Human AI interaction design shapes future capabilities and performance
Adaptive Complementarity in Human-AI Systems: Architecture as a State-Shaping Choice
Human-Computer Interaction
Summary
Choosing how humans and AI work together changes not just how well they do tasks now but also what they can do in the future. The authors present a framework called adaptive complementarity that helps decide how to set up interactions like who sees what information, who does which tasks, and when things happen. These choices affect how skills develop and how well the team performs later. Different ways of working together can change outcomes even if the human skill level is the same. The framework helps figure out when it’s worth adjusting the setup based on what has happened before.
What this means in practice
- •For ai system designers: Design interaction protocols that consider how current settings shape future team abilities and workflow value.
- •For business process managers: Optimize human-AI collaboration structures by evaluating long-term effects of information sharing and task division.
A position paper. It proposes an approach and reports no results.
Authors
Babak Heydari
Abstract
Human-AI interaction can improve current performance while changing the capabilities and relationships on which future performance depends. We develop adaptive complementarity, a framework for choosing interaction architecture with these state consequences in view. Access, information exposure, task allocation, timing, and communication can alter which arrangement will be valuable later; their settings can often be reset faster than the capabilities, search patterns, or conventions they create. Three mechanisms organize the argument: information exposure and collective search, delegation and capability evolution, and strategic interdependence and information governance. Their integration yields cross-mechanism implications, including conditions under which a loss of expertise heterogeneity increases the information differentiation required to preserve independent search. We distinguish strong human-AI complementarity from advantage over another workflow and from advantage over an evolving reference policy. A knowledge-coverage illustration shows how different interaction histories can reverse current workflow rankings even at equal human competence. It also separates that result from the incremental value of state feedback, which can be small when a well-chosen stable workflow anticipates learning. The framework directs evaluation toward the states present interaction creates, their consequences for later architectural fit, and the conditions under which observing and responding to them is worthwhile.