Guides · Agentic AI
Agentic AI in healthcare, from definition to deployment.
Agentic AI — systems that plan and execute multi-step tasks rather than answer single prompts — is entering healthcare through the back office first. The documented deployments cluster where work is structured and the risk is administrative: prior authorization, revenue-cycle and coding work, documentation and handover in nursing workflows. Clinical autonomy remains the exception, and for good reason: an agent that acts is a different risk object from a model that predicts, and the safety frameworks, oversight designs, and evaluation methods it demands are still being written.
These guides cover both halves of that picture. On the definitional side: what agentic AI actually means in a healthcare context, and what MCP and the interoperability standards imply for hospital agents that need to touch the EHR. On the operational side: how to evaluate an agent before deployment, how to design human oversight that survives real workloads rather than dissolving into rubber-stamping, and what the documented deployments — tracked and dated here — actually show. The aim is a working map of a category that changes quarterly, drawn from primary sources rather than product announcements.
10 guides in this collection
Agent safety frameworks for clinical settings
There is no single safety standard for clinical AI agents yet. In its place is a stack of published frameworks — general AI risk, LLM and agent security, healthcare assurance, and regulation — that a hospital has to compose itself. This guide maps which standard governs which layer. As of July 2026.
Updated 22 Jul 2026Agents in nursing workflows: documentation, handover, and the virtual-nursing evidence
Two very different things get marketed as the "AI nurse": documentation assistants that reformat what a nurse says, and virtual-nursing programs that move tasks to a remote colleague. The measured time savings, the completeness gains, and why one of these has much stronger evidence than the other. As of July 2026.
Updated 22 Jul 2026Designing human oversight for clinical agents
How to build supervision around an AI agent that acts on the clinical record — translating EU AI Act Article 14 and FDA guidance into concrete oversight tiers, automation-bias defences, and after-go-live monitoring. As of July 2026.
Updated 22 Jul 2026Documented agentic deployments in healthcare: a tracker
A running tally of the healthcare AI-agent systems that carry a published paper or the operator's own disclosure — what each one does, where the human sits, and what it actually reported. The field is loud; the documented set is small. As of July 2026.
Updated 22 Jul 2026EHR-integrated agents: what it takes, and what the evidence shows
Putting an AI agent inside the electronic health record means three hard jobs — read the record, reason over it, and act on it — each governed by a standard and measured by a benchmark. Here is what the published evidence says about how well today's agents do each one. As of July 2026.
Updated 22 Jul 2026How to evaluate an agent before deployment
A pre-deployment checklist for clinical AI agents — ten dimensions to test before a system touches a patient, each tied to a published benchmark or a named safety framework, with the questions to put to any vendor. As of July 2026.
Updated 22 Jul 2026MCP and interoperability for hospital agents
A hospital agent needs two standards to do its job: one for how the model reaches its tools, and one for the shape of the clinical data it reaches. This guide maps the MCP-plus-FHIR stack from the specifications themselves, and the security duties that live at the seam between them. As of July 2026.
Updated 22 Jul 2026Prior-authorization agents: what the CMS rule and the evidence actually say
Prior authorization is being automated from both ends at once — providers building agents to submit and appeal, payers running algorithms to adjudicate. What the CMS-0057-F final rule now requires, what the published evidence shows an agent can and cannot do, and the one guardrail regulators drew around automated denials. As of July 2026.
Updated 22 Jul 2026Revenue-cycle and coding agents: accuracy, denials, and the compliance stakes
Coding and denial-management agents are being pointed at the most repetitive, highest- volume work in a hospital's back office. What the peer-reviewed accuracy benchmarks actually show, why a fabricated billing code is a compliance event rather than a cosmetic error, and where the audit trail has to stay human. As of July 2026.
Updated 22 Jul 2026What is agentic AI in healthcare
The hub for agentic AI in a clinical setting — the working definition from the peer-reviewed literature, the anatomy of an agent, what benchmarks show these systems can and cannot yet do, and why the definition itself carries governance weight. As of July 2026.