This post is a really important one for those of us working in scholarly publishing - https://gradientflow.substack.com/p/a-new-framework-for-ai-knowledge
It talks about distinc patters for how we might interact with agents for knowledge work. The post describes the scholar agent, analysis agent, and facilitator agent patterns - go read the post to get the gist of it.
The key quote from the piece is
It talks about distinc patters for how we might interact with agents for knowledge work. The post describes the scholar agent, analysis agent, and facilitator agent patterns - go read the post to get the gist of it.
The key quote from the piece is
Firms that invest now in provenance tracking, shared memory stores, and clear escalation paths will be positioned to let future models shoulder more of the cognitive load without surrendering accountability
What I am interested in is that we have a lot of interaction patterns yet to explore. Related reading to this - liberating structures - https://www.liberatingstructures.com, and how do you manage talking to multiple agents at the same time? - https://interconnected.org/home/2025/05/23/turntaking