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

Описание: 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

00:00 Introduction
01:54 Discussing Long Horizon Agents
03:00 Examples of Long Horizon Agents
04:56 Harness Engineering and Model Integration
07:09 Evolution of Agent Frameworks
18:22 Building Long Horizon Agents vs. Software
19:21 Understanding Non-Deterministic Systems
19:43 The Importance of Tracing in Lang Smith
20:44 Context Engineering and Its Significance
21:14 Testing and Collaboration in Agent Development
22:14 Iterative Nature of Building Agents
23:04 The Role of Memory in Agent Development
23:52 Challenges for Existing Software Companies
27:43 Human Judgment in Evaluating Agents
32:47 Future of Agent Development and Memory
34:37 Async and Sync Modes in Long Horizon Agents
37:29 The Role of Code Sandboxes and File Systems
38:51 Conclusion and Future Predictions