Clinical Harness for Governable Medical AI Skill Ecosystems
Summary
This paper proposes the Clinical Harness, a runtime governance architecture for registering, orchestrating, guarding, and monitoring AI-enabled clinical capabilities, using osteoporosis as a demonstration case.
View Cached Full Text
Cached at: 06/26/26, 05:13 AM
# Clinical Harness for Governable Medical AI Skill Ecosystems Source: [https://arxiv.org/abs/2606.26494](https://arxiv.org/abs/2606.26494) [View PDF](https://arxiv.org/pdf/2606.26494) > Abstract:Medical AI remains organized around isolated models, whereas clinical care requires accountable capabilities that persist across time\. We propose clinical AI skills and the Clinical Harness: a runtime governance architecture for registering, orchestrating, guarding and monitoring AI\-enabled clinical capabilities\. Using osteoporosis as an exemplar, we show how knowledge\-driven, data\-driven and physics\-enhanced skills can support lifecycle care under runtime governance\. ## Submission history From: Tianhan Xu \[[view email](https://arxiv.org/show-email/3796e7ba/2606.26494)\] **\[v1\]**Thu, 25 Jun 2026 00:53:24 UTC \(2,794 KB\)
Similar Articles
From Single Chatbots to Governed Agent Ecosystems: An Agentic AI Pattern Catalogue and Orchestration Framework for Mission-Critical Hospital Information Management Systems
This paper proposes a compliance-first Agentic AI pattern catalogue and orchestration framework for hospital information management systems, moving from single chatbots to governed multi-agent ecosystems with risk stratification, governance hooks, and support for EHR systems like Epic and Cerner.
Evidence-Grounded AI for Musculoskeletal Care
This paper presents an evidence-grounded AI framework for diagnosing and treating musculoskeletal conditions, leveraging clinical data and orthopedic knowledge.
From Model Scaling to System Scaling: Scaling the Harness in Agentic AI
This paper argues that advancing agentic AI requires scaling the system architecture around foundation models, focusing on auditable, modular, and verifiable components. The authors introduce CheetahClaws, a reference harness, and outline bottlenecks in context governance, trustworthy memory, and dynamic skill routing.
Asclepius: An Adaptive Harness for Long-Horizon Clinical Agents
Asclepius is an adaptive agent scaffolding for long-horizon clinical tasks that improves critical-action correctness by 22% over a baseline agent framework in simulated emergency-department shifts.
Runtime Governance for Agentic AI: Action-Boundary Control with Trusted Provenance and Fail-Closed Execution
The paper introduces Aegis, a runtime governance system for agentic AI that mediates tool actions through trusted authorization, preventing risky side effects in evaluated sandbox scenarios.