to hear your thoughts on all things software. Take the survey now! See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.
#970
July 17 · 28 min
Developers who move fast still need to do it together
At MS Build, Ryan is joined by Cassidy Williams, Senior Director of Developer Advocacy at GitHub and former Stack Overflow Podcast host, to discuss how agentic coding is shifting dev work towards higher-level strategy while increasing decision fatigue; why human taste, community feedback, and mentorship are becoming more essential than ever for developer careers; and the new GitHub Copilot announcements coming out of Microsoft, including the new GitHub Copilot app. Episode notes: This episode was recorded at Microsoft Build. You can learn more about what they announced at the show and what’s new at GitHub here. Listen to our other episodes recorded at Build on agentic workflows and responsible AI. Connect with Cassidy on LinkedIn and X. See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.
#969
July 14 · 28 min
Your AI is only as responsible as you are
Recorded at Microsoft Build, Ryan welcomes Sarah Bird, Microsoft’s Chief Product Officer for Responsible AI, about how we can build and use AI responsibly with the NIST approach, why most irresponsible AI comes from experimentation without thought of impact, and how Microsoft is researching thoughtful human/AI workflow design to reduce unnecessary escalation. Episode notes: This episode was recorded at Microsoft Build. Listen to our other episode recorded at Build on agentic workflows here. Connect with Sarah on LinkedIn. See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.
#968
July 10 · 31 min
Building more than just an agent harness
Live from Microsoft Build, Ryan is joined by Jay Parikh, Microsoft’s VP of AI Core, for a conversation on what enterprises need to build, deploy, and run AI agents at scale with demonstrable ROI; how Microsoft built an end-to-end agent development system that goes past just the harness; and how you can evaluate for reliability and correctness in models that get more intelligent and autonomous everyday. Episode notes: This episode was recorded at Microsoft Build. Learn more about the announcement and news from Build, including Microsoft’s new GitHub app and Foundry platform, at the Microsoft blog. Connect with Jay on LinkedIn. See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.
#964
July 8 · 30 min
What's left for infrastructure-as-code after AI moves in?
SPONSORED BY IBM Ryan is joined by Rosemary Wang, Developer Advocate at IBM, to explore what infrastructure as code looks like once AI starts writing and deploying it. They discuss why guardrails still lag adoption, breaks down what it means when “anyone can deploy,” and why deep systems knowledge still matters. Episode notes: Try out Bob, IBM’s coding agent that Rosemary talked about in the episode. Connect with Rosemary on X, LinkedIn, or Bluesky. See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.
#967
July 7 · 31 min
Agent orchestration is so two-years ago
Ryan welcomes Saahil Jain, CTO of You.com, to discuss why building agents with a 2024 mindset is a mistake as modern models improve at long-horizon tasks, why heavy orchestration layers can hurt model performance more than help it, and why the 2026 competitive edge actually comes from information retrieval and unique data paired with end-to-end evaluation. Episode notes: You.com is an AI-powered search and productivity engine helping enterprises find information, create content, and automate complex tasks using web search APIs, multi-model AI access, and agentic intelligence. Connect with Saahil on LinkedIn or reach out to him at saahil@you.com. Today’s shoutout goes to user knittl for winning a Populist badge on their answer to Remove all null values. See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.
#966
July 3 · 25 min
The good, the bad, and the AI apps
Ryan welcomes Benny Chen, co-founder of Fireworks AI, to the show to explore what actually makes an AI application good or not, how to balance qualitative signals with quantitative metrics when evaluating AI, and how open-source eval protocols and community efforts are setting the standard for AI evaluation. Episode notes: Fireworks AI is a cloud platform designed for developers and enterprises to run, customize, and scale open-source generative AI models. Connect with Benny on LinkedIn. Congrats to user techtabu for winning a Stellar Answer badge for answering How can I delete all local Docker images?. See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.
#965
July 2 · 22 min
How do you turn AI coding chaos into a repeatable playbook?
Vivek Raghunathan, SVP of engineering at Snowflake, joins Leaders of Code at Snowflake Summit to break down the five-stage framework his org used to go from "let chaos reign" to a repeatable, org-wide system for AI-assisted engineering. Vivek explains how Snowflake systematically rolled out coding agents across its engineering org — starting with unrestricted experimentation, then codifying what worked into a shared vocabulary of 14 "AI design patterns," from plan-in-English to fencing off parallel agents to reducing on-call toil through continuously updated skills. Vivek walks through the "inner loop" and "outer loop" of software development, explains Snowflake's internal Yegge scale for measuring how far engineers have progressed along that continuum, and shares how a three-person team used coding agents to deliver a 40x improvement on Snowflake's query compiler. The discussion also: Breaks down Snowflake's "focus weeks," where engineers get dedicated time to either catch up on best practices or push the frontier further. Explores the pioneers/settlers/skeptics framework for meeting engineers where they are in adopting AI tools, and why the shift can trigger something like the stages of grief. Covers how Snowflake cut release validation time from 15 days to a single day, and why more automated testing hasn't come at the cost of production stability. Looks ahead to a four-step maturity model for on-call and incident response, where agents may eventually take primary on-call duty. Connect with Vivek Raghunathan on LinkedIn. See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

Showing 1–20 of 27 episodes