The Stack Overflow Podcast
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.
Episodes
Mentioned books
10 snips
Sep 8, 2026 • 29min
Scaling your money safely with AI
Srini Venkatesan, PayPal’s CTO specializing in fintech, AI, and large-scale commerce, explores how to scale financial AI safely. He discusses deterministic validation, human oversight, multi-agent software development, and codifying expert knowledge for trustworthy automation. The conversation also covers controlling AI costs, modernizing merchant integrations, testing agentic payments, and the future of personalized, headless commerce.
61 snips
Sep 4, 2026 • 32min
How to build a secure-by-default AI coding agent
Greg Jennings, Anaconda’s VP of Engineering for AI Products, explores how to build coding agents that are secure by default. They discuss treating AI-generated code as untrusted, sandboxing agents, auditing actions, and why deterministic barriers beat prompt-based guardrails. Jennings also covers AI security’s defender advantage and Anaconda’s acquisition-led platform strategy.
22 snips
Sep 1, 2026 • 30min
The good ol’ days of building Java
Tim Lindholm, an early Java engineer at Sun Microsystems, revisits the language’s formative years. He shares how he repaired its shaky runtime, why a cross-platform ABI was central to challenging Windows NT, and how applets began as a simple demo. He also discusses Java’s write-once ambition, HotSpot’s performance leap, and later building Google’s distributed resource-management systems.
10 snips
Aug 28, 2026 • 25min
When you keep AI Lean, you keep AI correct
Leo de Moura, Senior Principal Applied Scientist at AWS and creator of the Lean language and proof assistant. He talks about writing programs and mathematical proofs in one system. He explores combining probabilistic AI with deterministic proofs. He discusses using proofs to verify agent policies, detect trickery, and safely optimize code.
12 snips
Aug 25, 2026 • 33min
Inside LinkedIn's cognitive memory agent for agentic personalization
Praveen Bodigutla, Principal AI researcher at LinkedIn who led development of their cognitive memory agent, explains a four-layer tree-structured memory for a hiring assistant. He discusses conversation, episodic, procedural, and semantic layers. Topics include ingestion and compaction of interaction streams, storage and access-control at scale, reducing LLM calls with incremental updates, and balancing freshness, latency, and relevance.
26 snips
Aug 21, 2026 • 26min
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, brings decades of dev tooling and AI experience. He frames agentic development as the next democratizing wave. He argues individuals will become team leads of agents. The conversation covers reshaping code review, new interview approaches for agent reasoning, risk-based human vs agent review, and data activation challenges.
28 snips
Aug 21, 2026 • 33min
Get rid of your CAPTCHA, the future of the web is bots
Brian Alvey, CTO at WordPress VIP and veteran web technologist, talks about how AI agents are reshaping web architecture. He explores building sites for bots instead of humans, CMS tradeoffs for headless and enterprise needs, and how structured content and metadata make machines prefer your site. He also covers scaling WordPress for extreme use cases and making bots look smart to win.
47 snips
Aug 18, 2026 • 29min
Building an agentic SDLC with a QA engineering mindset
Suneet Malhotra, Senior Manager of Test Engineering at Motorola Solutions who builds open-source agentic SDLC pipelines. He describes a five-agent pipeline from design to PR review. He discusses using multiple LLMs as judges and measuring their agreement with Cohen’s kappa. He covers model selection strategies and a spec-enrichment step to shift QA left.
19 snips
Aug 14, 2026 • 28min
Solving integration woes with a hackathon
Meryll Blanchet, Director of Engineering for Adobe Brand Visibility and veteran product leader, talks about using a three-day internal hackathon to rapidly integrate Semrush capabilities into Adobe. She covers prep and focused scope, cultural and identity alignment, building a prompt strategy agent, technical API patterns, and turning hackathon wins into everyday engineering habits.
34 snips
Aug 11, 2026 • 30min
Your tokenmaxxing is not valuemaxxing
Rob Whiteley, CEO of Coder and former computer engineer, builds developer platforms and applies AI to software development. He argues tokenmaxxing is just an effort metric and warns of Goodhart’s Law. He explores new AI-native measurements, using PR merges and business impact to judge agentic workflows. He also covers prompting, manageable PRs, and democratizing developer skills.
