Harrison Chase of LangChain on Deep Agents, LangSmith, and Earning Trust | NVIDIA AI Podcast Ep. 297

Harrison Chase of LangChain on Deep Agents, LangSmith, and Earning Trust | NVIDIA AI Podcast Ep. 297

Author: NVIDIA May 6, 2026 Duration: 24:54
LangChain has surpassed 1 billion downloads—and the framework that started as a weekend project is now the harness powering the next generation of production-grade AI agents. In this episode, Harrison Chase, co-founder & CEO of LangChain, breaks down the architecture behind deep agents, explains why systems like Claude Code, Manus, and Deep Research all share the same foundational pattern, and lays out what it actually takes to deploy autonomous agents responsibly in the enterprise. 🔬Topics covered: What is a "deep agent," and why does architecture matter more than ever? How enterprises are (and aren't) embracing autonomous agents LangSmith: observability, tracing, and evaluation-driven development Mixing frontier and open models (NVIDIA Nemotron) in multi-agent systems What's next: async subagents, proactive/always-on agents, agent memory, and agent identity Chapters: 00:00 – LangChain origin story and the deep agent architecture 01:46 – What is a deep agent? 03:31 – Enterprise trust: risk, autonomy, and iteration 04:38 – LangSmith: observability and evaluation-driven development 13:30 – Frontier vs. open models and the Nemotron Coalition 18:10 – What's next: async subagents, agent memory, and agent identity

Behind every major shift in how we live and work, there's a story about the technology that made it possible. The NVIDIA AI Podcast, produced by NVIDIA, delves into those narratives, moving beyond headlines to explore the human and technical ingenuity driving progress. Each episode connects with creators, researchers, and pioneers who are applying artificial intelligence and accelerated computing in surprising ways. You'll hear conversations that unpack complex ideas, from how AI is accelerating scientific discovery in medicine and climate science to its role in reimagining creative industries and building more sustainable systems. This isn't about abstract futures; it's a grounded look at the tools and collaborations solving real-world problems today. The discussions are crafted to be accessible, offering clarity on transformative topics without oversimplifying the profound work being done. Tuning into this podcast provides a unique vantage point into the ecosystem of innovation, where the focus is on practical applications and the thinkers turning possibility into reality. It's an ongoing series for anyone curious about the mechanics of change and how computational power is being harnessed to tackle some of our most pressing challenges and unlock new opportunities across every field.
Author: Language: English Episodes: 50

NVIDIA AI Podcast
Podcast Episodes
Superhuman Surgery with Moon Surgical and Maestro - Ep. 272 [not-audio_url] [/not-audio_url]

Duration: 33:04
CEO Anne Osdoit joins the podcast to explore how Moon Surgical’s Maestro platform blends robotics, AI, and human expertise to boost surgeon skills, enhance workflow efficiency, and reduce fatigue. Hear firsthand how pati…
Amperity Reimagines Data and Developer Workflows with AI - Ep. 271 [not-audio_url] [/not-audio_url]

Duration: 36:40
Derek Slager, co-founder and CTO of Amperity, explores how agentic AI and vibe coding are reshaping enterprise data management and the developer experience on the NVIDIA AI Podcast. Hear how Amperity’s platform unifies c…
How OpenUSD and AI Are Building Smarter Virtual Worlds - Ep. 268 [not-audio_url] [/not-audio_url]

Duration: 24:21
Aaron Luk, NVIDIA’s Director of Product Management for Simulation Technology, dives into Universal Scene Description (OpenUSD) and how it integrates seamlessly with AI to simulate rich, physically accurate scenarios. Dis…