Training Data Context Engineering Our Way to Long-Horizon Agents: LangChain’s Harrison Chase
127 snips
Jan 21, 2026 
Harrison Chase, cofounder of LangChain and a pioneer in AI agent frameworks, dives into the world of long-horizon agents capable of autonomous operation. He explains how context engineering has become vital for agent development, emphasizing improvements in harnesses over mere model upgrades. Harrison shares fascinating applications of coding agents and highlights the importance of traces as new sources of truth. He also contrasts building agents with traditional software, revealing insights into memory and self-improvement mechanisms that set them apart.
AI Snips
Chapters
Transcript
Episode notes
Why Long-Horizon Agents Now Work
- Long-horizon agents work because models improved and harnesses matured together.
- Coding-first agents lead adoption because they naturally produce draftable outputs for human review.
Build Opinionated Harnesses
- Use a batteries-included harness rather than a minimal framework for long agents.
- Provide built-in planning, compaction, and file-system tools to manage multi-step context.
Make Subagents Communicate Clearly
- Design subagents and skills with clear communication protocols and final-response rules.
- Prompt subagents so their outputs are consumable by the main agent to avoid missing context.