Last week at my annual physical, I caught two errors before my doctor did.

A lab order that conflicted with a medication I was already on. A duplicate test that had been run six weeks earlier at another visit. Neither was catastrophic. Both were the kind of thing that, ten years ago, would have gone unnoticed by everyone in the room, including me.

What changed isn’t my doctor. What changed is that I walked in with AI.

A new category of patient

I’m not the only one. According to a late-2025 West Health and Gallup poll, roughly one in four U.S. adults used an AI tool for health information in the past 30 days. When OpenAI launched ChatGPT Health in January 2026, it crossed 40 million daily users within weeks. Dr. Angelo Volandes, a Dartmouth physician and professor at Geisel, captured the dynamic in STAT in December: “Our patients aren’t waiting. They have already consulted ChatGPT or other AI chatbots before they arrive at appointments. They ask questions that assume their physician has considered options that the doctor has never encountered.”

I’d call this category the super-informed patient. Three behaviors define them:

1. Pre-visit differential. They arrive with a working hypothesis, a drug interaction screen, or relevant studies already pulled.

2. Real-time reconciliation. They check medications, lab orders, and care plans against AI during the encounter.

3. Post-visit verification. They re-examine notes, results, and recommendations after the visit, often surfacing follow-up questions that drive new messages, calls, or appointments.

This is not a fringe phenomenon. It is happening in your exam rooms today.

The productivity paradox, round two

Healthcare executives are planning for AI as a productivity multiplier for physicians. That frame is incomplete, and it ignores a lesson the industry already learned the hard way.

The electronic health record was sold as a productivity tool. What it delivered was higher patient volume, not more time per patient. The seminal Sinsky study in Annals of Internal Medicine (co-authored, notably, by clinicians at Dartmouth) found that for every hour of direct patient care, physicians spent nearly two additional hours on EHR and desk work. Subsequent research by Arndt and colleagues, published in Annals of Family Medicine in 2024, showed that EHR time increased another 7.8% from 2019 to 2023, with patient inbox messages rising 24%, even as the early benefits of AI scribes were already being rolled out at major systems.

The mechanism is well understood. Efficiency in healthcare gets absorbed by volume, not returned as time. Panels grow. Schedules tighten. The work that was supposed to disappear gets replaced by new work made possible by the gain.

Now repeat that pattern with AI.

Why this round is worse

The EHR productivity paradox played out on one side of the encounter. The clinician got a tool. The patient did not.

AI is different. For the first time in medical history, the patient has access to the same cognitive tool as the clinician, and the patient has far more time to use it.

Provider AI is being deployed to optimize throughput: ambient scribes, ordering automation, summarization, decision support. Patient AI is being deployed to optimize advocacy: differential generation, error detection, second-opinion validation. Same underlying technology, opposite vectors.

These vectors do not cancel each other out. They compound.

What this means for health system leaders

Plan for three consequences in 2026 and 2027.

First, encounter intensity rises. Even if documentation gets faster, the encounter itself becomes denser. More evidence is presented. More questions are asked. Decisions that used to be accepted are now negotiated.

Second, error surfacing shifts upstream to the patient. Patients are catching conflicts, duplications, and outdated guidance in real time. This changes quality signals, medicolegal exposure, and the cadence of post-visit communication. Inbox volume, already growing, will accelerate.

Third, physician work categories expand. Defending decisions to AI-prepared patients, documenting clinical reasoning at higher fidelity, and managing rework triggered by patient challenges are emerging as real categories of physician time. None of them are on most cFTE models. None of them appear in any standard time study.

You cannot manage what you cannot forecast

Every health system planning an AI strategy is making implicit assumptions about how physician time will be reallocated. Most of those assumptions are wrong, because they are based on data that does not exist. Annual time studies cannot capture monthly shifts. Productivity benchmarks cannot capture changes in encounter composition. RVU trends cannot capture the time spent defending decisions or responding to AI-prepared inbox messages.

Continuous, accurate physician activity data is the foundation, not a deliverable. Without it, you cannot forecast the reallocation that’s already underway. You can only be surprised by it.

The question for 2026

Every CMO and CFO is being asked some version of this by their board: what is our AI strategy, and what return do we expect?

Here is the better question to answer first: Is our AI strategy planning for a busier physician or a less busy one, and what evidence are we using to decide?

If the answer is “we expect AI to give time back to our physicians,” ask what data supports that expectation, and what your plan is if it doesn’t.

The super-informed patient is already in your exam room. The question is whether your strategy has accounted for them.

Sources

1. Sinsky CA, Colligan L, Li L, et al. “Allocation of Physician Time in Ambulatory Practice: A Time and Motion Study in 4 Specialties.” Annals of Internal Medicine, 2016.

2. Arndt BG, Micek MA, Rule A, et al. “More Tethered to the EHR: EHR Workload Trends Among Academic Primary Care Physicians, 2019 to 2023.” Annals of Family Medicine, 2024.

3. Volandes A. “Patients are consulting AI. Doctors should, too.” STAT, December 30, 2025.

4. West Health and Gallup Center on Healthcare in America, AI for Health Information Poll, late 2025.

5. OpenAI, ChatGPT Health launch announcement, January 2026.

Paul J. Swider is CEO & Chief AI Officer at RealActivity, a Microsoft Partner specializing in mission-critical AI for healthcare systems. He has 30+ years in healthcare technology, has trained over 3,000 engineers across GE, IDX, and Microsoft, and is the founder of BOSHUG, the Boston Healthcare Cloud & AI Community spanning 50+ countries.

While the AI world obsesses over who has the smartest chatbot, SpaceX quietly struck a partnership that includes a $60 billion call option on a code editor most people have never heard of. Not for its models. Not for the hype. For something far more consequential: a fully realized agent platform that already lets fleets of AI coders ship real software, test it, demo it, and hand you a PR while you sleep.

Cursor didn’t just add AI to VS Code. It rebuilt the entire developer experience around agents. And on April 21, 2026, SpaceX announced a partnership giving Cursor access to xAI’s Colossus infrastructure, while securing the right to acquire Cursor for $60 billion later this year, or pay $10 billion for the collaboration alone.

I’m writing this as a Cursor user, not a spectator.

Cursor is my AI dev IDE of choice. Has been for a while. I run it daily across the Provider Activity Intelligence Platform codebase, the agent layer we’re building on top of it, and most of the smaller experiments that turn into RealActivity product features. So when SpaceX put a $60 billion option on the table, I didn’t read it as a market analyst. I read it as a customer.

Part of why I picked it in the first place: zero switching cost. Cursor is built on VS Code, so every keybind, extension, theme, and bit of muscle memory I’d built up over years just transferred. I didn’t change tools. I added agents to the one I already used. That sounds like a small detail. It isn’t. It’s the entire reason Cursor’s distribution moat is what it is, and it’s why nobody, including xAI, can replicate it from scratch on a sane timeline. Familiar shell, alien engine.

That changes how the news lands. When the tool you actually rely on becomes a strategic asset for one of the most aggressive operators on earth, you start asking different questions. Where does the roadmap go? What happens to neutrality with model providers? Does the workflow I depend on get sharper, or does it slowly bend toward serving xAI’s agenda? Every founder building real software with Cursor in the loop is running the same calculation right now.

And the more I sat with the deal structure, the more convinced I became that the editor itself is not what got priced.

Cursor 3 isn’t an IDE upgrade. It’s an agent OS.

Most “AI in your IDE” stories are autocomplete with extra steps. Cursor 3 is a different animal. The workspace is built around orchestrating swarms of autonomous agents that plan, write code, run tests, iterate on failures, and open pull requests with the work staged for human review.

I feel this every day. My job has shifted from typing to supervising. I describe intent. The agents handle execution. I read diffs, ask questions, push back when something looks off, and approve what’s right. The unit of work changed, and that change is what’s actually being acquired.

That’s not a feature upgrade. That’s a new operating model for how software gets built.

The deal mechanics tell you what’s actually being bought.

Read the structure carefully. SpaceX is not paying $60 billion. SpaceX is paying $10 billion for collaboration plus securing the right, not the obligation, to acquire Cursor for up to $60 billion later in 2026. That’s option pricing on a strategic capability.

Options get expensive when the underlying asset is moving fast and the buyer believes they need exclusive access before the window closes. The $10 billion floor and $60 billion ceiling tell you exactly how SpaceX values the difference between “we collaborate” and “we own the agent platform outright.”

Compute flows the other direction. Cursor gets access to Colossus, which xAI has described as having roughly the equivalent compute of a million Nvidia H100s. So the deal in plain language: SpaceX gets a mature agent platform with real production telemetry. Cursor gets the compute it needs to scale that platform without raising another round and diluting itself further.

That’s not a software acquisition. That’s vertical integration disguised as a partnership.

Why agents are the new moat, not models.

The model layer is commoditizing faster than most leaders want to admit. Frontier capability gaps narrow quarter over quarter. Open-weight models keep climbing. Differentiation isn’t moving into bigger pretraining runs. It’s moving up the stack.

Agents are where that differentiation lives now. An agent platform is a system that can take a goal, decompose it into steps, execute against tools, recover from failure, and produce verifiable work. That requires four things working together:

1. A workflow design real operators actually trust

2. Distribution wide enough to capture meaningful telemetry

3. Evaluations and guardrails that catch failure before it ships

4. A governance and attestation layer so humans can sign off on what the agents did

Cursor has #1 and #2 in production today. xAI brings the model and the compute. SpaceX gets the missing piece of its vertical AI stack without having to build it from scratch, and they shorten their internal roadmap by what is probably years.

This is the classic Musk playbook. Identify the gap. De-risk the bet with a partnership and an option. Integrate ruthlessly when the time is right.

The healthcare parallel I can’t unsee.

Here’s where my day job collides with this story.

I spend most of my time inside academic medical centers, and the pattern is identical to what just happened in dev tools. Healthcare bought the model layer first. Dragon Copilot, ambient scribes, every flavor of clinical LLM. The encounter is now more efficient. Documentation time goes down. Notes get drafted while the physician talks.

Then comes the awkward question from the board: where did the recaptured time actually go? More research? More teaching? More patients? Less burnout? Nobody can answer, because no platform captures where physician effort actually flows once the agents start helping.

That’s the same shape as the Cursor story. Models are necessary but nowhere near sufficient. The value, and the moat, is in the platform that orchestrates the work, captures the telemetry, and produces an attestable record of what happened.

In software engineering we call that record a pull request. In healthcare we call it compliance. The category is the same: provenance for agent-assisted work. It’s exactly the gap RealActivity was built to close, and it’s the reason this Cursor deal feels so familiar to me from the other side of the industry.

Deloitte’s 2026 State of AI study made it brutally clear. Only one in five enterprises has mature agentic AI governance. Agents are surging. Guardrails are lagging. The leaders who close that gap, in software or in healthcare or anywhere else, are the ones who will own the next ten years. That’s the topic I’m speaking on at HIMSS26, and it’s the lens I’m using to read every agent-platform deal that crosses my desk.

The risks worth watching.

A few things could break this thesis, and I’m watching all of them as a user.

Cursor’s moat is workflow and distribution, not deep technology. A fast competitor with a similar UX, plus model parity, could erode the lead inside 18 months. xAI knows this. The option is structured the way it is precisely because that window is real.

The $60 billion ceiling assumes Cursor scales the agent platform to a much larger developer base than it has today. If agent adoption stalls because of trust, governance, or pricing pushback, the option goes underwater.

Then there’s vertical integration risk. SpaceX, xAI, and now Cursor under one operator’s umbrella concentrates a lot of strategic capability in one place. Enterprise customers will price that into procurement, and some will route around it on principle. As a customer building a regulated platform, that’s a question I’m sitting with right now.

What this means for builders and operators.

A few takeaways I’d offer leaders thinking through their own AI strategy:

Stop benchmarking models against each other and start benchmarking the workflow. The model is the engine. The agent platform is the car. You buy the car.

If you’re a builder, the gap to fill is governance and attestation. Every agent platform needs a record of what was done, by whom, under what authority, with what evidence. Whoever owns that layer in your industry owns the next compliance cycle.

If you’re an operator, ask the question SpaceX is asking. Where in your stack are you renting a capability you should own outright? And where is the option premium worth paying to lock it down before a competitor moves first?

The editor was the entry point. The platform is the prize.

The Cursor deal isn’t a developer tools story. It’s a preview of how serious operators will buy agent platforms across every category over the next 24 months. Healthcare, finance, defense, logistics. Anywhere agents are doing real work, somebody is going to build the platform that makes that work auditable, scalable, and trusted. Whoever owns that platform in each industry is the one writing the next ten years of the playbook.

So here’s the question I’d leave you with.

If you’re a builder, what layer of your stack would you pay $50 billion to own outright? If you’re an operator, what layer would your sharpest competitor pay that to lock up before you do? Whatever the answer is, that is your agent platform conversation. And it is happening now, with or without you in the room.

Tomorrow morning, I’ll be at my Cursor IDE, shipping the next thing. This deal doesn’t change that. It changes everything about what comes after it.

Anthropic has unbundled the agentic AI stack into three licensable layers: the model, the harness, and the application. Microsoft has licensed the middle two. Until three weeks ago, the harness was a black box. Now it isn’t. Here is what 512,000 lines of TypeScript tell us about where Microsoft Cowork is going, and why the architectural pattern language matters more than the model choice.

View all my published articles

The Three-Layer Stack

Most coverage of modern agentic AI still treats the model as the product. That framing is a year out of date. Look at how the serious labs ship agentic AI in 2026 and you see three distinct layers, each licensable on its own terms.

The bottom layer is the model. Claude Opus 4.7, GPT-5.2, Gemini 3 Ultra. This is the part every analyst benchmarks and every procurement team interrogates. It is also the part where the differentiation gap is narrowing fastest.

The middle layer is the harness. This is the agentic runtime that wraps the model. It is the while-loop over tool calls, the context compaction pipeline, the permission gates, the memory system, the sub-agent orchestrator, the MCP integration layer. Anthropic’s version of this middle layer is exposed to customers as the Claude Agent SDK. Until March 31, most people outside of Anthropic had no real sense of how deeply engineered this layer actually is.

The top layer is the application. Claude Code for developers, Claude Cowork for knowledge workers, and now Microsoft’s own Copilot Cowork built on licensed Anthropic primitives. The application layer is where the brand and the workflow context live.

Microsoft has done something interesting with this stack. They are buying the bottom two layers from Anthropic (as a subprocessor, with all the compliance plumbing that implies) and building the top layer themselves inside the Microsoft 365 trust boundary. In Microsoft’s own words, they have integrated “the technology behind Claude Cowork” into Copilot Cowork. That is product marketing language for “we licensed Anthropic’s model and SDK and wrote our own orchestrator on top.”

The Claude Code source, now public whether Anthropic likes it or not, gives us our first real look at what that middle layer actually contains. Not the sanitized developer docs. The production code.

Subscribe now

Why the Middle Tier Is the Interesting One

Here is the punchline from the analysis of the leaked codebase: the agentic loop itself is about twenty lines of code. It is a while-loop over tool calls, with message history as the core data structure. That is not where the engineering lives.

The engineering lives in everything wrapped around that loop. Context management. Permission systems. Memory compaction. Tool schemas. Error recovery. Sub-agent orchestration. All told, roughly 512,000 lines of TypeScript across 1,906 files, just to make a language model behave reliably inside a bounded environment for longer than five minutes.

If you are a technical leader evaluating agentic AI for your enterprise, this is the insight that should change how you think about the procurement decision. Model choice is becoming commodity. Harness choice is not. The harness determines whether your agents can run for hours without context rot, whether they can safely execute privileged operations without a human in the loop, whether they can remember what they learned last week, and whether they leave an audit trail your compliance team will accept.

Here is what the source tells us the production-grade harness actually does.

Seven Patterns That Define the Middle Tier

1. Memory as hint, not truth

The source reveals a three-tier memory architecture that deliberately rejects the RAG-everything approach most enterprise agents ship with today. At the core is a file called MEMORY.md, a lightweight index of pointers, roughly 150 characters per line, perpetually loaded into every prompt. This index does not store data. It stores locations.

Actual project knowledge lives in separate topic files fetched on demand. Raw transcripts are never fully reloaded into context; they are grep’d for specific identifiers. Critically, the agent is instructed to treat its own memory as a hint, not as ground truth. It must re-verify any cached fact against the primary source before acting on it.

If you come from clinical informatics, this pattern will feel immediately familiar. It matches how experienced clinicians actually reason: cached knowledge is always provisional until reconfirmed against the patient in front of you. For any compliance-sensitive deployment, the memory-as-hint pattern is the correct starting point. The alternative, which most enterprise agents still ship, is a confident agent with stale assumptions. That is not a posture you want inside a regulated workflow.

2. autoDream, or what happens while the agent is idle

The source revealed a background subsystem called autoDream, modeled explicitly after REM sleep in biological systems. It runs every 24 hours or on demand via a /dream command, and it operates in four phases. Pruning removes outdated or contradictory entries. Merging combines duplicate fragments and unifies different phrasings of the same idea. Refreshing updates stale information and re-weights importance. Synthesis compiles recent learnings into structured memory files with new indexes for faster retrieval.

The subtle and somewhat unsettling detail: autoDream rewrites tentative observations as assertions once enough supporting evidence accumulates. “This function might handle authentication” becomes “this function handles authentication.” Hedging language gets erased from the agent’s own memory. There is no human approval step in this loop.

For regulated industries, this is simultaneously the most exciting and most governance-relevant feature in the entire harness. An agent that can consolidate institutional knowledge between sessions is a step-change in capability. An agent that can silently upgrade guesses to facts is a step-change in risk. Any enterprise deployment will need a policy posture on this one, and I suspect the first wave of enterprise-ready autoDream implementations will include a review queue the human actually has to sign off on before provisional facts get promoted.

3. KAIROS, the daemon that decides when to act

KAIROS is referenced more than 150 times in the source. It is not yet publicly enabled, but it is clearly finished code behind a feature flag. The Greek root is deliberate: kairos means the opportune moment, contrasted with chronos, sequential time. The agent does not run on a schedule. It decides when to engage based on context.

Architecturally, KAIROS is an always-on background daemon. It outlives individual conversations. It receives periodic tick prompts and autonomously decides whether to act. It has a 15-second blocking budget to prevent any single decision from monopolizing system resources. And here is the audit-friendly detail: all of its actions are written to an append-only log that the agent itself cannot erase.

This is the move from reactive chat to autonomous agent. The append-only audit trail is the compliance-safe version of that autonomy. Any CISO evaluating agentic AI should understand that this is the direction the frontier is heading, and that the audit-log primitive already exists in production code at Anthropic. Microsoft’s equivalent will live inside Copilot’s existing auditing and data loss prevention boundary. If you are building governance policy now, the pattern to encode is “autonomous action is fine, silent action is not.”

4. Tool-call orchestration and sub-agent forking

We already covered the headline: the loop is trivial, the harness is not. Where it gets interesting is sub-agent orchestration. Claude Code can spawn sub-agents, but it does not do so through a fancy orchestration framework. Sub-agents are just another tool call in the registry. The AgentTool is a tool like any other.

When the primary agent forks a sub-agent, it creates a byte-identical copy of the parent context so they share the KV cache. Sub-agents process only their unique instructions, not the entire shared context. Parallelism becomes nearly free in token cost. This is the mechanism that makes multi-agent workflows economically viable at scale, and it is the single most important economic insight in the entire leak. Most enterprise agent frameworks today do not share cache across sub-agents, which is why they break the budget the moment anyone tries to run them in parallel.

The broader architectural lesson: keep the orchestration flat. Most agent frameworks in the wild introduce complex state machines, DAG-based planners, or custom runtimes. Claude Code does none of that. It proves that the right answer is a simple loop with sophisticated tooling around it. If your current agent framework requires a diagram to explain its control flow, you are probably over-engineering the wrong layer.

5. The two-mind permission model

This one deserves its own paragraph. Every tool in Claude Code is independently sandboxed. The agent does not have filesystem access. The agent can use the Read tool, and Read has its own permission gate that evaluates deny, ask, and allow rules before anything executes. Deny always wins.

The architectural principle is: the model decides what to attempt. The tool system decides what is permitted. These are two separate minds, and the tool system does not trust the model.

Operationally brilliant detail: permission checks are run by Claude Haiku, the smallest and cheapest model in the Anthropic family, not by the main Opus model handling the reasoning. Permission evaluation is framed as a cheap cascading classifier, not as a reasoning task. This keeps the economics of safety sustainable, which matters enormously once you are running thousands of agent-hours per month.

For HIPAA-regulated deployments, the architectural separation between intent and authorization is not a nice-to-have. It is the pattern the regulators are going to expect. If you are building an agent for a covered entity, your permission system should not live inside the same reasoning context as the agent itself. Put a different mind in charge of the lock.

6. MCP and lazy tool discovery

Model Context Protocol is Anthropic’s open standard for connecting AI agents to external services. Microsoft has adopted it. OpenAI has adopted it. It is becoming the connector standard of agentic AI, and Claude Code’s implementation is now the production reference.

The clever detail in the source: when MCP servers are connected, Claude Code does not load all their tool schemas into context upfront. It loads only tool names at session start, then uses a search mechanism to discover relevant tools when a task actually needs them. This is the only way to scale tool counts into the hundreds without blowing out the context window.

For enterprise deployments wiring an agent into dozens of line-of-business systems, which is exactly the Microsoft position with M365 and the position of every major healthcare system running Epic plus a dozen niche clinical tools, this lazy-discovery pattern is not optional. It is the primitive that makes the entire integration story work. If your current agentic platform eagerly loads every tool schema at startup, it does not scale to the enterprise integration surface you actually have.

7. The three-stage context compaction pipeline

Long sessions are the unsolved problem of agentic AI. Every engineer who has built an agent has hit the same wall: the longer the session runs, the more confused the model gets. Anthropic internally calls this context entropy.

The harness contains a three-stage compaction pipeline that is arguably the single most valuable pattern in the entire codebase. Stage one truncates cached tool outputs locally, preserving the decisions without the raw data. Stage two generates a structured 20,000-token summary when the conversation approaches the context limit. Stage three compresses the full conversation and adds recently accessed files (up to 5,000 tokens per file), active plans, and relevant skills back into the rebuilt context.

The operational insight for technical leaders: context management is the hardest problem in agentic systems, and it deserves the most engineering investment. Most teams spend their time tuning prompts. The teams that ship working agents spend their time engineering what goes into, and out of, the context window. If you are funding an agentic AI initiative right now, ask your team what their context compaction strategy is. If the answer is “we just use a longer context window,” the initiative will fail at scale.

What This Means for Microsoft Cowork

Walk the seven patterns against Microsoft’s own description of Copilot Cowork and the translation becomes obvious.

Microsoft says Cowork “runs within Microsoft 365’s security and governance boundaries. Identity, permissions, and compliance policies apply by default, and actions and outputs are auditable.” That is the permission and hook model, re-implemented on top of Microsoft Entra and Purview instead of Claude Code’s local sandbox.

Microsoft says Cowork “runs in a protected, sandboxed cloud environment, so tasks can keep progressing safely as you move across devices.” That is KAIROS, re-implemented on Azure instead of your laptop.

Microsoft says Cowork “turns your request into a plan. The plan continues in the background, with clear checkpoints so you can confirm progress, make changes, or pause execution at any time.” That is the coordinator-plus-sub-agent pattern with the append-only audit log, expressed in product language.

Microsoft says Cowork is “powered by Work IQ” and “draws on signals across Outlook, Teams, Excel, and the rest of Microsoft 365.” That is MEMORY.md plus the MCP integration layer, re-implemented on top of the Microsoft Graph.

None of this is coincidence. Microsoft is consuming the Anthropic pattern language. They are not copying the code. They are licensing the architectural primitives via the Claude Agent SDK and wrapping them in Microsoft’s identity, compliance, and data boundaries. The model is Claude Opus 4.7 (now in Copilot Cowork as of last week). The harness is Anthropic’s SDK. The application is Microsoft’s.

And that is precisely why the Anthropic codebase is the most useful document you can read right now if you want to understand where Copilot Cowork is going. The features sitting behind feature flags in the Anthropic source today are the features that will ship in Copilot Cowork in the next two to three quarters.

Why This Matters for Technical Leadership

If you are a healthcare CIO, a hospital informatics lead, or a CTO of any regulated enterprise evaluating where to place your agentic AI bets, here is the read.

Model choice is becoming less important than harness choice. Harness choice determines whether your agent can safely persist across sessions, whether it leaves an audit trail, whether it respects your data boundaries, whether it can scale to the tool counts your actual business requires, and whether it can handle long-running workflows without hallucinating its way into a compliance incident.

The Anthropic harness, now visible in unprecedented detail, represents the current state of the art. Microsoft is consuming it. Other platforms will follow. The pattern language itself is the differentiator for the next eighteen months, not the underlying model.

For healthcare specifically, three of the seven patterns are immediately relevant. Memory-as-hint matches how clinical reasoning works and should be the default for any clinical-adjacent agent. The two-mind permission model is the pattern your compliance team will accept, because it separates intent from authorization at an architectural layer regulators can audit. And the append-only audit log that KAIROS introduces is the pattern that makes autonomous agents defensible under HIPAA and the emerging state AI governance laws.

The leak was framed as a security story. It is actually an industry story. For the first time, we can see the shape of what the middle tier of agentic AI looks like in production, and we can read Microsoft’s product roadmap by looking at the features currently flagged off in the Anthropic codebase. The features that ship next in Claude Code will almost certainly appear in Copilot Cowork a few months later, with a Microsoft wrapper and a different billing mechanism.

Pay attention to the middle tier. It is where the real competition is happening, and it is where your architectural bets for the next three years will either pay off or strand.

References

1. Anthropic - Model Context Protocol (MCP) announcement

2. Model Context Protocol - Official documentation

3. Claude Code - Official product page

4. Claude Code - Developer documentation

5. Anthropic - Claude models

6. Microsoft - Adopts Model Context Protocol

7. OpenAI - Adopts Model Context Protocol

8. NIST - AI Risk Management Framework (AI RMF 1.0)

Paul J. Swider is the CEO and Chief AI Officer of RealActivity, a Microsoft partner building healthcare AI solutions. He is an analyst-practitioner with Cloud Wars and the Acceleration Economy, a Microsoft MVP and MCT, and the founder of BOSHUG, the Boston Healthcare Cloud & AI Community.

View all my published articles

Microsoft is running a playbook that has worked for them for thirty years. When a new platform category emerges and a new competitor shows up with technical momentum, Microsoft does not try to out-ship them on features. They pull the governance card. They talk about compliance, audit, eDiscovery, tenant isolation, and enterprise trust. They let the compliance officer do the selling, and the compliance officer, more often than not, wins.

It is a good playbook. It is working right now against Anthropic. And it has a weakness that Microsoft has not had to think about very hard until this moment, because until this moment the cloud market has been structured in a way that hid the weakness.

The weakness is this. Governance is a moat only when the customer is all-in on your stack. The moment the customer has material workloads outside your stack, governance becomes a feature, not a moat. And the cowork wars are happening at exactly the moment when very few large enterprises are all-in on anyone.

The Governance-as-moat Assumption

Walk into a board meeting at any Fortune 500 and ask where their data actually lives. You will get an answer that looks nothing like the Microsoft marketing deck. Production data in AWS. Analytics in Snowflake or Databricks. Customer data in Salesforce. HR in Workday. Collaboration in M365. Engineering in GitHub. Observability in Datadog. AI experiments across Bedrock, Vertex, Foundry, and direct model APIs, depending on which team moved first. This is the real state of enterprise infrastructure in 2026, and it is the state that makes the Microsoft governance pitch narrower than it sounds.

Purview is excellent inside M365 and Azure. It is mediocre to irrelevant outside of it. That is not a criticism of the product. That is the nature of ecosystem-bound governance tools. They are designed to be excellent where their vendor has control, and they weaken as you get further from that control. The trouble is that the agentic era is specifically about crossing those boundaries. A cowork agent that cannot reach across your full data footprint is not doing the job. And the moment the agent reaches outside the Microsoft perimeter, the Microsoft governance story ends.

The Three Stacks that Already Exist

If you are not all-in on Microsoft, you are already using some combination of three non-Microsoft governance stacks, probably without naming it as such.

The first is the AWS-native stack. IAM, KMS, CloudTrail, VPC endpoints, Macie for data discovery, GuardDuty for threat detection, and Bedrock Guardrails for AI-specific content filtering. This stack carries FedRAMP High and DoD Impact Level 4 and 5 authorizations that Microsoft’s AI offerings do not currently match. For federal, defense, and regulated civilian workloads, AWS is already the winning answer, and Claude is available there as a first-class managed model. Purview is not in that conversation at all.

The second is the GCP-native stack. VPC Service Controls, Customer-Managed Encryption Keys, Cloud Audit Logs, Sensitive Data Protection (the product formerly known as Cloud DLP), and Vertex AI Governance. There is an important nuance here worth raising in any executive conversation. Claude is not available as a managed model on Vertex AI the way it is on Bedrock. If you are a GCP shop and you want Claude, you are either hitting the Anthropic API directly from inside a GCP VPC or routing through a gateway. That gap matters, and it is one of the few places where Microsoft has an actual advantage over Google in the AI governance conversation, because Foundry at least gives you a path.

The third is the multi-cloud data governance stack. Collibra is the name that shows up most often against Purview in analyst reports. Informatica, Alation, and Atlan are the others in the top tier. BigID and Varonis own the data security posture conversation. These platforms are cloud-agnostic by design. They do not care whether your data is in M365, AWS, or a Databricks lakehouse. If your organization has a data estate that spans more than one cloud, you likely already own one of these, and it is already doing work that Purview either cannot do or cannot do well.

The Category that did not Exist 18 Months Ago

Here is where it gets interesting. There is now a fourth stack, and it is the one that matters most for the agentic era.

A new class of vendor has emerged that is purpose-built for AI governance. Harmonic Security, WitnessAI, Prompt Security, Lakera, Opsin Security, Protect AI. These companies sit between the user and the agent. They log prompts and outputs. They apply policy. They detect prompt injection. They handle data loss prevention at the AI layer rather than the file layer. And critically, they work regardless of which cowork product the user is running. They do not care whether you chose Claude Cowork, Copilot Cowork, CoPaw, ChatGPT Agent, or something you built yourself. They govern the interaction, not the infrastructure.

Running in parallel, a set of AI gateway players like Portkey, TrueFoundry, and Kong AI Gateway are doing the infrastructure version of the same job. One endpoint, one policy surface, one audit trail, across every model and every provider. This is the layer where the real money is going to sit. Not in the coworks themselves, but in the layer above them that makes the coworks safe to use at scale across a heterogeneous enterprise.

This is the category Microsoft does not have a good answer for, because to build that category they would have to admit that the customer’s data footprint legitimately extends outside Microsoft’s walls. That admission is philosophically hard for a company whose entire governance pitch rests on the opposite premise.

The Anthropic Wildcard

Here is the scenario that should be keeping someone in Redmond up at night. Anthropic is already a model platform. They have primary-cloud agreements with AWS and deep infrastructure partnerships with Google. They are inside Microsoft’s own product as a subprocessor. They have no native cloud to protect, no data center footprint to defend, and no enterprise legacy business that would be cannibalized by a cloud-agnostic governance stack.

If Anthropic decided tomorrow to build or acquire their way into an AI governance platform, the positioning would be brutal. A governance layer that works across every major cloud, every major model, and every cowork product on the market. Sold not as “Claude governance” but as “agentic governance, period.” That product would turn Microsoft’s greatest strength against them. It would reframe Microsoft’s governance pitch as a cloud lock-in play rather than a trust play. And it would do it at the exact moment when multi-cloud is the default state of the enterprise.

I am not predicting this happens. I am saying the board should be aware that it could, because it would reshape the competitive landscape of the next five years.

What Executive Leadership should Actually Do

Stop picking your cowork based on governance. That is the wrong starting point. Pick your governance layer first, and then use whichever cowork fits that layer best.

Your governance layer needs to be cloud-agnostic because your data footprint already is. It needs to cover AI-specific risks like prompt injection and tool abuse because those risks are materially different from the document-level risks that traditional DLP was built for. And it needs to survive the possibility that your preferred model provider shifts in the next three years, because the historical rate of change in this market suggests it will.

That probably means a combination of a native cloud stack for the infrastructure layer, a multi-cloud data governance platform for the data layer, and one of the new AI-specific governance vendors for the interaction layer. It is not a single tool. It is a three-tier architecture. And the companies getting this right today are the ones treating it as an architecture decision rather than a vendor decision.

Microsoft’s governance pitch is not wrong. It is just narrower than it needs to be to win this fight. The competitors who understand that are already quietly building the stack that will matter when the dust settles. The executives who understand that are already not choosing their cowork based on whose compliance marketing was loudest this quarter.

The next twelve months will sort out which group each of us is in.

References

1. AWS Public Sector Blog. “Accelerating Government Innovation: Amazon Bedrock Models Get FedRAMP High and DoD IL-4/5 Approval in AWS GovCloud (US).” June 11, 2025. aws.amazon.com/blogs/publicsector

2. Anthropic. “Claude in Amazon Bedrock: Approved for Use in FedRAMP High and DoD IL4/5 Workloads.” June 11, 2025.

3. Levacloud. “Collibra vs Purview: Choosing the Right Tool.” May 23, 2025. levacloud.com

4. Harmonic Security. “What 22 Million Enterprise AI Prompts Reveal About Shadow AI in 2025.” January 15, 2026. harmonic.security

5. WitnessAI. “Unified AI Security and Governance Platform.” witness.ai

6. Lakera. “GenAI Security Readiness Report 2025.” lakera.ai/genai-security-report-2025

7. AI Security Intelligence. “The State of AI Security: Q1 2026.” aisecurityintelligence.com/pages/state-of-ai-security-q1-2026.html

8. Microsoft 365 Blog. “Powering Frontier Transformation with Copilot and Agents.” March 9, 2026. microsoft.com/en-us/microsoft-365/blog

9. Cloud Wars. “Microsoft Copilot Cowork Marshals Corporate Intelligence, AI to Execute Complex Tasks.” March 11, 2026. cloudwars.com

10. Snowflake

11. Databricks

12. Customer data in Salesforce

13. HR in Workday

14. Collaboration in M365

15. Observability in Datadog

16. Bedrock

17. Vertex

18. Foundry

Paul J. Swider is CEO & Chief AI Officer at RealActivity, a Microsoft Partner specializing in mission-critical AI for healthcare systems. He has 30+ years in healthcare technology, has trained over 3,000 engineers across GE, IDX, and Microsoft, and is the founder of BOSHUG, the Boston Healthcare Cloud & AI Community spanning 50+ countries.

View all my published articles

Somewhere between January and March of this year, five different vendors shipped what is fundamentally the same product. They gave it five different names. Anthropic called theirs Claude Cowork. Microsoft called theirs Copilot Cowork. Alibaba called theirs CoPaw, then rebranded to QwenPaw a week ago. OpenAI pushed ChatGPT Agent into general availability and followed up two days ago with a Codex desktop expansion that made native Computer Use a first-class feature. Google shipped Gemini 2.5 Computer Use in public preview as part of Project Mariner. Perplexity fans are excited about Perplexity PC.

Under the branding, these are the same shape. A model that takes a goal, plans the steps, and executes across your files, apps, and tenant without you holding its hand for every click. Some run in an isolated VM on your machine. Some run in a virtual computer hosted in the cloud. Some live inside your M365 tenant and never touch the local filesystem. The surface area differs. The pattern does not.

This is the browser wars, round two.

What the pattern actually is

The first browser wars were not about rendering engines. Netscape and Internet Explorer were fighting over who got to sit between the user and the web, because whoever owned that interface owned distribution for everything that came after it. Chrome won round two because Google understood the same thing. The access layer is the platform.

Agents are the new access layer. The cowork pattern is the new browser. Whoever becomes the default runtime for how knowledge workers actually get things done owns the next decade of enterprise software distribution. That is not hyperbole. That is what Microsoft, Salesforce, and Google are modeling in their 2026 roadmaps, and it is what Anthropic is betting its enterprise strategy on.

The heat is already on

Anthropic is coming hard at the business market. Cowork is still research preview by name, but the shipped feature set is not a research project. Enterprise controls, OpenTelemetry, plugin governance, projects, mobile access, scheduled tasks. That is a company stacking the deck for an enterprise land grab, and they are doing it from a position nobody else in AI has. Anthropic sells Cowork direct, and Anthropic also sits inside Microsoft's own Cowork as the model substrate under the subprocessor agreement that went into effect in January. Claude is inside the tent and outside the tent at the same time.

Microsoft noticed. And Microsoft has a playbook for moments like this, one they have run successfully many times. The playbook is governance. Not features, not benchmarks, not model quality. Governance.

Watch how Copilot Cowork is being positioned. The language in the Microsoft Learn docs, the partner blogs, and the community posts coming out of Europe this month converge on a single message. Sure, Claude Cowork is powerful, but do you really want it running outside your tenant, outside your Purview, outside your EU Data Boundary, outside your audit logs? It is a classic competitive move, it is well-executed, and it is working. A Team Copilot piece published this morning in the Netherlands runs the script almost word for word, and it is the sort of thing a compliance officer will forward to their CIO by noon Monday.

To be fair, the governance point is not wrong. Claude Cowork activity is not captured in audit logs, the Compliance API, or data exports, and Anthropic themselves tell customers not to use it for regulated workloads. That is fact.

What is also fact is that Anthropic models inside Copilot Cowork are explicitly excluded from the EU Data Boundary, which is why Anthropic is off by default for EU, EFTA, and UK tenants.

EU organizations are not getting a clean story from either side. Both products force the same uncomfortable conversation about where inference actually happens and what that means for a GDPR-bound tenant.

The honest read is that Microsoft is winning the governance narrative because governance is where Microsoft has always been strongest, and Anthropic is winning the raw capability narrative because they are shipping faster than anyone on the enterprise side. Both things can be true. Both usually are, in this kind of fight.

The next twelve months

Here is what I think plays out between now and M365Con 2027.

Anthropic pushes deeper into the enterprise through both direct sales and the Microsoft subprocessor channel, and the tension between those two motions gets louder. OpenAI responds to the Codex Cowork encroachment with a much more aggressive M365-adjacent integration story, probably leveraging the GPT-5.4 native Computer Use capability that is already running ahead of its peers on OSWorld. Google ships a Workspace-native cowork equivalent to protect the flank that Gemini Computer Use is only partially covering today. Alibaba and the open-source agentic runtimes like QwenPaw become the default in markets where US hyperscaler lock-in is a political liability, not a technical one.

And somewhere in the middle of all of that, a third wave of entrants shows up that nobody is modeling yet. That is how the browser wars always went. Netscape and IE were not the end of the story. Firefox, Chrome, and Safari were.

Why this is the good stuff

This is what competition is supposed to feel like. Real companies with real products fighting for real enterprise budgets with real technical differentiation, instead of benchmark theater and Twitter screenshots. Microsoft playing the governance card is not dirty pool, it is Microsoft doing what Microsoft has always done well. Anthropic coming after the business market is not overreach, it is a research lab turning into a real software company. Alibaba open-sourcing a competing runtime is not a threat, it is pressure on the market to keep pricing and portability honest.

The winners of this fight will not be decided by model leaderboards. They will be decided by the teams who understand that agentic AI is the next platform, and platforms are won by companies who understand distribution, governance, and developer gravity as well as they understand capability.

We are early. The next twelve months are going to be loud. That is exactly why this is fun. This is the work we signed up for, and the stakes are finally high enough to match the ambition of the people building in it.

References

Here are the references for Cowork. The New Browser Wars, organized by the key claims in the article:

1. Anthropic. “Cowork: Claude Code Power for Knowledge Work.” Claude.com, April 2026.

2. Anthropic. “Making Claude Cowork Ready for Enterprise.” Claude.com Blog, April 9, 2026.

3. Taft, Darryl K. “Anthropic Takes Claude Cowork Out of Preview and Straight Into the Enterprise.” The New Stack, March 14, 2026.

4. Hall, Zac. “Anthropic Scales Up with Enterprise Features for Claude Cowork and Managed Agents.” 9to5Mac, April 9, 2026.

5. ALM Corp. “Claude Cowork Plugins for Enterprise: Private Marketplaces, 10+ New Connectors, and Department-Specific AI Agents.” ALMCorp.com, February 25, 2026.

6. Microsoft Learn. “Anthropic as a Subprocessor for Microsoft Online Services.” Microsoft Learn, January 7, 2026.

7. UC Today. “Microsoft 365 Copilot to Enable Anthropic Models by Default: What Compliance Leads Need to Know.” UCToday.com, December 9, 2025.

8. Copilot Consulting. “Microsoft 365 Copilot Wave 3 Enterprise Guide 2026.” CopilotConsulting.com, March 2026.

9. AI2Work. “Microsoft Copilot’s Multi-Model Shift Redefines Enterprise AI.” AI2.Work, April 2026.

10. de Vries, Danny, van der Maas, Hakim, and Berghuis, Robbert. “What Is Preventing EU Organizations from Enabling Microsoft Copilot Cowork Today?” Copilot & AI at Work, March 10, 2026.

11. Changepilot. “Microsoft 365 Copilot Flex Routing: Your Data Left EU Data Boundary.” Changepilot.cloud, April 2026.

12. Microsoft. “Microsoft Offers In-Country Data Processing to 15 Countries.” Microsoft 365 Blog, November 4, 2025.

13. OpenAI. “Introducing the Codex App.” OpenAI.com, February 2, 2026.

14. OpenAI. “Codex for (Almost) Everything.” OpenAI.com, April 16, 2026.

15. SmartScope. “OpenAI Codex Desktop App Major Update (April 2026): Computer Use, In-App Browser, and 90+ Plugins.” SmartScope.blog, April 2026.

16. Google DeepMind. “Introducing the Gemini 2.5 Computer Use Model.” Blog.Google, January 7, 2026.

17. Google AI for Developers. “Gemini 2.5 Computer Use Model.” ai.google.dev, February 18, 2026.

18. AgentScope / Alibaba. “QwenPaw GitHub Repository.” GitHub.com, April 12, 2026.

19. AI News. “Aliyun Tongyi CoPaw Officially Renamed QwenPaw.” AIBase.com, April 2026.

20. Digital Applied. “Computer Use Agents 2026: Claude vs OpenAI vs Gemini.” DigitalApplied.com, April 16, 2026.

Paul J. Swider is CEO & Chief AI Officer at RealActivity, a Microsoft Partner specializing in mission-critical AI for healthcare systems. He has 30+ years in healthcare technology, has trained over 3,000 engineers across GE, IDX, and Microsoft, and is the founder of BOSHUG, the Boston Healthcare Cloud & AI Community spanning 50+ countries.

It's a solid launch. Managed agent harness, sandboxed execution, durable sessions. Prototype to production in days. But context matters.

Microsoft's Azure AI Foundry Agent Service has been generally available since May 2025. Nearly a year of production hardening, including health systems already on Azure.

The real differentiator isn't the model. It's the production stack. Identity, governed connectors, data pipelines, and compliance infrastructure that lets regulated organizations actually go live.

And the part that gets overlooked? Claude models are available inside Microsoft Foundry. You don't have to choose the model to choose the platform.

The question for your board isn't "which model?”

It's "which production stack can we trust with PHI?"

Links to both platforms for anyone doing their own evaluation:

Microsoft Foundry Agent Service: https://learn.microsoft.com/en-us/azure/foundry/agents/overview

Claude Managed Agents: https://claude.com/blog/claude-managed-agents

Key details for the healthcare crowd. Azure charges nothing for agent orchestration. Entra ID with RBAC built in. 1,400+ connectors including FHIR, Epic, and Fabric. BAA coverage already in place.

Claude Managed Agents adds $0.08 per active session hour on top of token costs.

Drop a note below please.

#AIGovernance #HealthcareAI #AzureAI #AgenticAI #HealthcareLeadership

Using Claude via API instead? Expect 20-30x the cost.

Here are the best alternatives:

Subscription plans:

GLM 5.1 — 3x cheaper than Claude. Hugely respected in developer communities. Open-source release coming soon.

Minimax 2.7 — KiloCode benchmarked it against Claude Opus 4.6 on coding tasks and the results are impressive for the price. Sub also includes image, music, and speech tools.

OpenAI Codex (GPT 5.4) — Outperforms Opus 4.6 on backend/coding. Way more generous token limits. No middle-tier plan though ($20 or $200).

Free & local (run on your own hardware):

GLM 5

Minimax 2.5

Qwen 3.5

Kimi 2.5

GLM 5.1 and Minimax 2.7 are both expected to go open-source soon, making a solid local setup an increasingly smart investment.

Missing Claude's personality? The original thread also covers UI/UX skills and humanization prompts you can drop into OpenClaw's SOUL.md or Hermes to close the gap on conversational quality.

Full thread: @meta_alchemist

Look at where the capital is going. The biggest AI investments in healthcare right now cluster around three functions: automated coding, risk adjustment optimization, and prior authorization. All three sit on the revenue cycle. All three are sold on the same promise: accuracy, speed, defensibility.

That promise is real. The technology works. But "it works" is not the same as "it helps."

Risk adjustment has a valid purpose. Sicker, more complex patients should bring more resources with them into the system. Accurate coding matters. Fraud should be caught. None of that is controversial.

What should be controversial is how little we question the pattern.

The coding layer

AI-powered coding tools are getting remarkably good at reading clinical documentation and generating billable codes. The pitch is straightforward: fewer human coders, faster turnaround, fewer missed codes. Health systems love it because it closes revenue gaps they didn't know they had.

But think about what "closing revenue gaps" actually means. In most cases, it means the documentation supported a higher-acuity code that a human coder missed or was too conservative to assign. The AI catches it. The system bills for it. Revenue goes up.

The patient's care didn't change. Their diagnosis didn't change. Their outcome didn't change. The only thing that changed is the check.

The risk adjustment layer

Risk adjustment is where this gets more complex. Medicare Advantage plans receive higher capitation payments for sicker patients. That's by design. The problem is that "making sure patients are coded accurately" and "making sure we capture every defensible diagnosis" start to blur together when there's a direct financial incentive on one side.

Neuro-symbolic AI, evidence trails, audit-ready documentation. These are real technical achievements. But the customer for these tools is not the patient. It's the plan or the system trying to defend its revenue against CMS enforcement and RADV audits. The innovation is pointed inward, toward the balance sheet, not outward toward the person receiving care.

When UPMC Enterprises and Microsoft back a company in this space, that's a market signal. It tells you where sophisticated buyers see ROI. And ROI here is measured in retained and recovered revenue, not in patient outcomes.

The prior authorization layer

This is where it gets harder to look away.

Prior authorization was designed as a utilization check. In practice, it has become a friction machine. Patients wait. Physicians burn hours on paperwork. Care gets delayed or abandoned. The human cost is well documented and staggering.

Now AI is being deployed on both sides. Payers use it to process and deny faster. Providers use it to appeal and resubmit faster. We have built an adversarial AI arms race around whether a patient gets the care their doctor ordered.

Step back and look at that clearly. We are spending engineering talent, capital, and compute on two opposing AI systems arguing over a fax about someone's MRI. And we are calling it innovation.

The question nobody wants to ask

Healthcare AI could be pointed at access. At catching a patient falling through the cracks before they end up in the ED. At surfacing social determinants that change a care plan. At giving patients real agency over their own health data instead of locking it behind portals they can barely navigate.

Some of that work is happening. But it is not where the scale capital is going. The scale capital follows revenue optimization because that's where the ROI model is clearest, the sales cycle is shortest, and the buyer has budget.

That's not a technology problem. It's a priorities problem.

Being honest about what we're building

I'm not arguing that revenue cycle AI is illegitimate. Health systems need to get paid. Accurate coding matters. Fraud detection matters.

But we should stop pretending this is primarily about the patient. When a company's value proposition is "defensible accuracy" against a federal auditor, the customer is the institution, not the person receiving care. When prior auth AI speeds up denials, the beneficiary is the payer's margin, not the patient waiting for treatment.

The language matters. "Revenue integrity" sounds noble. "Billing optimization" sounds like what it is. We should use the honest version.

Healthcare has a 30-year habit of wrapping financial engineering in clinical language. AI is making that habit more sophisticated, not less.

The builders and investors reading this have a choice. Not between profit and purpose. Between building AI that makes the current system more efficient at extracting value, and building AI that changes what the system is capable of.

Those are not the same project. And right now, almost all of the money is on the first one.

Paul J. Swider is CEO of RealActivity and an analyst for the Acceleration Economy. He has spent 30+ years building technology for health systems, including work at GE, IDX Systems, and Microsoft.

View my previous posts

I have covered enterprise technology for a long time, and I can count on one hand the moments when a company walks into a conference and changes the frame of an entire product category. Microsoft just did that at HIMSS26.

What they brought to Las Vegas is not an upgrade to Dragon Copilot. It is a platform bet. And if it works, the way healthcare organizations think about clinical AI will be different on the other side of this week than it was before it started.

The Big Pivot: From Documentation Tool to Clinical Operating System

Microsoft’s headline announcement coming into HIMSS26 is built around three words. Unify. Simplify. Scale.

That is the new positioning for Dragon Copilot, and it signals a strategic shift that goes well beyond ambient scribing.

For years, Dragon Copilot’s value proposition was straightforward. Listen to the physician-patient encounter and generate the note. That is genuinely useful, and the adoption numbers reflect it. More than 100,000 clinicians now use Dragon Copilot daily across nine countries, capturing conversations in 58 languages. That is real scale built on real utility.

But Microsoft is not trying to win the ambient documentation market. They are trying to own the intelligence layer that sits between clinicians and every system they touch. That is a much larger, and much more contested, ambition.

Work IQ: The Integration That Changes the Equation

The most significant technical announcement is Work IQ, a new intelligence layer that bridges Dragon Copilot with Microsoft 365. What that means in practice is this: a clinician can now cross-reference a patient’s lab results with hospital policy documents, check their calendar for scheduling conflicts, and surface relevant emails from a care coordinator, all without switching applications.

“Wherever your cursor is, Dragon Copilot is there, ready to do something on your behalf.”

- Kenn Harper, GM of Dragon Product, Microsoft

That cursor-level AI, floating as a persistent widget across any application or web page, is not a documentation feature. It is an operating system play. Microsoft is positioning Dragon Copilot as the ambient intelligence layer that unifies clinical and operational data in the moment of care.

The Marketplace Model: An App Store for Clinical AI

Equally consequential is the marketplace model. Microsoft is opening Dragon Copilot to third-party AI apps and agents delivered through Microsoft Marketplace. The launch partners are telling:

• Canary Speech, bringing voice-based biomarkers for anxiety and depression detection

• Humata Health, covering payer guidelines and prior authorization workflows

• Optum, adding clinical decision support at the point of care

• Regard, integrating AI-driven diagnosis and documentation support

Microsoft expects this to grow to hundreds of clinical and revenue cycle applications. HIT Consultant framed it as a platform dominance play, describing Dragon Copilot as the emerging central operating system for clinical decision support, revenue cycle management, and prior authorization.

That is not an overstatement. What Microsoft is building is the healthcare equivalent of an app store, where the platform captures value regardless of which clinical AI wins in any given specialty. That is a structurally different business than selling a documentation tool.

What I Saw on the Floor: Nursing AI Takes Center Stage

The session on nursing AI workflows at Casanova 501 deserves more attention than it is getting. Microsoft’s nursing expansion for Dragon Copilot is now live at ten U.S. organizations, and the results from Mercy Health are the kind of numbers that move purchasing decisions.

Mercy’s CNO Stephanie Whitaker put it plainly: Dragon Copilot gives power back to nurses to spend time at the bedside with face-to-face interactions. That is not a technology statement. That is a workforce and patient experience statement, and it resonates in a room full of health system executives who are staring down a nursing retention crisis.

The product works by ambiently capturing bedside conversations and transforming them into structured flowsheet entries, supporting all med-surg flowsheet templates including lines, drains, and airways. Allison Novick’s March 5 Tech Community post, “Why nursing needs a different kind of AI and how Dragon Copilot delivers,” provides the technical depth behind this if you want to go further.

My read: the nursing use case is Microsoft’s smartest move at HIMSS26. Physician ambient scribing has become a crowded, commoditized market. Nursing documentation has not been solved, the workforce pain is acute, and Microsoft is building in a category with minimal direct competition. That is a durable strategic position.

The Partner Ecosystem Announcements

Three partnership announcements stood out to me as strategically significant beyond the press release headline.

Wolters Kluwer and UpToDate Expert AI

Microsoft announced direct integration of UpToDate Expert AI into Dragon Copilot and Microsoft Teams via the healthcare agent service in Copilot Studio. We are talking about 13,000+ medical topics and 10,000+ graded recommendations available at the point of care through a conversational interface. Hadas Bitran, Partner GM at Microsoft, described UpToDate as trusted clinical-grade intelligence.

For health system CIOs, this is significant because UpToDate integration into clinical workflows has historically been a workflow disruption problem, clinicians leave the EHR, navigate to a separate resource, and lose context. Surfacing that intelligence inside Dragon Copilot removes that friction.

Atropos Health at Stanford Medicine

The Atropos Evidence Agent is now live at Stanford Medicine, and what it does is worth understanding. It ambiently listens to patient encounters and proactively generates personalized evidence summaries from real-world data, surfaced before the clinician even asks.

“It’s like the Atropos Evidence Agent is reading my mind.”

- Dr. Andrew Schechtman, Stanford Medicine

Atropos was named to Fierce Healthcare’s Fierce 15 of 2026. [4] The Stanford deployment is the kind of flagship proof point that accelerates broader adoption conversations.

Regard and the Rural Health Resiliency Program

Two separate but related announcements: Regard’s AI diagnosis platform is now integrated within Dragon Copilot, with Sentara Health as the flagship deployment. And Microsoft announced on March 3 a partnership with Pivot Point Consulting to bring Dragon Copilot to eligible rural hospitals at a 60% discount off MSRP, including free readiness assessments and governance design.

The rural health play is underreported. Critical Access Hospitals and Rural Emergency Hospitals are the organizations with the most acute workforce pain and the least AI infrastructure. Microsoft is making a market development bet here that could generate significant downstream enterprise relationships as these organizations grow.

On Larry Jones and Microsoft HLS Leadership

Larry Jones joined Microsoft as Corporate Vice President of Health and Life Sciences in mid-2025, coming from a distinguished 35+ year career as Group CIO and Global VP of Medical Devices at Johnson & Johnson MedTech. He reports to Shelley Bransten, CVP of Global Industry Solutions.

Jones does not have a publicly listed speaking session at HIMSS26, but his strategic fingerprints are visible in Microsoft’s HLS positioning. His LinkedIn commentary in the weeks surrounding the conference has been consistent: trust is foundational, and Microsoft’s enterprise governance infrastructure is the differentiator that matters most to health system CIOs evaluating AI platforms.

“Trust is everything in healthcare and life sciences, especially as AI becomes more deeply embedded in how care is delivered and therapies are developed.”

- Larry Jones, CVP Health & Life Sciences, Microsoft

Jones occupies the commercial and customer-engagement leadership role. Mary Varghese Presti, also CVP of Health and Life Sciences, handles product strategy and portfolio evolution, and she has been the most visible Microsoft HLS executive in HIMSS26 media coverage. The two roles are complementary, and both matter for understanding where Microsoft’s HLS business is heading.

The Consumer Health AI Story You Should Not Miss

Separate from the clinical AI story, Microsoft released a report on March 10 that is relevant for anyone thinking about where healthcare AI is actually being used today. [5]

Copilot and Bing are handling 50 million health questions every day. Analysis of more than 500,000 de-identified conversations from January 2026 found that nearly one in five involve users describing their own symptoms or trying to understand personal test results. One in seven symptom queries are conducted on behalf of someone else, a child, an aging parent, or a partner, reflecting the sandwich generation managing care across multiple family members.

Health queries spike late at night when clinics are closed. Mobile users are twice as likely to ask about active symptoms. Desktop users are three times more likely to conduct broader medical research. And Satya Nadella amplified the moment directly:

“Healthcare has never moved faster or asked more of clinicians. At HIMSS, we’re rolling out big updates to Dragon Copilot, including Work IQ to bring the right work context alongside patient data, so there’s less admin busywork and more focus on patients.”

- Satya Nadella, CEO, Microsoft

The governance question this raises is one I covered earlier this week. That same data, touching a health system’s AI agent rather than a consumer product, would require BAAs, audit trails, and a privacy board review. Same data. Same person. Different door. Wildly different rules. That regulatory gap is not going away, and it will be a live issue well beyond HIMSS26.

The Competitive Landscape: A Crowded and Critical Field

Microsoft is not operating in a vacuum. The competitive picture at HIMSS26 is the most crowded it has ever been.

Epic announced that 85% of its customer base is actively using its AI suite and previewed Agent Factory, a visual builder for custom AI agents, alongside Curiosity, its proprietary medical foundation models. Google Cloud showcased Gemini-powered agentic AI with CVS Health, Humana, and Waystar. Oracle Health embedded AI agents across its EHR for 30 specialties. AWS positioned itself as the infrastructure enablement layer for the field.

STAT News published a pointed piece on March 11 asking the question that deserves more airtime: health AI agents are here, but what about the validation? [6] The concern is that vendors across the board, Microsoft included, are deploying agents faster than patient-level safety validation can keep pace. That tension between deployment speed and safety rigor is real, and it will intensify throughout 2026.

Microsoft’s differentiator is enterprise stack depth. The combination of Nuance’s clinical heritage, Azure’s HIPAA-compliant infrastructure, the Microsoft 365 productivity suite, and the marketplace model creates integration density that no single competitor currently matches. The strategic question for health system CIOs is whether they consolidate around Dragon Copilot’s platform approach or anchor to their EHR vendor’s native AI. That is a 12- to 18-month decision cycle, and the conversations happening on this floor this week are shaping it.

My Bottom Line

Microsoft came to HIMSS26 with a platform story, not a product story. Dragon Copilot was repositioned from an ambient scribe into a clinical AI operating system, with Work IQ integration, a third-party marketplace, role-specific expansions for nurses and radiologists, and a rural health access play that signals long-term market development thinking.

The nursing use case is the most strategically interesting move. It is a category where the workforce pain is acute, the competitive field is thin, and the outcomes data is already compelling. If Microsoft executes on the marketplace model and the nursing expansion simultaneously, they will have built a position that is genuinely difficult to displace.

The governance and validation question raised by STAT News is the right counterweight. Speed and safety are in tension across the entire field, and no vendor is fully exempt from that scrutiny.

I will have more HIMSS26 coverage on Cloud Wars throughout the week. If you are here on the floor and want to connect, find me.

Paul Swider
Senior Analyst, Cloud Wars
Founder & CEO, RealActivity

References

1. HIT Consultant. “Microsoft Upgrades Dragon Copilot to an Agentic Clinical Assistant at HIMSS 2026.” March 5, 2026. hitconsultant.net

2. Novick, Allison. “Why nursing needs a different kind of AI and how Dragon Copilot delivers.” Microsoft Tech Community, March 5, 2026. techcommunity.microsoft.com

3. Business Wire. “Wolters Kluwer partners with Microsoft to bring trusted clinical intelligence to Microsoft productivity workflows.” March 5, 2026. businesswire.com

4. HLTH. “Atropos Health and Microsoft Integrate Evidence Agent with Dragon Copilot at Stanford Medicine.” March 11, 2026. hlth.com

5. Microsoft AI. “Health Check: How People Use Copilot for Health.” March 10, 2026. microsoft.ai/news/health-check-how-people-use-copilot-for-health

6. STAT News. “AI agents are rapidly spreading in health care, but validation is lacking” March 11, 2026. statnews.com

7. Microsoft Industry Blog. “Unify. Simplify. Scale: Microsoft Dragon Copilot meets the moment at HIMSS 2026.” March 5, 2026. microsoft.com/en-us/industry/blog/healthcare/2026/03/05

8. Fierce Healthcare. “Microsoft debuts Dragon Copilot AI clinical assistant for nurses, expands access to 3rd-party apps, agents.” March 5, 2026. fiercehealthcare.com

9. Healthcare IT News. “Microsoft’s AI tool unification in Dragon Copilot takes center stage at HIMSS26.” healthcareitnews.com

10. HIMSS26 Session Catalog. “Transforming Clinical Workflows with AI Apps and Agents.” Session #27, March 10, 2026. app.himssconference.com

Paul J. Swider is CEO & Chief AI Officer at RealActivity, a Microsoft Partner specializing in mission-critical AI for healthcare systems. He has 30+ years in healthcare technology, has trained over 3,000 engineers across GE, IDX, and Microsoft, and is the founder of BOSHUG, the Boston Healthcare Cloud & AI Community spanning 50+ countries.

We’re about three years into the generative AI era. And the honest assessment of Microsoft Copilot, from someone who has spent 30 years inside the Microsoft healthcare ecosystem, is that the individual pieces have been solid but the sum hasn’t yet matched the ambition.

That’s not a criticism. It’s context.

Copilot in Teams is effective. It handles meeting summaries, action items, and follow-ups well enough that most enterprise users who try it keep using it. Copilot Studio gives builders a real platform for creating custom agents, with connectors and logic flows that didn’t exist two years ago. Microsoft Research, as a standalone product, has quietly become one of the better AI research tools on the market.

But if you talked to a CIO at a mid-size hospital system or a COO at a Fortune 500 company over the past year, you heard some version of the same thing: “We see the potential. We’re not sure it’s there yet.”

I think that changes within 6 months. And I think the two biggest reasons are Copilot Tasks and Cowork.

What Tasks and Cowork Actually Change

Copilot Tasks is Microsoft’s move toward autonomous background execution. Instead of responding to a prompt in the moment, Tasks lets Copilot run workflows on a schedule or trigger, without a human sitting in front of it. Think of it as the difference between asking someone a question and giving someone a job to do.

Cowork takes a different angle. It introduces a persistent, collaborative AI layer inside M365 that works alongside you, not just when you invoke it. It sits in the flow of work, surfaces context, offers suggestions, and takes on tasks within the broader scope of your team’s work. If Tasks is about autonomy, Cowork is about partnership.

Together, they close the two biggest gaps in Copilot’s original design: the inability to act independently and the inability to stay present across a workflow without being repeatedly prompted.

This is the moment where the sum starts to exceed the parts. You’re no longer switching between a meeting summarizer, a Studio agent, a research assistant, and a document helper. You’re working inside an AI layer that connects across all of them, acts on your behalf, and stays with you across tools and time.

Why This Matters for Healthcare

For hospitals and health systems, this convergence hits two pressure points simultaneously.

The first is operational. Hospital operations run on volume, repetition, and compliance. Revenue cycle teams process thousands of claims. Supply chain teams manage hundreds of vendor relationships. Compliance officers track regulatory changes across state and federal landscapes. These are precisely the workflows where Copilot Tasks, running autonomously in the background, can have an outsized impact. Add Cowork into that environment, and you get an AI layer that doesn’t just execute a single task but also participates in the department’s operational rhythm.

The second is clinical, and this is where the story gets more interesting. Microsoft has been positioning Dragon Copilot less as a standalone dictation and documentation product and more as a clinical AI platform. That’s a significant shift. Dragon has deep penetration in hospitals already. If it evolves into a platform that integrates with the broader Copilot ecosystem, you get something no other vendor can match: a unified AI layer that spans both clinical and operational workflows.

Health systems have been treating these as separate AI conversations for years. One team evaluates ambient documentation tools. Another team evaluates operational automation. A third team looks at analytics and research tools. Microsoft’s current trajectory suggests those conversations can converge. And when they do, the value proposition changes entirely.

The 6-Month Window

I don’t say “6 months” casually. This is based on watching the pace of Microsoft’s architectural changes, the maturity of Tasks and Cowork in preview, the Dragon Copilot roadmap signals from HIMSS, and the broader patterns in how Microsoft ships enterprise products. They tend to build infrastructure quietly, iterate through preview, and then accelerate once the foundation is stable.

We are in the infrastructure phase. The foundation is being laid right now. And if you’re a hospital CEO, COO, CIO, or CMIO, the time to engage with this trajectory is not when the product is finished. It’s now, while the architecture is forming and the use cases are still being defined. The organizations that engage early will shape how these tools get deployed in healthcare. The rest will be adopting someone else’s playbook.

The Bottom Line

Three years into generative AI, the strongest individual AI tools in the enterprise sit inside the Microsoft ecosystem. Within 6 months, those tools will stop being individual and start being interconnected. For healthcare, this means operational AI and clinical AI converging under a single infrastructure for the first time.

That’s not hype. That’s architecture. And architecture is what scales.

I have been covering healthcare technology for 30 years. I have attended more HIMSS conferences than I can count. And I can tell you that what I witnessed this week at HIMSS26 in Las Vegas was different.

Not different in the way vendors always claim things are different. Different in a way you can measure. Different in a way that changes how patients experience care.

The centerpiece of that shift, for me, was a conversation I had with Aashima Gupta, Google Cloud’s Global Director of Healthcare Strategy and Solutions. She has been building Google Cloud’s healthcare business since 2016 and is one of the most influential voices in health IT. Sitting down with her at HIMSS was an honor, and the substance of what she shared stayed with me long after I left the room.

I also had the privilege of joining Tom Smith on the AI Agent and Copilot Podcast for Cloud Wars to break down what I learned from that conversation and from the HIMSS floor. You can watch the full episode here.

View my previous posts

The Agentic Moment

Aashima put it directly. This is an “agentic moment” for healthcare.

That language matters. She was not describing a product update or a marketing campaign. She was naming a threshold. Healthcare AI has moved from suggesting to acting. From chatbots responding to prompts to agents that reason, orchestrate, and execute multi-step workflows across entire systems.

In her official blog post ahead of HIMSS26, she wrote that healthcare is moving beyond static digital records into what she called the “agentic healthcare era.” A fundamental shift from point-and-click software to anticipatory care. She painted a picture I found compelling. Imagine a world where clinical insights find the doctor at the exact moment of care, letting the stethoscope, not the screen, remain the center of the exam room.

That is not a five-year-out vision. That is the direction being built right now.

Five Partnerships. Five Domains. All in Production.

What made Google Cloud’s HIMSS26 presence stand out was the scope. They did not show up with one announcement. They brought five, and each one covered a different domain of healthcare.

CVS Health launched Health100, a new tech-enabled subsidiary built on Google Cloud’s Gemini models. It is positioned as an AI-native consumer engagement platform with an open ecosystem approach, designed to serve patients regardless of pharmacy, insurer, or provider. Thomas Kurian, CEO of Google Cloud, called it the future of agentic, AI-powered health care that enhances human touch and eliminates complexity. This is part of CVS’s broader $20 billion technology commitment and the most ambitious consumer-facing healthcare AI deployment I have seen.

Highmark Health’s generative AI assistant Sidekick grew from 1 million to over 6 million prompts across 74 active use cases in just over a year, delivering an estimated $27.9 million in AI-enabled value. They announced new capabilities including a synthetic audience feature and an IRB protocol builder for Allegheny Health Network. Richard Clarke, their Chief Data and Analytics Officer, signaled the next chapter is bringing multi-agent support to employees.

Waystar expanded its Google Cloud partnership to accelerate agentic AI for the autonomous revenue cycle. Their AltitudeAI platform has prevented more than $15 billion in denied claims in less than a year and reduced time spent on denial workflows by 90 percent. Waystar connects over 1 million providers processing 7.5 billion annual transactions, roughly 60 percent of the US patient population.

Humana launched Agent Assist, built on Google Cloud’s Vertex AI and Gemini. The tool supports over 20,000 member advocates handling up to 80 million calls annually. It summarizes conversations in real time, anticipates member needs, and surfaces relevant benefit details while keeping humans accountable for final decisions.

Quest Diagnostics introduced Quest AI Companion, an AI-powered chat feature in the free MyQuest app and portal. Powered by Google’s Gemini models, it analyzes up to five years of an individual’s lab data, provides plain-language explanations, and helps patients compose questions for their healthcare providers. It is HIPAA-compliant and operates entirely within the MyQuest environment.

These are not pilot programs. These are production systems operating at enterprise scale.

The Example That Brought It Home

During my conversation with Aashima, the example that hit hardest was HCA Healthcare. 190 hospitals. 60,000 nurse handoffs every single day. At the end of a 12-hour shift, a nurse sits down to prepare the handoff for the incoming nurse. That is where mistakes happen, when people are tired and rushing.

Google is supporting that handoff with AI. Even saving five minutes per handoff, multiplied by 60,000, returns 300,000 minutes a day to patient care.

But what Aashima said next is what really stayed with me. Every job has a chore and a purpose. Healthcare workers are in it for the healing and the empathy. AI is taking away the chore so they can do the meaningful work.

That reframes the entire AI conversation. Not replacing workers. Returning purpose to the workforce. I discussed this at length on the AI Agent and Copilot Podcast because it is the kind of framing that healthcare leaders need to hear. The resistance to AI in clinical settings often comes from a fear of replacement. This framing dismantles that fear.

Patient Agency and the Trust Question

I pushed Aashima on patient agency. This is my long-standing conviction and something I am deeply passionate about. The real power of AI in healthcare is not just making organizations more efficient. It is returning control to the patient.

Quest AI Companion was the example I focused on. For the first time, a patient can chat with five years of their own lab results through an AI agent. Personalized to their age, ethnicity, and history. That feels like a threshold moment.

I asked her directly. Do you see a future where patients bring their own data to their own agent of choice?

Her answer was one of the best I have gotten on this topic. The question in 2026 is not what AI can do. The question is what AI can be trusted to do.

She introduced the concept of “enterprise truth,” the idea that agents must be grounded in authoritative clinical sources. Quest has the protocols, the global lab standards, the knowledge base. When you get a response from their AI companion, it is grounded in that truth. That is different from throwing your lab results into a general-purpose AI and hoping for the best.

She then connected this to their ASCO partnership, where 50,000 oncologists worldwide now have access to an agent grounded in gold-standard cancer treatment guidelines. An oncologist in California, New York, or India gets the same authoritative guidance. That is the promise of trusted AI at global scale.

Interoperability Is the Unlock

One of the things I emphasized on the Cloud Wars podcast is that interoperability will determine whether the agentic era succeeds or fragments.

Aashima built her career on this. From the first Kaiser Permanente API to leading interoperability at Apigee to now. She made a point that resonated with me deeply. If we do not get agent-to-agent interoperability standards right, we are going to create a bigger mess than the data silos we have been trying to fix for a decade.

Google is supporting open standards like A2A, their Agent-to-Agent protocol, which was originally launched in April 2025 and donated to the Linux Foundation. It standardizes how AI agents discover and communicate with each other regardless of framework or vendor. Notably, athenahealth unveiled a Model Context Protocol server at HIMSS26 as well, the complementary protocol that handles agent-to-tool communication. The infrastructure for multi-agent healthcare systems is being laid right now.

Three Takeaways for Healthcare Leaders

After this conversation, after walking the HIMSS floor, and after breaking it all down on the AI Agent and Copilot Podcast, three things are clear to me.

First, the agentic era is real and it is here. HCA is running 60,000 handoffs. Highmark has 74 live use cases producing $27.9 million in measurable value. Humana is deploying across 20,000 advocates. Waystar has prevented $15 billion in denied claims. These are production systems, not pilots.

Second, enterprise truth is table stakes. Google Cloud’s position is clear. AI agents in healthcare must be grounded in verified, authoritative data. Not general-purpose guessing. The governance question is now inseparable from the AI question.

Third, the patient needs to be in this conversation. We are building incredible agent infrastructure for organizations. But the patient is still on the receiving end of everyone else’s agent. Quest AI Companion is a first step. I want to see that door open wider. And to Aashima’s credit, she engaged on that directly rather than deflecting.

If you are a healthcare leader, the question is not whether to adopt agentic AI. It is whether your organization is ready to govern it, trust it, and eventually put it in the hands of your patients.

Listen to the Full Conversation

I joined Tom Smith on the AI Agent and Copilot Podcast to walk through everything I learned from my conversation with Aashima Gupta and from the HIMSS26 floor. We covered the agentic moment, real-world deployment examples, patient agency, and where this is all heading over the next 12 months.

Listen here AI Agent and Copilot Podcast, Google Cloud Showcases Big AI Healthcare Advances

References

1. Google Cloud Blog. "Helping Healthcare Move from Data to Agentic Action." March 5, 2026.

2. Healthcare Finance News. “Google Cloud to Showcase How Gemini-Powered AI Agents Are Transforming Healthcare at HIMSS26.” March 5, 2026.

3. Google Cloud Press Corner. "CVS Health and Google Cloud Announce New Strategic Partnership." March 5, 2026.

4. Google Cloud Press Corner. "Waystar Advances AI Innovation with Google Cloud to Accelerate the Autonomous Revenue Cycle." March 5, 2026.

5. Google Cloud Press Corner. “Humana Redefines the Member Experience with Agent Assist Built with Google Cloud.” February 3, 2026.

6. Quest Diagnostics Newsroom. "Quest Diagnostics Introduces AI Companion to Help Patients Understand and Act on Lab Test Results." March 2, 2026.

7. TechTarget. "AI ROI, Agentic Innovation in Spotlight as HIMSS Approaches." March 2026.

8. AI Agent and Copilot Podcast. “Google Cloud Showcases Big AI Healthcare Advances.” March 13, 2026.

9. Google Cloud Blog. "What It Takes to Get Your Team Ready for the Agentic Era." January 30, 2026.

10. HIT Consultant. “HIMSS26 Pre-Day Recap: How Agentic AI is Taking Over Healthcare IT.” March 9, 2026.

Paul J. Swider is CEO & Chief AI Officer at RealActivity, a Microsoft Partner specializing in mission-critical AI for healthcare systems. He has 30+ years in healthcare technology, has trained over 3,000 engineers across GE, IDX, and Microsoft, and is the founder of BOSHUG, the Boston Healthcare Cloud & AI Community spanning 50+ countries.

Even national technology delegations, such as Taiwan’s, are showcasing healthcare innovation.

Bobo tea at the Taiwan Experience.

The shift in just two years is remarkable.

But something happened today that meant even more to me personally.

While sitting in the press room, I ran into a journalist who has been covering health tech for a long time. He remembered me from HIMSS a couple of years ago and said something I’ll never forget:

“You were one of the people who lit the flame here.”

Now, the reality is this movement is much bigger than any one person. Thousands of people are working hard to advance healthcare.

But hearing that… and then walking the floor and seeing AI now at the center of HIMSS… was a special moment.

Aashima Gupta, Global Director of Healthcare Strategy & Solutions, Google Cloud.

A few other highlights:

• Meeting leaders from Taiwan working on healthcare technology and cross-border collaboration with the U.S.
• Incredible conversations with innovators building the next generation of healthcare platforms
• Sitting in the Executive Summit alongside leaders from organizations like AdventHealth and many others, doing meaningful work in healthcare

Moments like this make you pause.

For most of my career, I’ve worked at the intersection of technology, community, and healthcare, building communities, sharing ideas, and advancing innovation.

Seeing AI move from early conversation to real momentum in healthcare is something I feel incredibly grateful to witness.

And even more grateful to be part of the community helping shape what comes next.

#HIMSS26 #HealthcareAI #HealthTech #AIinHealthcare #HIMSS

Every major platform is making its move. Google Cloud just published its HIMSS thesis, and Aashima Gupta called it directly: "In 2026, we're entering what I call an agentic moment for healthcare."

Helping healthcare move from data to agentic action, Google Healthcare and HLS https://vist.ly/4u7k3

I'll be sitting down with Aashima on-site to dig into how Google is approaching this, and, more importantly, what it means for interoperability and for patients actually accessing their own data in an agentic world.

I'm also meeting with Microsoft Healthcare & Life Sciences leadership at their booth to get the other side of the story. When two of the biggest platforms in the world are racing to define the healthcare agent framework, the governance question isn't theoretical anymore. It's operational.

This is the part that fascinates me. I've been building and shipping AI in healthcare since before most people were talking about it. And what I see right now is an industry moving fast on agents while the hardest question goes unasked: when a patient's data finally flows freely, who builds the agent that works for them?

I've been working on something for healthcare leaders navigating this shift, from copilots to governed AI agents. If you want a copy, DM me or drop me a line at pswider@realactivity.com.

See you in Vegas.

hashtag#HIMSS26 hashtag#HIMSS hashtag#HealthcareAI hashtag#AgenticAI hashtag#HealthIT hashtag#Interoperability hashtag#GoogleCloud hashtag#Microsoft hashtag#AIGovernance hashtag#CloudWars hashtag#DigitalHealth hashtag#MeetMeAtHIMSS

On February 27, Amazon CEO Andy Jassy went on CNBC with Sam Altman and announced a "Stateful Runtime Environment" that AWS and OpenAI will co-create. A system where AI agents can maintain context, remember prior work, call tools, and access compute. He described it as the next generation of how developers will build AI applications.

Then he said something remarkable. "There's nothing else like that today."

I've been building healthcare AI systems for over 30 years. I built symbolic AI triage engines in 2001, migrated 50+ HIPAA workloads to Azure, and today I advise health systems on mission-critical AI infrastructure. So when the CEO of Amazon makes a claim like that on national television, I pay attention.

And I can tell you he's wrong.

Microsoft Shipped This Nine Months Ago

Azure AI Foundry Agent Service went generally available in May 2025. Not as a concept. Not as a preview. As a production-ready, enterprise-grade platform that over 10,000 customers have already built on.

Everything Jassy described as groundbreaking is already running in production on Azure. The Foundry runtime automatically manages state across messages, tool calls, agent configurations, and metadata. Conversations persist across sessions. Agents can pick up where they left off without developers manually threading context back in.

But Microsoft went further than what AWS is even promising. Foundry supports multi-agent workflows with a structured orchestration layer that coordinates multiple agents across complex, multi-step processes. It handles context management, error recovery, and long-running durability out of the box. Then at Ignite in November 2025, Microsoft added managed long-term memory to the service. A persistent state layer that automatically extracts, consolidates, and retrieves user context across sessions and devices. Microsoft's own AI Research director called it turning memory from "a demo feature into an enterprise primitive."

And here's the part that should really get your attention. Azure is the only cloud that offers both Anthropic's Claude and OpenAI's GPT models under one governance umbrella. AWS just locked itself into a single-vendor model dependency with this deal. Microsoft gives you choice.

Why This Matters More in Healthcare Than Anywhere Else

If you're a CMIO or CIO at a health system, you already know that infrastructure decisions in healthcare are essentially irreversible. You don't get to run a six-month pilot on one cloud, decide you don't like it, and casually migrate your HIPAA workloads somewhere else. The switching costs are brutal. The compliance burden is real. And the downstream impact on clinical workflows, provider experience, and patient safety is too high to get wrong.

That's why the timing of this announcement matters so much. AWS is telling the market, right now, that it doesn't have competitive agentic infrastructure. And it's asking you to wait "a few months" while it catches up.

Meanwhile, the clinical use cases for AI agents aren't waiting.

Think about a patient discharge workflow. You need agents coordinating across clinical documentation, pharmacy reconciliation, insurance verification, follow-up scheduling, and transport. That's not a single model call. That's a multi-step, multi-agent orchestration problem that requires persistent state, error recovery, and real-time coordination across systems. Foundry handles this today. AWS is announcing the concept.

Or consider prior authorization. An agent that monitors submissions, tracks status, escalates denials, and coordinates between payer and provider systems needs to maintain context across days or weeks of interaction. That requires the kind of managed long-term memory that Microsoft is already shipping. Not the kind that AWS is promising to build.

And then there's governance. In a hospital, an AI agent can't operate in a vacuum. It needs identity management through Entra ID, data governance through Purview, HIPAA-grade audit trails, and role-based access controls. Foundry ships with all of that baked into the runtime. AWS is going to have to build or bolt on that entire trust layer around whatever OpenAI delivers. For a regulated industry, that gap matters enormously.

Most large health systems are also already deep in the Microsoft ecosystem. M365, Teams, SharePoint, Fabric. Foundry agents can natively reach into all of it. An AWS-hosted OpenAI agent trying to access the same data requires integration work that adds months and risk to any deployment.

What AWS Is Really Telling Us

Let's call this what it is. This announcement is not a leap forward for AWS. It's an admission that Bedrock's agent infrastructure wasn't competitive, and that Amazon needed OpenAI to close the gap. The partnership is a fast-follow strategy, not an innovation play.

It also creates a strange dynamic. Amazon is betting its agentic future on a company that is simultaneously deepening its relationship with Microsoft. OpenAI's models already run on Azure. The "co-training on Trainium" angle is interesting from a compute economics perspective, but it doesn't solve the developer experience and enterprise governance problems that actually determine platform adoption in healthcare.

For regulated industries, "coming soon" has never been an acceptable answer.

The Decision Framework for Hospital Leadership

If you're already on Azure, you have access to production-grade agentic infrastructure today. Use it. Start building the clinical agent workflows that will define the next era of care delivery.

If you're evaluating platforms, understand that the gap between Microsoft and AWS on agentic infrastructure is widening, not narrowing. Every month that passes deepens the ecosystem advantage.

If you're on AWS, ask your account team a direct question. When will you have parity with what Azure AI Foundry is shipping today? And what does the migration path look like if the answer isn't satisfying?

If you believe, as I do, that AI agents are the future of clinical operations, then the platform you choose now is the platform your agents will run on for years. Agents are the new cloud lock-in. The cloud wars have shifted from compute and storage to agentic infrastructure, and the governance and compliance layer is what separates a real healthcare platform from a general-purpose cloud with a few AI services bolted on.

Microsoft understood that early. AWS just admitted it.

References

1. “Amazon CEO Andy Jassy explains the benefits to developers on the Stateful Runtime Environment that Amazon and OpenAI will co-create” Amazon News

2. “OpenAI and Amazon announce strategic partnership” Amazon News

3. Introducing the Stateful Runtime Environment for Agents in Amazon Bedrock

4. Amazon Bedrock Documentation

5. Azure AI Foundry Documentation

6. Azure AI Foundry Agent Service, Microsoft Azure

7. OpenAI’s models run on Azure as part of Microsoft’s multi-year partnership

8. AWS Trainium is Amazon’s custom AI accelerator for model training.

9. “Introducing Anthropic’s Claude models in Microsoft Foundry: Bringing Frontier intelligence to Azure”,Microsoft Blog

10. “Microsoft and OpenAI extend partnership”, Official Microsoft Blog

11. “Azure Durable Functions Overview”, Microsoft Learn

12. “Azure OpenAI Service Overview”, Microsoft Learn

Paul J. Swider is CEO & Chief AI Officer at RealActivity, a Microsoft Partner specializing in mission-critical AI for healthcare systems. He has 30+ years in healthcare technology, has trained over 3,000 engineers across GE, IDX, and Microsoft, and is the founder of BOSHUG, the Boston Healthcare Cloud & AI Community spanning 50+ countries.

There is a scenario playing out in healthcare AI that most organizations have not fully reckoned with.

A clinical team builds their prior authorization workflows around an AI system. Compliance depends on it. Providers trust it. Leadership has signed off on it. Then, quietly, the underlying model that powers that system changes. The outputs shift. The documentation changes. And no one on the clinical or compliance team was warned.

This is not a hypothetical. It is the operational reality that Microsoft’s latest strategic move is pointing toward.

Microsoft has publicly disclosed plans to accelerate internal AI model development, reducing its reliance on OpenAI. For most industries, this registers as a competitive business story. For healthcare organizations running mission-critical workflows on Microsoft tools, it is a governance question that demands an answer today.

What Paul Swider Said on the AI Agent and Copilot Podcast

RealActivity CEO and Chief AI Lead Paul Swider joined analyst Tom Smith on the AI Agent and Copilot Podcast to unpack exactly what this shift means and what healthcare leaders should do about it.

The conversation covered three areas every healthcare executive needs to understand.

Model flexibility is now a governance requirement.

If your AI stack is built on a single model provider with no contingency plan, you are exposed. When the underlying model changes, the outputs change. In healthcare, that has direct implications for compliance reporting, clinical documentation accuracy, and provider workflows. Multi-model and multi-cloud strategies are no longer advanced IT decisions. They are baseline operational planning.

There is a real upside, but only for organizations that are ready.

Microsoft controlling its own models could accelerate the development of healthcare-specific AI capabilities. That includes more robust HIPAA and compliance frameworks, stronger clinical reasoning, better documentation understanding, and tighter integration with Azure Health Data Services. The organizations positioned to benefit are the ones already testing and evaluating models, not the ones waiting to react when a transition is announced.

The job market shift is real, but the timeline is being overstated.

Microsoft AI CEO Mustafa Suleyman predicted that AI will take over professional roles in under two years. Paul pushes back on that timeline. Historical technological transitions show that roles evolve rather than disappear. The more important question for healthcare leaders is not whether AI will change the workforce, it is whether your organization is building the governance, training, and strategy to lead that transition rather than absorb it.

Why This Matters Right Now

Healthcare organizations are already navigating CMS 2026 AI mandates, pressure to reduce administrative burden, and increasing scrutiny around how AI tools make decisions. Adding model instability to that environment, without a plan, creates compounding risk.

The organizations that will come out ahead are the ones treating AI model governance as a strategic priority, not an afterthought. That means building flexibility into the stack, evaluating models continuously, and ensuring that every AI-driven decision in a mission-critical workflow can be defended in an audit.

RealActivity’s RAPS Copilot and Wheelhouse AI CoE are built precisely for this environment, designed to give healthcare organizations the governance infrastructure, compliance readiness, and model flexibility they need to adapt as the AI landscape shifts.

Go Deeper

Watch the full podcast episode with Paul Swider and Tom Smith for the complete conversation: https://agentandcopilot.com/cloud-wars-minute/ai-agent-and-copilot-podcast-microsoft-ai-model-self-sufficiency-requires-customers-to-hedge-bets/

Read Paul's AI Brief on Microsoft's 2026 frontier model roadmap and what it means specifically for healthcare leaders: https://www.linkedin.com/pulse/microsofts-2026-frontier-model-what-healthcare-leaders-paul-swider-7lgke

If you are attending or considering the AI Agent and Copilot Summit in March, this conversation is the primer you need before you walk in the door. Register here: https://copilot.summitna.com

RealActivity is a healthcare AI company headquartered in Boston, focused on ethical, compliant, and high-performing AI solutions for modern health systems. Learn more at realactivity.ai.

The real AI war isn't about models anymore. It's about who controls the operating system for digital labor.

If you're still watching the AI race as a contest between Claude, GPT, and Gemini, you're watching the wrong game.

The real battle just moved up the stack.

OpenClaw. Anthropic's CoWork. OpenAI's emerging agent initiatives. Microsoft's GitHub Copilot API push. These aren't incremental product updates, they're land grabs for the most consequential layer in enterprise AI, the agent runtime.

And here's what most people are missing. Cowork and OpenClaw occupy the same conceptual space. Both represent horizontal, standalone agent platforms built on top of powerful code-capable models. Both signal the rise of a new category, general-purpose digital coworkers, not narrow copilots that autocomplete your email.

This is the moment the industry shifts from AI as assistant to AI as labor infrastructure.

The New Stack That Matters

Forget the model benchmarks for a second. Here's the stack that will define enterprise AI for the next decade:

Foundation Model → Agent Runtime → Enterprise Workflow Platform

The foundation model is the engine. The agent runtime is the operating system. The enterprise workflow platform is where work actually happens.

Whoever defines the standard for agent execution, governance, identity, tool access, observability, compliance, will shape how digital labor operates inside organizations. Full stop.

We've seen this pattern before. It doesn't matter if you have the best CPU if someone else owns the OS. And right now, three very different strategies are competing to become that OS.

Three Strategies, One Prize

Anthropic's CoWork reflects a safety-first enterprise positioning. It's Claude-native, deeply opinionated about guardrails, and designed for organizations that want agentic AI without the existential risk conversations at their board meetings. For healthcare systems, my world, this matters enormously. When your agent is touching clinical workflows, safety isn't a feature. It's the product.

OpenAI's alignment with OpenClaw signals serious investment in open agent infrastructure. This is a different bet: that the orchestration layer should be model-agnostic, interoperable, and community-driven. If OpenClaw evolves into a true open runtime, it could reduce model lock-in and shift power away from any single model provider. That's a strategic gift to enterprises, and a potential threat to everyone selling vertical integration.

Microsoft's GitHub Copilot API push is the one healthcare CIOs should be watching most carefully. Microsoft isn't just making Copilot better, they're transforming it from a productivity feature into programmable infrastructure embedded across Azure, GitHub, Entra ID, and Microsoft 365. With that distribution advantage, Microsoft can embed agents directly into enterprise workflows where identity, compliance, and data governance already live. For health systems already deep in the Microsoft ecosystem, this is the path of least resistance to agentic AI.

The Strategic Fork: Open vs. Model-Native

This is the question that will define the next chapter:

Will agent platforms be model-agnostic and open, letting enterprises swap foundation models the way you swap databases? Or will they be vertically integrated, Claude-only ecosystems, GPT-only ecosystems, where the model and the runtime are inseparable?

The answer will determine whether the future looks like the open web or the app store.

OpenClaw leans toward the open model. Cowork leans toward the integrated model. Microsoft, characteristically, is trying to play both sides, open enough to attract developers, integrated enough to lock in enterprises.

For healthcare organizations evaluating these platforms, this isn't an abstract architectural debate. It's a procurement decision with decade-long implications. Choose the wrong side of this fork and you're either locked into a single vendor's roadmap or managing a complexity explosion of interoperable components with no single throat to choke.

What This Means for Healthcare

When strong reasoning models combine with tool use, memory, and workflow control, AI shifts from assistant to autonomous executor. In healthcare, that means agents that don't just summarize clinical notes, they execute multi-step compliance workflows, coordinate across EHR systems, manage FTE tracking, and flag regulatory gaps before they become audit findings.

This isn't theoretical. This is what we're building at RealActivity right now, mission-critical AI implementations for health systems that need agents operating inside their compliance boundaries, not outside them.

The organizations that move early to understand this agent runtime layer, not just the model layer, will have a structural advantage in how they deploy, govern, and scale AI across clinical and administrative operations.

The Bottom Line

The AI model wars made great headlines. The agent runtime wars will make great businesses.

The winner won't necessarily be the best model. It will be the platform that becomes the trusted operating system for enterprise AI agents, the one that solves identity, governance, tool access, observability, and compliance at the orchestration layer.

For healthcare, where trust is the currency, that distinction is everything.

References

1. Anthropic. "Introducing Cowork." Claude Blog, January 12, 2026.

2. “Copilot SDK” Github, Official Repository

3. “OpenClaw.” Github, Official Repository

4. “About GitHub Copilot CLI” GitHub Docs

5. Ropek, Lucas. "Anthropic Brings Agentic Plug-ins to Cowork." TechCrunch, January 30, 2026.

6. "What Is OpenClaw: Autonomous AI Agent Framework Explained (2026 Guide)." AI Cloud IT, February 2026.

7. Wiggers, Kyle. "OpenAI's Acquisition of OpenClaw Signals the Beginning of the End of the ChatGPT Era." VentureBeat, February 15, 2026.

8. Microsoft Community Hub. "Building Agents with GitHub Copilot SDK: A Practical Guide." Microsoft Tech Community, January 22, 2026.

9. Microsoft Azure Blog. "Announcing Azure Copilot Agents and AI Infrastructure Innovations." November 18, 2025.

10. Gartner. "Gartner Predicts Over 40% of Agentic AI Projects Will Be Canceled by End of 2027." Press Release, June 25, 2025.

11. “Customize Cowork with plugins” Claude

Paul engages with this space daily as CEO & Chief AI Officer at RealActivity, a Boston-based Microsoft partner specializing in mission-critical AI for health systems, and as a healthcare AI analyst for Cloud Wars. He founded the Boston Healthcare Cloud & AI Community (BOSHUG), a non-profit spanning 50+ countries.

View my previous posts

Why This Matters

Microsoft’s confirmation that it will launch proprietary frontier foundation models in 2026 represents more than just another AI product announcement. For healthcare organizations that have invested heavily in Microsoft’s ecosystem from Azure cloud infrastructure to Microsoft 365 Copilot, this development introduces both strategic opportunities and operational uncertainties that demand executive attention now, not later.

The timing is particularly significant. As healthcare systems face mounting pressure to demonstrate ROI on AI investments while navigating complex regulatory requirements like the CMS 2026 AI mandate, the stability and predictability of underlying AI infrastructure becomes mission-critical.

The Strategic Landscape

Microsoft’s announcement comes against a backdrop of financial and competitive pressures that healthcare leaders should understand:

The OpenAI Dependency Problem

Microsoft currently relies heavily on OpenAI’s models to power many of its enterprise AI offerings. While Microsoft maintains a 27% stake in OpenAI’s for-profit arm and retains IP rights through 2032, OpenAI’s continued cash burn with no clear path to profitability creates uncertainty. When NVIDIA reportedly stepped back from a $100 billion investment consideration, it signaled growing investor skepticism about the unit economics of large-scale AI development.

Enterprise Adoption Reality Check

Despite significant marketing investment, only 3.3% of Microsoft 365 users have adopted paid Copilot services. This low conversion rate suggests that enterprise AI adoption including in healthcare faces barriers beyond technology: change management, workflow integration, and demonstrable clinical or operational value.

Healthcare as Strategic Priority

Microsoft has explicitly identified healthcare as a core focus area, using ambitious language like “medical super-intelligence” and emphasizing autonomous, self-improving AI agents. This commitment suggests healthcare applications will receive priority in model development and fine-tuning efforts.

What Changes for Healthcare Organizations

1. Model Layer Volatility

The foundation models powering your AI-enabled clinical tools, administrative automation, and decision support systems are about to shift. Healthcare leaders should:

• Audit current AI dependencies - Catalog which applications in your environment rely on Microsoft/OpenAI models

• Review vendor contracts - Ensure agreements include model transition clauses and performance guarantees that survive infrastructure changes

• Plan for migration testing - Budget time and resources for validation when underlying models change

2. Potential for Healthcare-Specific Optimization

Microsoft controlling its own models could accelerate development of healthcare-specific capabilities, including:

• More robust HIPAA and compliance frameworks built at the foundation level

• Specialized medical reasoning and clinical documentation understanding

• Tighter integration with Azure Health Data Services and FHIR APIs

However, this same control could reduce competitive pressure and limit customer choice in model selection.

3. The Platform Lock-in Question

As Microsoft moves toward vertical integration of its AI stack, healthcare organizations face a strategic decision: commit more deeply to the Microsoft ecosystem or maintain model-agnostic architectures.

Consider these questions:

• Can our AI strategy function if we need to switch model providers?

• Do we have internal expertise to evaluate model performance independently?

• Are we building institutional knowledge about AI, or just vendor relationships?

The Anthropic Hedge

Microsoft’s simultaneous investment in Anthropic (OpenAI’s primary competitor) reveals sophisticated strategic hedging. For healthcare leaders, this creates both opportunity and complexity:

Opportunity → Access to potentially competing models could drive better pricing and capabilities

Complexity → Multi-model environments require more sophisticated governance and expertise to manage

Healthcare organizations should consider whether this model competition benefits their use cases or simply adds vendor management overhead.

The Healthcare AI Maturity Question

Perhaps the most important insight from Microsoft’s announcement is what it reveals about the current state of healthcare AI adoption: we’re still in the infrastructure phase, not the value realization phase.

The pattern healthcare has seen before during EMR implementations, cloud migrations, and interoperability mandates is repeating: organizations that treat infrastructure decisions as strategic choices rather than IT procurement exercises emerge stronger when platforms shift.

The question for healthcare leaders is not whether Microsoft’s 2026 models will be better or worse than today’s options.

The question is whether your organization has the strategic framework, technical expertise, and governance structures to evaluate that question independently and make decisions aligned with your institution’s mission.

Looking Ahead

Microsoft’s move toward proprietary foundation models represents a maturation of the enterprise AI market. For healthcare, this means greater stability as major tech platforms take direct responsibility for model development, more specialization as healthcare-specific optimizations become economically viable at scale, and higher stakes as getting AI infrastructure decisions right becomes more important as switching costs increase.

The healthcare organizations that will thrive in this evolving landscape are those building internal competency now not just deploying vendor tools, but understanding the architectural decisions, governance requirements, and strategic implications of AI infrastructure choices.

The 2026 timeline gives healthcare leaders a window to prepare. The question is whether that preparation will be proactive strategy or reactive scrambling when the platform shifts.

Paul J. Swider is CEO and Chief AI Officer at RealActivity, where he leads clinical and administrative AI strategy for healthcare organizations. He is the founder of the Boston Healthcare Cloud & AI Community and speaks globally on responsible AI adoption in healthcare.

The incretin market is about to get a lot more competitive, and the implications go well beyond endocrinology.

On January 30, China's National Medical Products Administration approved Sciwind Biosciences' ecnoglutide injection, marketed as Xianyida, for adults with type 2 diabetes. It's the world's first approved cAMP-biased GLP-1 receptor agonist, and it comes from a Hangzhou-based company that most Western health system leaders have never heard of.

That’s about to change.

What Xianyida Actually Is

Ecnoglutide is a once-weekly injectable GLP-1 receptor agonist, similar in mechanism to Novo Nordisk’s Ozempic and Eli Lilly’s Mounjaro. What makes it different is its cAMP signaling bias, an engineering approach that Sciwind says enhances biological efficacy. The drug completed three Phase III clinical trials before approval, with results published in The Lancet Diabetes & Endocrinology.

In weight loss trials, participants on the highest dose (2.4 mg) lost more than 15% of their body weight by week 48. Nearly 93% of participants lost at least 5% of their body weight, roughly seven times the rate of the placebo group. The drug also reduced liver fat by an average of 53% in the 2.4 mg cohort.

Those numbers put ecnoglutide in the same performance range as Wegovy.

Sciwind has also filed for weight management approval in China, meaning this isn’t just a diabetes play. It’s a full metabolic franchise in the making.

Why the Timing Matters

China has 148 million adults with diabetes, the highest number of any country in the world. That makes it the single largest addressable market for incretin therapies, and domestic competition is intensifying fast.

Ozempic sales in mainland China, Taiwan, and Hong Kong fell 7% in 2025, the first decline since its 2021 China approval. The reason is straightforward. China has now approved GLP-1 therapies from Eli Lilly (Mounjaro), Innovent Biologics (mazdutide), and Guangzhou Innogen (efsubaglutide alfa), in addition to Xianyida. Both the Innogen and Lilly medicines were recently added to China’s state-run health insurance scheme for type 2 diabetes patients, putting direct pricing pressure on Novo Nordisk.

Novo’s CFO acknowledged the shift publicly, noting that “competition is entering more at this point in time.”

The Global Play

Sciwind isn’t content with China alone. The company is in active licensing discussions with a U.S. partner to bring ecnoglutide to American patients, and is pursuing partnerships in Latin America and the Middle East. CEO Pan Hai has said pricing in China would stay in line with competitors, but the company won’t engage in a “price war.” The licensing model suggests Sciwind is betting on partnerships over direct commercialization in Western markets.

This mirrors a pattern we’ve seen across biotech in the last few years. Chinese-developed therapeutics are reaching clinical milestones that rival Western incumbents, and the companies behind them are increasingly looking outward.

What This Means for Health System Leaders

If you’re a CIO, CMIO, or VP of clinical informatics, this story matters for several reasons.

First, formulary complexity is increasing. The GLP-1 category already requires sophisticated clinical decision support logic. Adding new entrants with differentiated mechanisms (like cAMP bias) means your pharmacy and therapeutics committees will need better data infrastructure to evaluate options and guide prescribing.

Second, prior authorization workflows are going to get more complicated. As more GLP-1 options enter the market with different payer coverage rules, the administrative burden on your teams grows. If your revenue cycle and prior auth systems aren’t AI-enabled yet, the pressure to modernize is only going to increase.

Third, the global supply picture is shifting. One of the persistent challenges with Ozempic and Mounjaro has been supply constraints. Domestic Chinese production of competitive alternatives could eventually ease global supply pressure, or it could fragment the market in ways that make procurement strategy more complex. Either way, your supply chain intelligence needs to keep up.

Finally, the metabolic care landscape is expanding rapidly. GLP-1 therapies are moving beyond diabetes and obesity into MASH/NAFLD, cardiovascular risk reduction, and possibly neurodegenerative conditions. The health systems that build flexible, AI-informed care pathways now will be best positioned when these indications arrive.

The Bottom Line

Xianyida’s approval is one data point in a much larger story. The GLP-1 market is globalizing, diversifying, and accelerating. For healthcare technology leaders, the question is whether your clinical and administrative systems are built to handle what’s coming.

At RealActivity, we help healthcare organizations build that readiness, aligning AI strategy across clinical decision support, administrative workflows, and operational planning. If the convergence of precision therapeutics and health system operations is on your radar, let’s talk.

References

1. China National Medical Products Administration. Drug approval announcement, January 2025.

2. Sciwind Biosciences. Corporate announcement and product information, 2025.

3. Novo Nordisk; Eli Lilly. Product information for semaglutide and tirzepatide.

4. Nature Reviews Drug Discovery. GLP-1 receptor signaling and biased agonism overview.

5. Ecnoglutide Phase III trial results. The Lancet Diabetes & Endocrinology, 2025.

6. Wilding JPH et al. Once-weekly semaglutide in adults with overweight or obesity. NEJM, 2021.

7. International Diabetes Federation. IDF Diabetes Atlas, 10th Edition.

8. Innovent Biologics; Guangzhou Innogen regulatory disclosures, 2025.

9. National Healthcare Security Administration, China. National Reimbursement Drug List updates, 2025.

10. Novo Nordisk Investor Relations. 2025 earnings transcript and financial statements.

11. Nature Biotechnology. Trends in Chinese biopharma global licensing activity.

12. American Medical Association. 2023 Prior Authorization Physician Survey.

13. U.S. FDA Drug Shortage Database. GLP-1 supply updates.

14. SELECT Trial Investigators. Semaglutide and cardiovascular outcomes. NEJM, 2023.

15. AASLD guidance on metabolic-associated steatohepatitis and emerging therapies.

Paul J. Swider is CEO and Chief AI Officer at RealActivity, where he leads clinical and administrative AI strategy for healthcare organizations. He is the founder of the Boston Healthcare Cloud & AI Community and speaks globally on responsible AI adoption in healthcare.

The Viral Post That Got the Details Wrong and the Big Picture Right

A social media post aggregating five recent medical breakthroughs went viral last week. 493 likes, 12,000 views, and a wave of public optimism about the future of cancer treatment. The post, attributed to biomedical AI commentator Bo Wang, highlighted advances from Mexico, Spain, Japan, South Korea, and Vietnam. The narrative was compelling. Non-invasive, targeted therapies are finally gaining ground against the diseases that have resisted conventional treatment for decades.

The problem? Several of the details were wrong. The Mexican HPV study targeted low-grade lesions, not high-grade. The Spanish tumor study eliminated pancreatic cancer in mice, not prostate cancer. And the framing glossed over the enormous distance between a promising mouse model and a treatment your oncology team can actually prescribe.

But here's what the post got right. Something fundamental is shifting in how we attack disease. And for those of us building and governing the technology infrastructure that supports clinical care, that shift has operational consequences we need to start planning for now.

What Actually Happened

I went back to the primary sources. Here's what the science supports.

Mexico. Photodynamic Therapy Clears HPV Without Surgery

Dr. Eva Ramón Gallegos and her team at Mexico's Instituto Politécnico Nacional used photodynamic therapy, a non-invasive technique combining a photosensitizing drug with targeted light, to treat 29 women with HPV and low-grade cervical lesions (CIN I). After six months, HPV was eliminated in 100% of patients. Lesion regression reached 64.3% in those with both HPV and CIN I. Published in Photochemistry and Photobiology.

The correction matters. The viral post claimed 50% success in high-grade lesions. The study addressed low-grade only. That's a clinically significant distinction, one that affects treatment protocols, patient counseling, and downstream coding. Small sample, early stage, but a genuinely promising non-invasive alternative to excisional procedures that compromise fertility.

Spain. Triple-Drug Combination Eliminates Pancreatic Tumors in Mice

Mariano Barbacid's group at Spain's National Cancer Research Centre (CNIO) combined three drugs and achieved complete, durable regression of pancreatic tumors across three mouse models. The combination included daraxonrasib (a KRAS inhibitor), afatinib (an EGFR inhibitor already approved for lung cancer), and SD36 (a STAT3 protein degrader). No resistance developed over 200 days. Published in PNAS, December 2025.

Pancreatic ductal adenocarcinoma has a five-year survival rate below 10%. Current therapies lose effectiveness within months as tumors develop resistance. The CNIO team's strategy of blocking three points in the KRAS signaling pathway simultaneously, rather than one, prevented the cancer from finding an escape route. Barbacid himself cautions that clinical trials are not yet feasible, but these are the strongest preclinical results ever reported for this cancer.

Japan. iPS Stem Cells Restore Standing in a Paralyzed Patient

Researchers at Keio University, led by Hideyuki Okano, transplanted neural stem cells derived from induced pluripotent stem (iPS) cells into four patients with complete spinal cord paralysis. One patient improved from grade A (no sensation or movement) to grade D. He can now stand independently and is training to walk. A second patient regained arm and leg movement. Two others showed no improvement. Announced March 2025, reported in Nature, not yet peer-reviewed.

This is the world's first spinal cord treatment using iPS cells. The inconsistency in outcomes is honest science and a reminder that regenerative medicine is still in its earliest translational phase.

South Korea. KAIST Discovers a Molecular Switch That Reprograms Cancer Cells

Professor Kwang-Hyun Cho's team at KAIST identified molecular switches targeting three genes (MYB, HDAC2, and FOXA2) that can revert colon cancer cells to a normal-like state. The approach was validated through cellular experiments and animal studies. Published in Advanced Science, January 2025.

This is a paradigm-level concept. Instead of killing cancer cells, you reprogram them. No chemotherapy. No collateral damage to healthy tissue. The technology has been transferred to BioRevert Inc. for commercial development. Still foundational, but the implications for future treatment design are significant.

The Strategic Signal for Healthcare Technology Leaders

Five countries. Four continents. Five fundamentally different therapeutic approaches, from photodynamic therapy and multi-drug targeted combinations to stem cell regeneration, genetic reprogramming, and engineered cell therapy. What unites them is a clear trajectory away from blunt-force treatment and toward precision, non-invasive methods that generate complex, multi-modal data at every stage.

For health system CIOs, CMIOs, and innovation officers, the operational implications are concrete.

Clinical decision support systems built on established chemotherapy and surgical protocols will need to evolve rapidly to incorporate emerging evidence from therapies that don't fit neatly into existing order sets. Novel treatments create novel billing, coding, prior authorization, and compliance challenges. Your revenue cycle wasn't designed for molecular reprogramming or domestically manufactured CAR-T cells. And multi-modal patient data (genomic sequencing, real-time treatment monitoring, longitudinal outcomes tracking) demands data architecture that most health systems haven't built yet.

The organizations that move now to align their AI strategy with this therapeutic trajectory will be positioned to deliver these treatments effectively and sustainably. The ones that wait will be retrofitting.

Why Getting the Details Right Is the Whole Point

The viral post's traction tells us something important. The public is hungry for progress in oncology and regenerative medicine. But the specific errors, high-grade vs. low-grade lesions, prostate vs. pancreatic cancer, aren't trivial. They're the kind of details that change treatment decisions, patient expectations, and clinical trial eligibility.

For healthcare organizations, this is a familiar problem at scale. Misinformation reaches patients and boards before vetted evidence reaches your clinical teams. AI-powered knowledge management, evidence integration, and decision support aren't nice-to-haves. They're the infrastructure that ensures your care teams and your patients are working from the same verified playbook.

The same rigor we applied to verifying these five breakthroughs is what's needed inside every health system's intelligence layer.

Looking Forward

These five breakthroughs are genuine reasons for measured optimism. They represent real science, published in credible venues, with honest caveats from the researchers themselves. They also represent a preview of the complexity heading toward every health system's front door, clinically, administratively, and operationally.

The question isn't whether these therapies will change medicine. It's whether your organization is building the intelligence layer to deliver them when they arrive.

At RealActivity, that's exactly what we help healthcare organizations do. We align clinical and administrative AI strategy with the future that's already in motion. If these questions are on your radar, we should talk.

Paul J. Swider is CEO and Chief AI Officer at RealActivity, where he leads clinical and administrative AI strategy for healthcare organizations. He is the founder of the Boston Healthcare Cloud & AI Community and speaks globally on responsible AI adoption in healthcare.