CEOInterviews.AI
Start App
Try: AI strategy tariffs earnings guidance layoffs interest rates growth

Dex Horthy

Founder & CEO, Humanlayer

Search every verified Dex Horthy interview, podcast appearance, and on-the-record quote — each transcript cross-checked by AI and human review to confirm speaker identity. Dex Horthy, founder and CEO of HumanLayer, recently appeared on the podcast "High Taste Testers" and spoke at AGNTCon NA, where he discussed the practical limits of AI-generated code. On the podcast, he described using overnight automated coding runs to generate prototypes, noting that production software requires human review because models can produce more code than developers can reliably consume. He also commented on OpenAI's product strategy, suggesting that the merger of ChatGPT and Codex reflects a long-term move toward a unified harness for reinforcement learning. In his talk "Fighting Code Slop: The State of Software Factories," Horthy argued that unattended models do not improve or maintain codebase quality over time, despite significant advances in problem-solving capabilities in 2026. He referenced a shift in industry sentiment, noting that even a prominent advocate of not reading AI-written code has revised his position. Horthy also promoted HumanLayer's multiplayer coding agent workspace, which streams diffs to the cloud for real-time code review and supports collaborative sessions.

Recent appearances

  • High Taste Testers: OpenAI Shipped Everything. What Actually Works?

    October 16, 2026 · 📺 Latent Space

    Six AI power users compare what actually works—and what falls apart once you start using it. Ben Davis, Ben Hylak, Dex Horthy, Allison Durham, Alex Volkov, and swyx discuss OpenAI DevDay, coding agents, personal assistants, model preferences, and the gap between impressive AI capabilities and useful products. From Pi-powered personal agents and decision models to subagents, context management, prompt injection, and assistants that can spend money: what deserves a place in your daily workflow? CHAPTERS 00:00 High Taste Testers 01:26 OpenAI DevDay: Dots, Spaces, and product execution 10:28 Gr…

    Watch on YouTube ↗

  • Fighting Code Slop: The State of Software Factories - Dexter Horthy

    October 07, 2026 · 📺 Agentic AI Foundation

    Dex will be speaking at AGNTCon NA on October 22 & 23 in San Jose. Join 3500 other people at the event: https://hubs.la/Q04gbXLb0 Dex Horthy, CEO and co-founder of HumanLayer, argues that engineering teams shipping AI-written code still have to read it. This talk is for engineering leaders and developers building agentic coding pipelines who want to know where the lights-off software factory actually breaks down. His thesis: unattended models will not improve or maintain your codebase quality over time. Models got dramatically better in 2026 at solving problems. They did not get much better…

    Watch on YouTube ↗

  • What Actually Gets You 2-3x With AI Coding (ft. Dex Horthy)

    August 13, 2026 · 📺 Jan-Niklas Wortmann

    You can't get 10x with AI coding. Not today. Dex Horthy (Human Layer) makes the case for 2-3x if you refuse to ship slop, and why a perfect spec still produces garbage if you give the model permission to skip quality. That permission is how you burn a codebase into ash. We get into context engineering, where AI coding actually fails, why PR review is the bottleneck, how to use specs without worshipping them, cheap models vs Opus, compaction and sub-agents, and what to tell a 20-year engineer who is not living on Twitter. Dex is the founder of Human Layer. https://humanlayer.dev 00:00:00 You…

    Watch on YouTube ↗

  • No More Slop: Building Trust in an AI-First Organization with Austen Allred and Dex Horthy

    July 31, 2026 · 📺 Gauntlet AI

    This session isn't about which AI tools to use. It's about the systems, processes, and organizational habits that separate thoughtful AI adoption from simply producing more output. Host Austen Allred sits down with special guest Dex Horthy to explore how teams can move faster with AI while protecting the quality, craftsmanship, and trust that customers expect. Gauntlet transforms engineers into AI-first operators because most AI pilots don't have a technology problem, they have a talent problem. Hire Proven Talent: https://www.gauntletai.com/hire?utm_s... Upskill Your Team: https://www.ga…

    Watch on YouTube ↗

  • Why Software Factories Fail

    July 23, 2026 · 📺 AI Engineer

    In July 2025 Dex Horthy turned the lights off: an agent software factory where nobody read the code. It fell apart. An issue appeared that no amount of prompting could fix, the site was down, users were furious, and he was digging through a codebase he had stopped reading three months earlier. His claim is that this is not a skill or scale issue, and no harness or extra tokens fixes it, because it is a model training problem. Coding models are reinforced on one thing, did the test pass without breaking another, and nothing in that reward penalizes bad architecture, whose cost shows up months l…

    Watch on YouTube ↗

  • The Great Loops Debate — Dex Horthy, Geoff Huntley, Ian Livingstone, Greg Pstrucha, @insecure-agents

    July 17, 2026 · 📺 AI Engineer

    Oxford Style Debate: There is, or is not, a delta between the hype behind loops and what actually works in practice. Team No Delta (pro the way we do loops today) The hype around loops is valid and loops work well today in practice. Loops today can be a silver bullet and result in outsize productivity gains, and marks an important step up the autonomy curve towards real software factories. Ian Livingstone Geoff Huntley Team Delta (anti the way we do loops today) There is a delta between the hype behind loops and what actually works in practice. The way we are doing loops today is wrong. L…

    Watch on YouTube ↗

  • Context engineering with Dex Horthy

    July 15, 2026 · 📺 The Pragmatic Engineer

    Knowing how LLM contexts work and how to work around context limitations – aka “context engineering” – is becoming more important for software engineers working with LLMs. Let’s look into what works and what doesn’t, today. In this episode of The Pragmatic Engineer podcast, I sit down with the CEO and cofounder of HumanLayer, Dex Horthy, who coined the term “context engineering”. We discuss the ideas behind this context engineering, harness engineering, loop engineering, software factories, why his approach to AI-assisted software development has evolved, and how HumanLayer is helping enginee…

    Watch on YouTube ↗

  • The Software Factory: Dex Horthy on Shipping Fast Without AI Slop

    July 07, 2026 · 📺 Mastra

    Dex Horthy has spent the past year studying what happens to a codebase when you let AI write all of it and stop reading the output. His answer has a name: slop. And it's not just about sloppy prompting. In this episode, the HumanLayer founder Dex Horthy joins Shane and Abhi to draw the software factory on a whiteboard — the whole pipeline that builds the thing that builds the thing — and show exactly where teams tear out the parts that were holding quality up. He moves from the naive factory to the fully agentic one to the "lights-off" version where humans stop reading code entirely, then exp…

    Watch on YouTube ↗

  • Making Agents Ship in Complex Brownfield Codebases | Dex Horothy, CEO of HumanLayer

    April 28, 2026 · 📺 The Modern Software Developer

    In this episode of The Build System, I sit down with Dex, CEO of HumanLayer, father of the term “context engineering”, and one of the most prominent thought leaders in the AI coding ecosystem. We break down how teams are actually building with AI today, beyond demos and hype. The conversation digs into why most agent workflows don’t hold up in production, and what changes when you’re working inside large, messy, brownfield systems. We cover: why most “agent” examples online fail in real environments the gap between teams seeing ~15–30% gains and those reaching 2–3x productivity why coding its…

    Watch on YouTube ↗

  • Everything We Got Wrong About Research-Plan-Implement - Dexter Horthy

    March 24, 2026 · 📺 AAIF Live

    Dexter Horthy (HumanLayer) Keynote at the Coding Agents Conference at the Computer History Museum, March 3rd, 2026. Abstract // RPI was supposed to fix AI coding, but Dexter Horthy says it kind of broke it, especially when teams started outsourcing thinking to agents, so now he’s pushing qrspi: fewer magic prompts, more structure, more human ownership, because the real problem isn’t the AI, it’s engineers trying not to think. Bio // Dex is currently focused on building AI coding agents that can tackle complex problems in large codebases at HumanLayer. Prior to this, he worked on APIs for ag…

    Watch on YouTube ↗

  • Why Your AI Agents Don’t Work with Dex Horthy of HumanLayer | In-Context Cooking

    March 06, 2026 · 📺 Latent Space

    In this episode, we have Dex Horthy, founder and CEO of Humanlayer and the mind behind “context engineering,” joining us to recreate restaurant-style Dan Dan noodles. From his first internship at NASA JPL at 17 to building dev tools for AI engineers, Dex shares how real AI systems are actually built, why most demos don’t translate to production, and what the future of software engineering looks like in the age of coding agents. We talk about: • How Dex landed a NASA Jet Propulsion Lab internship at 17 • The origin of “context engineering” and why the term stuck • Why the top 1% of AI engineer…

    Watch on YouTube ↗

  • How to Ship Complex Features 10x Faster with AI Agents | Dex Horthy (HumanLayer)

    March 02, 2026 · 📺 AI Tinkerers

    Learn how Dexter Horthy, creator of the viral "12 Factor Agents" framework and founder of HumanLayer, built a structured multi-step agentic workflow that helps engineers ship complex features in large codebases — without sacrificing code quality or maintainability. Dex walks through his complete "Research → Design → Structure → Implement" methodology and gives a live demo of Riptide, his new orchestration tool built on top of Claude Code. What You'll Learn: Discover why most AI coding workflows break down on hard, real-world features — and how a disciplined, human-in-the-loop pipeline delive…

    Watch on YouTube ↗

The summary and quote tags on this profile are produced with AI assistance from verified, first-person interview transcripts, then checked by our team to confirm the speaker's identity and the accuracy of every quote. See how we verify →