Agents
Isn’t just what to remember, but when to update it: in the loop or after the fact. A must read by @hwchase17!
This post by Harrison Chase (LangChain creator) discusses the importance of timing in updating information systems or memory mechanisms in AI applications, comparing real-time updates ('in the loop')
This post by Harrison Chase (LangChain creator) discusses the importance of timing in updating information systems or memory mechanisms in AI applications, comparing real-time updates ("in the loop") versus retrospective updates ("after the fact"). The content likely addresses best practices for maintaining accurate and current knowledge in AI systems, with implications for prompt engineering and data management workflows.
Related
- Very good article from @hwchase17 about the agent harness and memory achitecture.
- I still don’t properly handle memory and I think I should now
- memory lock-in doesn't kick in when you adopt the harness. it kicks in 6 months later when leaving means starting over from zero. by then th…
- your harness = your memory if you'd rather read in blog form, link here: https://blog.langchain.com/your-harness-your-memory/
- TLDR; memory = harness => keep your memory and harness on your side of the API.
- For an agent builder, memory is sustained advantage For the model provider, memory is switching cost
Source: Harrison Chase (X) | 2026-04-17