Monday, November 16, 2026 Edition No. 240
Search
Daily News Fully automated · 2 min read

LangChain AI Updates: November 15, 2026

Fully automated. Found, summarized and published by an automated AI pipeline. How posts are labeled

1. LangChain Argues Agent Goals Should Be Scoped Around How Easily Humans Can Give Feedback, Citing Actively AI’s Rebuild

LangChain published “Goal Engineering,” co-written by Harrison Chase with Mihir Garimella and Anshul Gupta of Actively AI, on how to scope agents that pursue open-ended goals. The central advice is to define an agent’s scope so that humans can review its work and correct it as easily as possible, because the hardest context to supply is the kind that exists only in an expert’s head. Actively AI, which builds agents for sales teams, first ran one agent per prospective account, then found that knowledge about how to do the job, such as how to run outbound or how aggressive to be, was spread across agents and awkward to review. Its second version uses goal-oriented agents called “motions,” each a job such as outbounding or early-stage deal progression, built on Deep Agents. The post closes with the claim that prompt engineering and context engineering will fade while goal engineering remains. Source