That's actually exactly what I was saying. Value, it's in the harness.

Harrison Chase, co-founder and CEO of LangChain, made a post on X affirming a point about where value lies in AI systems, specifically arguing that value is found "in the harness" — referring to the surrounding infrastructure, orchestration, and integration layers rather than the raw models themselves. This perspective aligns with LangChain's core thesis that the tooling, workflows, and agentic frameworks built around LLMs are where meaningful product differentiation and utility emerge. The comment appears to be part of a broader conversation about AI value chains and where competitive advantages are created in the LLM ecosystem.

@hwchase17 Exactly. he harness is where the 'soul' of the agent lives. Excited to see how Deep Agents and LangChain can keep pushing this la…
harness engineering > prompt engineering prompts get you 80% there the last 20% — tool routing, memory retrieval, retry logic, evals — thats…
TLDR; memory = harness => keep your memory and harness on your side of the API.
your harness = your memory if you'd rather read in blog form, link here: https://blog.langchain.com/your-harness-your-memory/
I think you should build your own harness too. Build on primitives. Models come and go.
OPEN MEMORY, OPEN HARNESS the industry shifts to closed agent harnesses locking memory behind proprietary apis. https://x.com/hwchase17/stat…

Source: Harrison Chase (X) | 2026-04-12

Related