Stack Overflow

🎙️ We chat with Brian Alvey, CTO at WordPress VIP, about how AI agents are changing the business models of the web, what parts of how we build our sites won’t survive our current digital evolution, and why your site will always need structured content. https://lnkd.in/gTNjrn7T

AI agents can turn a vague idea into a plausible system almost instantly. But is moving at machine speed just getting you broken code faster? In this Dispatch from O'Reilly, IBM Research's Markus Eisele shares why detailed specs aren't old-world overhead in the age of AI, but the only thing standing between devs and an endless loop of trial and error. https://lnkd.in/gjeX4aET

🎙️ We welcome 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. https://lnkd.in/g7yT6qNp

🎙️ On Leaders of Code, Andi Gutmans, head of Agentic Data Cloud at Google and co-creator of PHP, joins Stack Overflow's Director of Platform Engineering Peter O'Connor to talk about why agentic development feels less like a break from the past and more like the next chapter of the same story, how Google is changing its own interview process to evaluate how candidates reason with and guide agents, and why human-in-the-loop is a risk-management question, not a trust-in-AI question. https://lnkd.in/gS79i2mz

🎙️ We welcome Meryll Blanchet,  Director of Engineering for Adobe Brand Visibility, for chat on Adobe's recent acquisition of Semrush, why Semrush and Adobe's LLM Optimizer work so well together, and how the Adobe team used a three-day internal hackathon to quickly deliver value to customers. https://lnkd.in/e76-qJih

AI allows engineering teams to generate more code than they can reasonably review. This creates a real problem that goes beyond just code quality, our Chief Product and Technology Officer Jody Bailey shares with CTO Uncovered Media, especially when important technical judgement lives solely in the heads of your engineers. The good news? Your technical teams already have the solution, now you just need to document it. https://lnkd.in/eU5hk_vr

While almost every industry uses some AI in their work, fintech (55%) and media and advertising (50%) come out on top when it comes to daily agentic AI usage, with energy (17%) being the industry with the lowest percentage of daily agentic AI users, according to our latest tech survey. Explore more findings from our #StackOverflowKnows survey on AI agents at work: https://lnkd.in/e4RYdVjs

What even is AI context architecture? In this No Dumb Questions, Phoebe asks Stack’s Engineering Manager Doug Whitley and Product Manager Ash Zade everything she wants to know about AI context architecture. Why is it so important? What makes for good AI context architecture? Why buy one when you can build your own? https://lnkd.in/eQb8ZJEK

🎙️ We're 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. https://lnkd.in/edvsnifa

🎙️ We welcome 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.” https://lnkd.in/gesRqV6W