ADEPTS: A Capability Framework for Human-Centered Agent Design

2025-07-18

AI Summary

Current AI agent development lacks a user-centered, unified capability standard, leading to misalignment among UX design, engineering implementation, and ethical governance—and thereby impeding improvements in understandability, controllability, and trustworthiness. To address this, we propose ADEPTS, the first systematic framework defining six core user-centered capabilities: Accountability, Discoverability, Explainability, Predictability, Teachability, and Safety. ADEPTS establishes an interdisciplinary, concise, and actionable capability taxonomy alongside standardized technical–experiential interface specifications. It bridges the gap between existing UX heuristics, engineering architecture patterns, and ethical checklists, enabling coordinated alignment of capability goals among developers, designers, and policymakers. Empirical evaluation demonstrates that ADEPTS effectively guides capability design and assessment across diverse AI agent types, confirming its broad applicability and practical utility.

Technology Category

• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness
• Humans and AI: User Experience and Usability
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Large language models have paved the way to powerful and flexible AI agents, assisting humans by increasingly integrating into their daily life. This flexibility, potential, and growing adoption demands a holistic and cross-disciplinary approach to developing, monitoring and discussing the capabilities required for agent-driven user experiences. However, current guidance on human-centered AI agent development is scattered: UX heuristics focus on interface behaviors, engineering taxonomies describe internal pipelines, and ethics checklists address high-level governance. There is no concise, user-facing vocabulary that tells teams what an agent should fundamentally be able to do. We introduce ADEPTS, a capability framework defining a set of core user-facing capabilities to provide unified guidance around the development of AI agents. ADEPTS is based on six principles for human-centered agent design, that express the minimal, user-facing capabilities an AI agent should demonstrate to be understandable, controllable and trustworthy in everyday use. ADEPTS complements existing frameworks and taxonomies; differently from them, it sits at the interface between technical and experience development. By presenting ADEPTS, we aim to condense complex AI-UX requirements into a compact framework that is actionable guidance for AI researchers, designers, engineers, and policy reviewers alike. We believe ADEPTS has the potential of accelerating the improvement of user-relevant agent capabilities, of easing the design of experiences that take advantage of those capabilities, and of providing a shared language to track and discuss progress around the development of AI agents.

Problem

• Lack of unified guidance for human-centered AI agent development
• Absence of concise user-facing vocabulary for agent capabilities
• Need for a shared framework bridging technical and experience design

Innovation

• ADEPTS framework defines core user-facing agent capabilities
• Six principles ensure understandable, controllable, trustworthy agents
• Bridges technical and experience development for AI agents