Distributed Agency
What interface forms are appropriate when agency is distributed across humans, models, and protocols? This thread examines how design changes when the user is sometimes a person, sometimes a model, sometimes both.
What interface forms are appropriate when agency is distributed across humans, models, and protocols?
Reading Path
-
The design question: what would a Bauhaus for agent-era interfaces look like?
-
An answer in practice: Doomslayer-UI as anti-feed, high-agency interface language
-
The knowledge dimension: epistemic horror as design methodology
-
Laws as types: making regulation machine-readable for agent consumption
-
Design systems as public APIs: when your interface speaks to machines too
-
Attestations as design surfaces: trust made visible and interactive
-
When the description of a coordination mechanism IS the coordination mechanism — agency through propagation