Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note3 min read

CoPlan: A Trustworthy Co-Intelligence Interface for Care Planning through Role-Based Contestable Argument Graphs

Source

arXiv

arxiv.org/abs/2608.05107v1

Read the source

Source

Plain-Language Brief

CoPlan is a new AI system designed to help with care planning for clinicians, patients, caregivers, and care teams. It allows stakeholders to inspect, challenge, and revise plans if they conflict with clinical judgment, patient values, or real-world feasibility. The system uses specialized AI agents that generate candidate interventions and supporting or challenging arguments, while human care planners can accept, reject, modify, or add arguments before final plan generation.

What the Document Says

  • AI-supported care planning is aimed at helping clinicians, patients, caregivers, and care teams coordinate complex decisions across clinical, functional, psychosocial, and environmental needs
  • Many AI systems present recommendations as fixed outputs
  • CoPlan aims to overcome this limitation by using a multi-agent workflow
  • In CoPlan, specialized AI agents generate candidate interventions and supporting or challenging arguments
  • Human care planners can accept, reject, modify, or add arguments before final plan generation
  • The system promotes co-intelligence, where humans and AI agents contribute complementary expertise
  • It also supports contestability, where recommendations remain open to inspection, revision, and justification
  • CoPlan was demonstrated in an aging-in-place care planning scenario
  • The system supports adaptive care team recruitment, role-based argument review, final care plan generation, and practical follow-up through scheduling agents
  • The work contributes a contestable care planning interface and a design framing for trustworthy human-AI care planning that preserves human agency and clinical accountability

Key Concepts Mentioned

  • AI-supported care planning
  • CoPlan
  • multi-agent workflow
  • specialized AI agents
  • candidate interventions
  • supporting or challenging arguments
  • human care planners
  • co-intelligence
  • contestability
  • inspection
  • revision
  • justification
  • aging-in-place care planning
  • adaptive care team recruitment
  • role-based argument review
  • final care plan generation
  • practical follow-up
  • scheduling agents
  • trustworthy human-AI care planning
  • human agency
  • clinical accountability

Claims Made by the Document

  • Many AI systems present recommendations as fixed outputs
  • CoPlan aims to overcome this limitation
  • The system supports adaptive care team recruitment
  • The system supports role-based argument review
  • The system supports final care plan generation
  • The system supports practical follow-up through scheduling agents
  • The work contributes a contestable care planning interface and a design framing for trustworthy human-AI care planning that preserves human agency and clinical accountability

Evidence Used

  • The text describes CoPlan's features and how it aims to improve the current state of AI-supported care planning

Methods / Approach

  • Using a multi-agent workflow
  • Generating candidate interventions and supporting or challenging arguments by specialized AI agents
  • Allowing human care planners to accept, reject, modify, or add arguments before final plan generation

Limitations Stated by the Authors

Not stated in source

Limitations Noted by the Agent

Agent interpretation — not from the source.

The system's effectiveness and performance in real-world scenarios is not evaluated or discussed in the provided text

Open Questions

  • What is the effectiveness of CoPlan in real-world scenarios?
  • How does the system handle conflicting arguments from human care planners and AI agents?

Notes for Future Q&A

May include interpretation. Labeled where it does.

The paper focuses on presenting the design of CoPlan, but it does not discuss its performance or effectiveness in real-world scenarios. It also does not elaborate on how the system handles conflicting arguments.

Raw Abstract / Excerpt

AI-supported care planning can help clinicians, patients, caregivers, and care teams coordinate complex decisions across clinical, functional, psychosocial, and environmental needs. However, many AI systems present recommendations as fixed outputs, limiting stakeholders' ability to inspect, challenge, and revise plans when they conflict with clinical judgment, patient values, or real-world feasibility. We present CoPlan - a Co-Intelligent and Contestable Interface for Human-AI Care Planning. CoPlan uses a multi-agent workflow in which specialized AI agents generate candidate interventions and supporting or challenging arguments, while human care planners can accept, reject, modify, or add arguments before final plan generation. Through this design, CoPlan combines co-intelligence, in which humans and AI agents contribute complementary expertise, with contestability, where recommendations remain open to inspection, revision, and justification. We demonstrate CoPlan in an aging-in-place care planning scenario. The system supports adaptive care team recruitment, role-based argument review, final care plan generation, and practical follow-up through scheduling agents. This work contributes a contestable care planning interface and a design framing for trustworthy human-AI care planning that preserves human agency and clinical accountability.