LLM -powered systems continue to move steadily into production, but this process is presenting teams with challenges that traditional software practices don’t commonly encounter. Models and agents are non-deterministic systems, which makes it difficult to test changes, reason about failures, and confidently ship updates. This has created the need for new evaluation tooling designed specifically around the properties of LLMs.

Comet is a platform with Roots and MLOps, to the rapidly evolving world of agent-based systems by treating prompts, tools, and workflows as optimizable components that can be evaluated and improved over time.

Gideon Mendels is the co -founder and CEO of Comet. He previously worked at Google on hate speech and deception detection, and he founded GroupWise, which trained and deployed NLP models processing billions of chats. In this episode, Gideon joins Kevin Ball to discuss how agent development sits between software engineering and ML, why eVals are the missing foundation for most AI teams, prompt optimization as a search problem, and the future for continuously improving agents in production.

Full Disclosure: This episode is sponsored by Comet.

Kevin Ball or KBall, is the vice president of engineering at Mento and an independent coach for engineers and engineering leaders. He co-founded and served as CTO for two companies, founded the San Diego JavaScript meetup, and organizes the AI inaction discussion group through Latent Space.

Please click here to see the transcript of this episode.

Sponsorship inquiries: [email protected]

The post Optimizing Agent Behavior in Production with Gideon Mendels appeared first on Software Engineering Daily.

AI-assisted programming has moved far beyond autocomplete. Large language models are now capable of editing entire codebases, coordinating long-running tasks, and collaborating across multiple systems. As these capabilities mature, the core challenge in software development is shifting away from writing code and toward orchestrating work, managing context, and maintaining shared understanding across fleets of agents.

Steve Yegge is a software engineer, writer, and industry veteran whose essays have shaped how many developers think about their work. Over the past year, Steve has been exploring the frontier of agentic software development, building tools like Beads and Gas Town to experiment with multi-agent coordination, shared memory, and AI-driven software workflows.

In this episode, Steve joins Kevin Ball to discuss the evolution of AI coding from chat-based assistance to full agent orchestration, the technical and cognitive challenges of managing fleets of agents, how concepts like task graphs and Git-backed ledgers change the nature of work, and what these shifts mean for software teams, tooling, and the future of the industry.

Kevin Ball or KBall, is the vice president of engineering at Mento and an independent coach for engineers and engineering leaders. He co-founded and served as CTO for two companies, founded the San Diego JavaScript meetup, and organizes the AI inaction discussion group through Latent Space.

Please click here to see the transcript of this episode.

Sponsorship inquiries: [email protected]

The post Gas Town, Beads, and the Rise of Agentic Development with Steve Yegge appeared first on Software Engineering Daily.

Python 3.14 is here and continues Python’s evolution toward greater performance, scalability, and usability. The new release formally supports free-threaded, no-GIL mode, introduces template string literals, and implements deferred evaluation of type annotations. It also includes new debugging and profiling tools, along with many other features.

Łukasz Langa is the CPython Developer in Residence at the Python Software Foundation, and he joins Sean Falconer to discuss the 3.14 release, the future of free threading, type system improvements, Python’s growing role in AI, and how the language continues to evolve while maintaining its commitment to backward compatibility.

Sean’s been an academic, startup founder, and Googler. He has published works covering a wide range of topics from AI to quantum computing. Currently, Sean is an AI Entrepreneur in Residence at Confluent where he works on AI strategy and thought leadership. You can connect with Sean on LinkedIn.

Please click here to see the transcript of this episode.

Sponsorship inquiries: [email protected]

The post Python 3.14 with Łukasz Langa appeared first on Software Engineering Daily.

Engineering teams often build microservices as their systems grow, but over time this can lead to a fragmented ecosystem with scattered data access patterns, duplicated business logic, and an uneven developer experience. A unified data graph with a consistent execution layer helps address these challenges by centralizing schema, simplifying how teams compose functionality, and reducing operational overhead while preserving performance and reliability.

Viaduct is Airbnb’s open-source, data-oriented service mesh and GraphQL platform built around a single, highly connected central schema. It has played a major role in scaling Airbnb’s engineering organization.

Adam Miskiewicz is a Principal Software Engineer at Airbnb and he worked on Viaduct. He joins the podcast with Gregor Vand to talk about how Viaduct originated inside Airbnb, the architectural principles that shaped it, the challenges of scaling GraphQL to millions of queries per second, and why the team decided to open-source the platform. They also discuss the future of backend development in an AI-driven world and how unified data layers may influence the next generation of engineering systems.

Gregor Vand is a security-focused technologist, having previously been a CTO across cybersecurity, cyber insurance and general software engineering companies. He is based in Singapore and can be found via his profile at vand.hk or on LinkedIn.

Please click here to see the transcript of this episode.

Sponsorship inquiries: [email protected]

The post Airbnb’s Open-Source GraphQL Framework with Adam Miskiewicz appeared first on Software Engineering Daily.

SED News is a monthly podcast from Software Engineering Daily where hosts Gregor Vand and Sean Falconer unpack the biggest stories shaping software engineering, Silicon Valley, and the broader tech industry.

In this episode, they cover Starlink’s rapid rollout of free, high-speed in-flight internet, Tesla’s move to deprecate Autopilot in favor of full self-driving, and Apple’s reported decision to power Siri with Google’s Gemini models. They also discuss Meta’s $2B acquisition of Manus, Waymo’s growing pains as autonomous vehicles scale, and the competitive shockwaves triggered by Google’s advances in custom AI hardware.

Gregor and Sean then dive deep into the state of the tech job market, examining OpenAI’s decision to eliminate vesting cliffs, the escalating war for elite AI talent, and what recent layoffs really say about the future of software engineering. They explore how AI coding tools are reshaping the balance between junior and senior engineers, why fundamentals still matter, and what developers should focus on heading into 2026.

Finally, they highlight standout threads from Hacker News, including Doom running on wireless earbuds, the enduring appeal of wildly over-engineered side projects, and why hacking for fun still matters in an age of industrial-scale AI.

Gregor Vand is a security-focused technologist, having previously been a CTO across cybersecurity, cyber insurance and general software engineering companies. He is based in Singapore and can be found via his profile at vand.hk or on LinkedIn.

Sean’s been an academic, startup founder, and Googler. He has published works covering a wide range of topics from AI to quantum computing. Currently, Sean is an AI Entrepreneur in Residence at Confluent where he works on AI strategy and thought leadership. You can connect with Sean on LinkedIn.

Please click here to see the transcript of this episode.

Sponsorship inquiries: [email protected]

The post SED News: Apple Bets on Gemini, Google’s AI Advantage, and the Talent Arms Race appeared first on Software Engineering Daily.

AI coding agents are rapidly reshaping how software is built, reviewed, and maintained. As large language model capabilities continue to increase, the bottleneck in software development is shifting away from code generation toward planning, review, deployment, and coordination. This shift is driving a new class of agentic systems that operate inside constrained environments, reason over long time horizons, and integrate across tools like IDEs, version control systems, and issue trackers.

OpenAI is at the forefront of AI research and product development. In 2025, the company released Codex, which is an agentic coding system designed to work safely inside sandboxed environments while collaborating across the modern software development stack.

Thibault Sottiaux is the Codex engineering lead and Ed Bayes is the Codex product designer. In this episode, they join Kevin Ball to discuss how Codex is built, the co-evolution of models and harnesses, multi-agent futures, Codex’s open-source CLI, model specialization, latency and performance considerations, and much more.

Kevin Ball or KBall, is the vice president of engineering at Mento and an independent coach for engineers and engineering leaders. He co-founded and served as CTO for two companies, founded the San Diego JavaScript meetup, and organizes the AI inaction discussion group through Latent Space.

Please click here to see the transcript of this episode.

Sponsorship inquiries: [email protected]

The post OpenAI and Codex with Thibault Sottiaux and Ed Bayes appeared first on Software Engineering Daily.

Engineering teams around the world are building AI-focused applications or integrating AI features into existing products. The AI development ecosystem is maturing, which is accelerating how quickly these applications can be prototyped. However, taking AI applications to production remains a notoriously complex process. Modern AI stacks demand LLMs, embeddings, vector search, observability, new caching layers, and constant adaptation as the landscape shifts week to week. Increasingly, the data layer has become both the foundation and the bottleneck to AI app productionization.

MongoDB has been expanding beyond its core document database into a full AI-ready database platform with integrated capabilities for operational data, search, real-time analytics, and AI-powered data retrieval. The company also recently acquired Voyage AI to provide accurate and cost-effective embedding models and rerankers to its users.

Fred Roma is a veteran engineer and is currently the SVP of Product and Engineering at MongoDB. He joins the show with Kevin Ball to talk about the state of AI application development, the role of vector search and reranking, schema evolution in the LLM era, the Voyage AI acquisition, how data platforms must evolve to keep up with AI’s breakneck pace, and more.

Full Disclosure: This episode is sponsored by MongoDB.

Kevin Ball or KBall, is the vice president of engineering at Mento and an independent coach for engineers and engineering leaders. He co-founded and served as CTO for two companies, founded the San Diego JavaScript meetup, and organizes the AI inaction discussion group through Latent Space.

Please click here to see the transcript of this episode.

Sponsorship inquiries: [email protected]

The post Production-Grade AI Systems with Fred Roma appeared first on Software Engineering Daily.

Package management sits at the foundation of modern software development, quietly powering nearly every software project in the world. Tools like npm and Yarn have long been the core of the JavaScript ecosystem, enabling developers to install, update, and share code with ease. But as projects grow larger and the ecosystem more complex, this older infrastructure is beginning to show its limits with performance bottlenecks, dependency conflicts, and growing concerns around supply chain security.

Darcy Clarke and Ruy Adorno are veterans of this ecosystem. Both spent years maintaining the npm CLI and helping guide the Node.js project, where they saw firsthand the technical debt and design tradeoffs that define modern JavaScript tooling. Now they’re building vlt, a new package manager and registry that rethinks performance, security, and developer experience from the ground up.

In this episode, Darcy and Ruy join Josh Goldberg to discuss how vlt works, why they believe package management needs a server-side reboot, what lessons they’ve drawn from npm’s evolution, and how features like declarative querying, self-hosted registries, and real-time security scanning could reshape how developers build and share JavaScript in the years ahead.

Josh Goldberg is an independent full time open source developer in the TypeScript ecosystem. He works on projects that help developers write better TypeScript more easily, most notably on typescript-eslint: the tooling that enables ESLint and Prettier to run on TypeScript code. Josh regularly contributes to open source projects in the ecosystem such as ESLint and TypeScript. Josh is a Microsoft MVP for developer technologies and the author of the acclaimed Learning TypeScript (O’Reilly), a cherished resource for any developer seeking to learn TypeScript without any prior experience outside of JavaScript. Josh regularly presents talks and workshops at bootcamps, conferences, and meetups to share knowledge on TypeScript, static analysis, open source, and general frontend and web development.

Please click here to see the transcript of this episode.

Sponsorship inquiries: [email protected]

The post Next-Gen JavaScript Package Management with Ruy Adorno and Darcy Clarke appeared first on Software Engineering Daily.

WebAssembly, or WASM, has grown from a low-level compilation target for C and C++ into one of the most influential technologies in modern computing. It now powers browser applications, edge compute platforms, embedded systems, and a growing ecosystem of languages targeting a portable and secure execution model.

Andreas Rossberg is a programming languages researcher and former member of the V8 team at Google. Andreas helped architect WebAssembly from its earliest concepts through its most recent milestone releases, including the groundbreaking 3.0 spec that introduces garbage collection, richer reference types, and major steps toward multi-language interoperability.

In this episode, Andreas joins Kevin Ball to explore the history of WebAssembly, the constraints that shaped its earliest design, the major turning points in versions 1.0, 2.0, and 3.0, and what’s coming next for WebAssembly.

Kevin Ball or KBall, is the vice president of engineering at Mento and an independent coach for engineers and engineering leaders. He co-founded and served as CTO for two companies, founded the San Diego JavaScript meetup, and organizes the AI inaction discussion group through Latent Space.

Please click here to see the transcript of this episode.

Sponsorship inquiries: [email protected]

The post WebAssembly 3.0 with Andreas Rossberg appeared first on Software Engineering Daily.

Surveillance technology is advancing faster than the laws meant to govern it. Across the United States, police departments are deploying automated license plate readers, facial recognition tools, and predictive systems that quietly log the daily movements of millions of people. These tools promise efficiency and safety, but critics argue that they represent a form of warrantless mass surveillance, and raise deep constitutional questions about privacy, accountability, and the limits of government power in the digital age.

Michael Soyfer is an attorney at the Institute for Justice, a nonprofit public interest law firm focused on defending individual rights. His work centers on the Fourth Amendment and the growing use of surveillance technologies by local governments. Michael joins the show with Kevin Ball to discuss the rise of Flock Safety cameras, the Institute for Justice’s lawsuit against the City of Norfolk, how decades-old legal precedents struggle to keep up with modern technology, and what citizens, technologists, and policymakers can do to protect privacy in an era of pervasive data collection.

Kevin Ball or KBall, is the vice president of engineering at Mento and an independent coach for engineers and engineering leaders. He co-founded and served as CTO for two companies, founded the San Diego JavaScript meetup, and organizes the AI inaction discussion group through Latent Space.

Please click here to see the transcript of this episode.

Sponsorship inquiries: [email protected]

The post America Under Surveillance with Michael Soyfer appeared first on Software Engineering Daily.

Modern software development is evolving rapidly. New tools, processes, and AI-powered systems are reshaping how teams collaborate and how engineers find satisfaction in their craft. At the same time, developer experience has become a critical function for helping organizations balance agility, security, and scale while maintaining the creativity and flow that make top tier engineering possible.

Capital One is continuously transforming its developer culture, with a focus on faster development cycles, reducing operational overhead, and boosting productivity across the organization.

Catherine McGarvey is the SVP of Developer Experience at Capital One. She joins the podcast with Sean Falconer to talk about what developer enablement means at enterprise scale, measuring developer productivity, being agile in a regulated environment, AI in enterprise development, the future for developers, and much more.

Full Disclosure: This episode is sponsored by Capital One.

Sean’s been an academic, startup founder, and Googler. He has published works covering a wide range of topics from AI to quantum computing. Currently, Sean is an AI Entrepreneur in Residence at Confluent where he works on AI strategy and thought leadership. You can connect with Sean on LinkedIn.

Please click here to see the transcript of this episode.

Sponsorship inquiries: [email protected]

The post Developer Experience at Capital One with Catherine McGarvey appeared first on Software Engineering Daily.