The Stack Overflow Podcast

Episode notes: 

This episode with Paypal’s CTO Srini Venkatesan was recorded at the Ai4 conference. 

Listen to our other Ai4 conversation with Greg Jennings, VP of Engineering for AI Products at Anaconda, about building secure-by-default AI coding agents here. 

Connect with Srini on LinkedIn.

See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

Ryan chats with Greg Jennings, VP of Engineering for AI Products at Anaconda, about what it takes to build a secure-by-default AI coding agent, why prompts shouldn't be treated as strict security guardrails, and how Anaconda is using strategic acquisitions to secure the AI software supply chain.

Episode notes:

Anaconda is a foundational platform for Python data science and machine learning, providing secure software supply chain governance and enterprise AI infrastructure.

Connect with Greg 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.

Ryan sits down with Tim Lindholm, an early contributor to the Java language at Sun Microsystems, to chat about what it was like building one of the most popular programming languages ever at its inception, why it was strategically important for the Java team to create a cross-platform ABI to compete with Windows NT, and how applets were initially just an interesting demo. 

Episode notes: 

Watch the new documentary by Cult.Repo on YouTube to learn more about the early history of Java and the people who built it.

Connect with Tim Lindholm on LinkedIn.

Shoutout to user gabuzo for winning a Populist badge for answering What is the standard method for generating a nonce in Python?.

See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

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.

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.

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.

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.

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.

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.