Blog

Clinical AI perspectives on interoperability, agentic systems, and care delivery, from the team building the living record.

RSS feed
Latest

Why Healthcare Needs AI Agents: Connecting FHIR, MCP, and A2A

AI agents go beyond chat. They read EHR data, trigger workflows, and collaborate across systems. Powered by MCP, A2A, and FHIR, they represent a new operational layer in healthcare. This article breaks down how these technologies work together to enable real-world clinical applications.

Prompt Opinion Team3 min read
Read article

More writing

AI for Patients: Moments of Care

If it feels difficult to keep up with the pace of health AI for patients, that is understandable. However, stepping back from the constant stream of announcements reveals a clearer pattern. The consum

3 min read

Bots are Users Too: Why HTI-5 Changes Everything

HTI-5: The "Digital Power of Attorney" We were all expecting HTI-5 to have a strong focus on AI. Honestly, I was hoping they would formally adopt the Model Context Protocol (MCP) to standardize how AI

3 min read

AI in Healthcare: Clinical DRS

For any sports fan, there is nothing more frustrating than a game decided by a clearly wrong call. In cricket, we lived with that frustration for decades until the arrival of the Decision Review Syste

3 min read

“Safe” AI Agents: The Determinism Inside Non-Determinism

The Paradox of Non-Determinism The core strength of generative AI is its ability to generate creative, context-aware, non-scripted responses. That flexibility is what makes large language models power

3 min read

Guardrails for AI Agents: A Mask Analogy for Safe AI

Over the last few days, I have been discussing a 7-layered structure to understand AI agents. The layer that generates the most confusion and questions is Layer 5: Guardrails. Guardrails are the mecha

3 min read

An “Open” Agent Framework: Building AI That Avoids the EHR Trap

I recently shared a 7-layer stack to illustrate how AI agents work, particularly within the healthcare context. The follow-up discussions have been insightful, and one recurring question keeps surfaci

3 min read

Guardrails for AI Agents: Designing Safety in a Non-Deterministic World

As AI agents become more powerful and autonomous, guardrails are what make them trustworthy. They sit at the intersection of capability and control, ensuring that intelligent systems operate safely in

3 min read

When Do You Really Need AI Agents?

Finding the Agent Sweet Spot in Healthcare There is a growing buzz that AI agents are the solution to every problem. Let’s be clear. AI is not a single thing. It spans a wide spectrum of capabilities,

2 min read

Clinical Decision Support with AI Agents

Clinical Decision Support has always been about one central goal: helping clinicians make better decisions at the point of care. As AI agents begin to mature within healthcare, the workflow layer beco

3 min read

Evaluating AI in Healthcare: Beyond the LLM

Most conversations about evaluating AI systems in healthcare focus almost entirely on evaluating large language models. Benchmarks, hallucination rates, accuracy scores, and prompt robustness dominate

3 min read

Decoding AI Agents in Healthcare: The 7-Layer Stack

What exactly is an AI agent? Is it just a large language model? Is it ChatGPT wearing a lab coat? These questions come up frequently. After extensive discussions, real-world use case exploration, and

3 min read

Generative AI in Clinical Workflows

Ambient listening and automated documentation have dominated the conversation around Generative AI in clinical workflows. These use cases are highly visible, easy to understand, and deliver measurable

2 min read

From Chatbots to Autonomous Agents

The Journey of AI in Healthcare There was a time when adding a new feature to an EHR meant adding another screen. More clicks. More menus. More training. When third-party integrations became possible,

3 min read

MCP vs Multi-Agent vs A2A

What is the difference between Model Context Protocol (MCP) and Google’s Agent-to-Agent (A2A)? Where does multi-agent AI fit in? These terms are often used interchangeably, but they describe different

3 min read

Workflow vs Agent: Cutting Through the AI Semantics

We are getting lost in the semantics of what an AI agent is versus just AI. Let’s simplify it. Start with what we all know: ChatGPT or any AI-powered app. It is an application driven by a large langua

3 min read

Why Won’t Epic Just Build It?

We recently shared a post mapping various Generative AI use cases across the clinical workflow. Since then, we’ve had numerous conversations with startups building AI solutions across those categories

2 min read

RPA vs Agentic AI: It’s Not About “Can It Think?”

“What is real? How do you define real? If you’re talking about what you can feel, what you can smell, what you can taste and see, then ‘real’ is simply electrical signals interpreted by your brain.” —

3 min read

Complex Concepts, Simple Trios

A tripod offers stability because it stands on three legs. Primary colors create every hue because they form a foundational trio. In innovation, complex systems often reduce to simple, interconnected

2 min read

SMART on FHIR: We Built the App Store Rails. So Where’s the App Economy?

When the iPhone launched in 2007, Steve Jobs initially discouraged native third-party apps. Instead, he advocated for web apps accessed through Safari. By 2008, Apple reversed course and launched the

3 min read

MCP is Spreading Fast and Catching up with FHIR

As Model Context Protocol rapidly gains traction in the LLM ecosystem, many teams are eager to see these capabilities integrated natively into EHR platforms. We are optimistic that MCP-native capabili

2 min read

FHIR-ify Your Data. LLM-ify Your Apps. MCP-ify Your LLM.

Lately, we have been in many conversations around Model Context Protocol, and one question keeps coming up: What’s the use case? Who’s asking for this? It is a fair question. On the surface, MCP can l

2 min read

What Exactly Is a Tool in MCP?

If you have been following the Model Context Protocol conversation, you have likely noticed that “tools” are becoming the central concept. But what exactly is a tool in this context? In MCP, a tool is

3 min read

Let’s Talk About the Other Side of AI in Healthcare

In healthcare, AI is advancing on two powerful fronts. The first is the intelligence layer. This includes models powering clinical decision support, predictive analytics, risk scoring, auto-documentat

2 min read

4 options to Integrate Copilots with EHRs

Every major EHR will support some form of chat-based interface sooner rather than later. The real question is not whether copilots will exist, but how they will be architected. There are four primary

3 min read