The 3 Roles of Context for AI Agents
3.42T1.5 sourceNielsen Norman Group
Source record
Published by Nielsen Norman Group (T1.5 source). The original is at https://www.nngroup.com/articles/3-agent-context-roles/?utm_source=rss&utm_medium=feed&utm_campaign=rss-syndication.
Pipeline notes
The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.
SummaryNielsen Norman Group describes a framework in which AI-agent power users curate three kinds of context: global (persistent across tasks), local (task-specific), and ambient (raw streams like email or chat), each serving a distinct role in supporting agent work.
Why it mattersCondenses NN/g user research into a concrete three-part mental model for organizing the information an AI agent needs, usable by anyone designing or running agent workflows.

Cited by
No citations on record.
