# Harrison Chase outlines new context engineering challenges for proactive agents

> Original title: A lot of content engineering challenges have pretty standard solutions, which has lead to some engineers saying agent engineering is solv...

- Source: Harrison Chase
- Published: 2026-10-31T15:31:29.000Z
- Bad Influence: https://badinfluence.news/items/we77q6xp0z0jltos9c2wpt9qp
- Original: https://x.com/hwchase17/status/2116553654857867330

## Summary

LangChain's Harrison Chase says agent builders are converging on a standard architecture of an LLM running in a loop, calling tools in a sandbox. He argues that proactive, always-on, goal-oriented agents raise new context engineering problems, including when to notify users, what memory to keep, and how to handle async subagent work. Chase says LangChain and the industry lack general solutions for these challenges yet.

## Post

A lot of content engineering challenges have pretty standard solutions, which has lead to some engineers saying agent engineering is solved/boring

True to some extent, but there are a bunch of (fun) new ones emerging as agents evolve! https://x.com/i/article/2116547440857718784