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: 100

NVIDIA AI Podcast
Podcast Episodes
One Brain, Any Robot: Skild AI's Skild Brain Explained - Ep. 295 [not-audio_url] [/not-audio_url]

Duration: 29:47
What if one AI brain could run every robot on the planet—a humanoid, a warehouse arm, and a dog-like inspection bot—all at once? That's not a thought experiment. That's what Skild AI is building right now. Deepak Pathak…
How AI Will Change Quantum Computing - Ep. 294 [not-audio_url] [/not-audio_url]

Duration: 31:28
What happens when you combine AI with quantum computing? NVIDIA's Nic Harrigan joins the AI Podcast to break down the state of quantum, explain why error correction is the pivotal challenge, and reveal how NVIDIA Ising—t…
Powering the AI Inference Wave with EPRI's Ben Sooter - Ep. 292 [not-audio_url] [/not-audio_url]

Duration: 32:20
AI is reshaping electricity demand. What does increased demand, and the shape of that demand, mean for the electric grid? Ben Sooter, Director of R&D at EPRI joins the podcast to explain why most of an AI model’s lifetim…