Agents
I think you should build your own harness too. Build on primitives. Models come and go.
Harrison Chase, co-founder of LangChain, advocates for developers building their own custom harnesses on top of foundational primitives rather than relying on high-level abstractions or specific model
Harrison Chase, co-founder of LangChain, advocates for developers building their own custom harnesses on top of foundational primitives rather than relying on high-level abstractions or specific model integrations. The core argument is that AI models are transient and frequently replaced, so tightly coupling applications to specific models creates fragility and technical debt. Building on stable primitives ensures greater longevity and adaptability as the rapidly evolving AI landscape continues to shift.
Related
- im excited about agent harnesses because i think are the first stable agent abstractions we can build on top (which is why we're investing s…
- Open Harness, separated from model providers is a critical architectural pattern.
- This 10-min read from @Vtrivedy10 changes how you build AI agents. Most people are stuck in the same loop; switching models when agents brea…
- For anyone building agentic workflows: the real bottleneck isn't the model, it's the harness. Open standards are a must, not just for flexib…
- Relying on model providers' stateful APIs or harnesses creates lock-in: switching models means losing your agent's memory -- a cost that onl…
Source: Harrison Chase (X) | 2026-04-12