Context Engineering Our Way to Long-Horizon Agents: LangChain’s Harrison Chase

About this episode

Harrison Chase discusses the evolution and importance of context engineering in the development of long-horizon AI agents.

Harrison Chase, cofounder of LangChain and pioneer of AI agent frameworks, discusses the emergence of long-horizon agents that can work autonomously for extended periods. Harrison breaks down the evolution from early scaffolding approaches to today's harness-based architectures, explaining why context engineering - not just better models - has become fundamental to agent development. He shares insights on why coding agents are leading the way, the role of file systems in agent workflows, and how building agents differs from traditional software development - from the importance of traces as the new source of truth to memory systems that enable agents to improve themselves over time. Hosted by Sonya Huang and Pat Grady

People in this episode

Hosts: Sonya Huang, Pat Grady

Guest: Harrison Chase

Topics covered

• AI agents
• context engineering
• long-horizon agents
• software development
• autonomous systems
• agent frameworks

Keywords

• AI
• agents
• context engineering
• LangChain
• software development
• autonomy
• file systems
• memory systems

Mentioned in this episode

Organizations: LangChain, Sequoia Capital

More episodes of Training Data

• Google DeepMind's Logan Kilpatrick: Why the Model Eats the Harness · June 11, 2026 · 51 min
• LIVE: Jensen Huang on Building the Dynamo of the Intelligence Age · June 10, 2026 · 41 min
• Knowing What Your Customers Want, All the Time: Listen Labs' Alfred Wahlforss · June 2, 2026 · 42 min
• How Cursor Trained Composer on Fireworks: Distributed Infrastructure for High-Performance RL · May 26, 2026 · 46 min
• Rebuilding IT From the Ground Up for the AI Age: Serval's Jake Stauch · May 19, 2026 · 38 min
• Suno's Mikey Shulman: Everyone Can Make Music Now · May 13, 2026 · 35 min