Affora enables software interfaces friendlier for automated agents

Affora: A Design System for Agent-Friendly Interfaces

Human-Computer InteractionArtificial IntelligenceSoftware Engineering

Summary

Using software usually assumes a human is in control, but now automated agents also interact with interfaces designed for people. The authors introduce Affora, a design system that helps make software interfaces clearer to these agents while still looking familiar to humans. They ran studies showing how different designs affect both humans and agents, and created reusable components that keep the meaning clear even if the look changes. Affora connects what users experience and what agents read through the same interface, improving agent interactions in many cases.

What this means in practice

Authors

Jin Gao

Abstract

Computer-use agents increasingly operate software designed for people, but interfaces often leave actions or task state unclear to machine readers. We present Affora, a design system that supports both readers while preserving visual freedom and familiar human workflows. Three controlled studies examine component implementations, visual variation, and interaction-design principles. Their findings inform guidance from individual components to complete sites, supported by reusable implementations and executable checks. Agent performance depends on the interaction meaning available through its interface representation; substantial visual variation remains possible when that meaning is preserved. Evaluation on independently authored interfaces shows gains where Affora addresses existing deficits, but limited effects where those deficits are absent or outside its coverage. A workflow case provides preliminary evidence of reduced interaction cost. Affora connects user experience and agent experience through a shared interface rather than a separate agent-only surface.