Agentic search doesn't find pages, it assembles answers

Ryan sits down with Jeff Wang, co-founder at EXA, to talk about the huge scale required to support trillions of agentic searches, the technical complexities of building custom embeddings and performant vector databases from scratch, and the need to dedupe the massive amounts of redundant content on the web to deliver high-trust answers.Episode notes:EXA is a full search engine built specifically for AI agents, featuring custom extraction models and vector databases designed to handle complex, trillion-scale queries without the AI slop.Connect with Jeff (through his triage agents) by emailing him at [email protected] to Populist badge winner Santhoopa Jayawardhana for earning the badge on their answer to Keycloak client vs user.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 Ahmad Al-Dahle, CTO at Airbnb, about deploying multi-party AI agents to tackle the uniquely gnarly problem of customer support, how a moving target of rigorous evaluations helps engineers balance latency against accuracy, and the ways in which AI coding tools demand an even higher level of judgment from software engineering teams.Episode notes:Learn more about how Airbnb is evolving its engineering organization to implement generative AI across the platform on their tech blog.Connect with Ahmad on Twitter and LinkedIn.Congrats to Famous Question badge winner techGuy for winning the badge on their answer to is WebView2 supported in the Citrix server?.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 Rakesh Kumar, professor of computer engineering at the University of Illinois Urbana-Champaign, about the astounding complexity of manufacturing modern semiconductors, the massive environmental and geopolitical footprint of AI data centers, and how AI models are rapidly shifting the future of chip design.Episode notes: Dive deeper into the history and future of semiconductors by checking out Rakesh's book, The Chip Age. Learn more about Rakesh’s work at University of Illinois Urbana-Champaign.Congrats to Necromancer badge winner Faisal Khan for winning the badge on their answer to Difference between SWIFT Interact & Fileact transmissions.See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

Recorded at LDX3 by LeadDev, Ryan chats with Dan Moore, Senior Director of CIAM Strategy and Identity Standards at FusionAuth, about adapting established OAuth2 protocols for the agentic era, the security necessity of giving autonomous AI agents their own distinct identities, and how AI coding tools are shifting developers' focus toward solving core business problems.Episode notes:FusionAuth is an identity and access management platform that provides customer authentication, OAuth, and security solutions for developers.This episode was recorded at LDX3. Listen to our other LDX3 conversation with engineering leaders Nivia Henry and Charity Majors. Read Dan’s most recent piece on the Stack Overflow blog about authentication and authorization in MCP.Connect with Dan at [email protected] 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 Charity Majors, co-founder and CTO at Honeycomb, for a conversation about applying the concept of immutable infrastructure to software development to treat code like cattle instead of pets, shifting the paradigm of system specifications to accommodate the rapid influx of AI-generated code, and navigating the complex ethical boundaries between system observability and human surveillance in modern technology ecosystems.Episode notes:Honeycomb is an observability platform that empowers engineering teams to visualize, analyze, and understand the behavior of their complex cloud systems. Connect with Charity on her blog at charity.wtf and read her team's posts on AI norms and values on the Honeycomb blog.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 James Gosling, creator of Java at Sun Microsystems, to talk about the early networking friction that drove the need for interconnectedness, the stringent reliability requirements of consumer electronics companies that inspired the Java virtual machine, and the evolution of garbage collectors that allow Java to handle large-scale concurrent memory management.Episode notes:Check out CultRepo’s recently released Java documentary to learn more about the early history of the language and the engineers who built it.Connect with James on LinkedIn and X.Congrats to Famous Question badge winner zainhassan for winning the badge on their answer to java.security.certpathvalidatorexception, trust anchor for certification path, not founded React Native.See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

Recorded on the floor of LDX3, Ryan chats with Nivia Henry, an engineering leader most recently at Netflix, about the reality of the supposed SaaS apocalypse, the complex calculus of the modern build-versus-buy decision in the era of AI, and the critical importance of understanding system architectures to manage long-term infrastructure costs.Episode notes:This episode was recorded at this year’s LDX3 by LeadDev, a conference focused on modern engineering leadership, management, and technical strategyNivia recently spent two and a half years tackling complex data and engineering challenges at Netflix and previously spent eight years driving product innovation at Spotify. Connect with Nivia on LinkedIn and on BlueSky.See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

Recorded at OpenAI Dev Day 2026, Ryan sits down with Andrew Ambrosino, member of the technical staff at OpenAI, for a conversation on OpenAI's strategy for merging ChatGPT and Codex into a unified experience, the advantages of localized computer access in their successful desktop application, and the technical hurdles of constructing ChatGPT Spaces to support real-time multi-agent collaboration.Episode notes:ChatGPT Space is a newly launched collaborative workspace within ChatGPT and Codex that allows software engineering teams and their active AI agents to work together in real-time.Connect with Andrew on X.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 Gabriela Moreira, CEO at Quint, about why formal specification languages like TLA+ are essential for catching system design flaws before writing code, how Quint brings developer-friendly syntax and executability to formal methods, and the ways trace validation and model-based testing can verify AI-generated code against real-world production data.Episode notes:Quint is an open-source, executable specification language and toolchain based on TLA+ that enables engineers to model, simulate, and verify system behaviors using an intuitive, programmer-friendly syntax.Connect with Gabriela on LinkedIn and X.Congrats to Populist badge winner Alex K. for winning the badge on their answer to SQL Server: Select Top 0?.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 Josh Triplett, member of the Rust Leadership Team at the Rust Project, to chat about how the borrow checker delivers compile-time memory safety without garbage collection overhead, why Rust consistently ranks as developers' most loved language by providing psychological safety for complex systems, and how strict compiler constraints make Rust an ideal target for AI coding agents.Episode notes:Rust is an open-source systems programming language focused on performance, type safety, and compile-time memory safety without the runtime overhead of garbage collection.Connect with Josh on his website, on LinkedIn, or chat with him on the Rust Zulip.Congrats to Great Answer badge winner Germa Vinsmoke for winning the badge on their answer to Can I access variables from another file?.See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.