Ian Mulvany

July 10, 2025

Patterns of agent interaction

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 

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 




About Ian Mulvany

Hi, I'm Ian - I work on academic publishing systems. You can find out more about me at mulvany.net. I'm always interested in engaging with folk on these topics, if you have made your way here don't hesitate to reach out if there is anything you want to share, discuss, or ask for help with!