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

The paper introduces CoPlan, an AI system designed to assist in care planning by allowing multiple stakeholders (clinicians, patients, etc.) to inspect, challenge, and revise plans. It uses a multi-agent workflow where AI agents generate interventions and arguments while human planners can accept, reject, modify or add arguments before finalizing the plan. The system supports adaptive care team recruitment, role-based argument review, care plan generation, and follow-up through scheduling agents.

What the Document Says

  • The AI system presented is called CoPlan.
  • CoPlan is designed for AI-supported care planning.
  • CoPlan allows stakeholders to inspect, challenge, and revise plans.
  • CoPlan uses a multi-agent workflow with specialized AI agents generating interventions and arguments.
  • Human care planners can accept, reject, modify or add arguments in CoPlan.
  • The final plan is generated after human intervention.
  • CoPlan supports adaptive care team recruitment.
  • It has role-based argument review feature.
  • CoPlan generates care plans and handles practical follow-up through scheduling agents.
  • The paper claims that CoPlan preserves human agency and clinical accountability.

Key Concepts Mentioned

  • AI system
  • care planning
  • multi-agent workflow
  • specialized AI agents
  • human care planners
  • adaptive care team recruitment
  • role-based argument review
  • final care plan generation
  • practical follow-up
  • scheduling agents

Claims Made by the Document

  • CoPlan can help in complex decision coordination across various needs.
  • AI systems often present recommendations as fixed outputs, limiting stakeholders' ability to inspect and revise plans.
  • CoPlan combines co-intelligence (human and AI contributions) with contestability (open to inspection and revision).
  • CoPlan preserves human agency and clinical accountability.

Evidence Used

  • The paper describes the design and functionality of CoPlan.
  • The authors state the limitations of traditional AI systems in care planning.

Methods / Approach

  • Use of multi-agent workflow
  • Incorporation of human intervention for plan revision

Limitations Stated by the Authors

  • The paper does not provide detailed information about how CoPlan handles conflicts between human and AI recommendations.

Limitations Noted by the Agent

Agent interpretation — not from the source.

  • The text lacks information about the system's effectiveness in real-world scenarios.
  • There is no data provided to evaluate the performance of CoPlan compared to traditional care planning methods.

Open Questions

  • How does CoPlan handle conflicts between human and AI recommendations?
  • What is the system's effectiveness in real-world scenarios?
  • How does CoPlan compare to traditional care planning methods in terms of performance?

Notes for Future Q&A

May include interpretation. Labeled where it does.

  • The paper focuses on introducing the design and functionality of CoPlan, but does not provide detailed information about its implementation or evaluation.

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.