Campus to Commure: Carnegie Mellon University

1% of all US Physician appointments now run on Commure Ambient AI. That's over 20 million annualized encounters. This is proof that when a targeted, well-designed healthcare automation solution delivers both clinical and financial value, adoption stops being an AI experiment and becomes an operational necessity.

Below are the lessons we’ve learned along the way working with small clinics that have enabled Commure to power the largest health systems in America.

Commure’s Journey: Focusing Where the Bulk of Care Is Delivered 

The majority of patient encounters happen outside of large medical centers and academic institutions. Independent practices, community hospitals, rural health systems, and outpatient clinics handle most preventive, chronic, and follow-up care.

These organizations typically run on tighter operational margins with staffing models leaving less room for redundancy and technology resources often limited. That means the cost of inefficiency is higher, both in time and in dollars. In a small rural clinic, shaving five minutes off every appointment could mean one or two extra patients seen each day.

These care environments are also where innovation cycles run fastest. With leaner teams and less bureaucracy, independent practices and community hospitals create a tighter feedback loop between clinicians, staff, and technology. For Commure, this has meant the opportunity to co-develop solutions in real-world settings, refining them quickly, and then scaling those proven gains into larger enterprises.

Developing with Rapid Feedback Loops in Clinic Settings 

From the outset, Commure focused deployments in care environments where speed, adaptability, and clear ROI are critical. These organizations need solutions that can integrate into existing workflows without a six-month change management program.

For automation to succeed here, it must:

• Work within current EHR systems without costly rip-and-replace projects.
  
  
• Support both clinical and billing workflows to ensure every improvement in care delivery is matched by strong revenue cycle performance.
  
  
• Deploy in weeks, not quarters, to generate early wins and keep leadership and staff engaged.

Commure CTO, Dhruv Parthasarathy, highlighted this approach at the most recent Commure Nexus event: “These small practices enable us to do cutting-edge work. They're almost like development labs and research settings for us; they co-develop, they want to take risks, they have really interesting use cases, and they move really, really fast. So we perfect everything with them, and then take that same technology up to the biggest health systems and EHRs in the world.”

By leaning into our agile and scrappy Silicon Valley roots, Commure is laying the groundwork for broader, system-wide adoption by proving value first in faster-moving, operationally-lean settings.

Growth Accelerators: Factors Driving Adoption

The rapid adoption of Commure Ambient AI and our integrated revenue cycle automation is driven by four main factors:

1. Clinician satisfaction:
   Clinicians see immediate benefits: less time spent charting, fewer clicks, and more time with patients. In some deployments, charting time has dropped by over 80%, with providers also capturing more billable work through accurate documentation.
   
   
2. Integrated clinical and financial impact
   Tight coupling between documentation and revenue cycle automation means fewer missed charges, cleaner claims, and faster payment. That combination supports both patient care quality and financial stewardship.
   
   
3. Peer-to-peer influence
   Healthcare communities talk. When a practice or hospital in a region starts seeing results, others take notice. Word-of-mouth adoption, especially among clinicians, has been a strong driver of growth.
   
   
4. Forward-deployed engineering
   Our engineering teams work side-by-side with clinicians and administrative staff during implementation. This hands-on approach ensures rapid customization to workflows, faster issue resolution, and continuous product refinement based on real-world feedback, accelerating time to value and deepening user trust.

Implications for Healthcare Leadership Across the Ecosystem

The success of healthcare automation solutions in high-volume, operationally lean settings has significant implications for health system leaders across the industry:

• Scalability is proven in smaller settings first. If it works in a clinic with minimal IT resources, it will work in a fully staffed enterprise IT department.
  
  
• Reliability comes from daily use and direct feedback. Clinicians stress-test these solutions in the real world, and their input goes straight to engineers to drive rapid improvements.
  
  
• Adaptability drives ROI. Automation solutions tailored to clinical realities will outperform top-down initiatives that disrupt established workflows.
  

For large health systems, these lessons offer a roadmap: start in high-impact, high-volume areas, then expand across the enterprise.

Building Toward System-Wide Transformation

The future of healthcare automation will be defined by solutions that work across the spectrum of care settings. Commure’s experience shows that success in the most resource-constrained environments is the strongest proof point for enterprise-scale readiness.

By continuing to design solutions that integrate seamlessly, deliver measurable outcomes, and align with the operational realities of different organizations, we’re building a foundation for system-wide transformation.

Whether you’re leading a rural clinic network, community hospital, or large health system, the path forward is clear: choose healthcare automation solutions that meet your clinical teams where they work, support your financial performance, and scale without friction.

If you are ready to rapidly build, deploy, and customize solutions that solve your most pressing challenges, we are ready to collaborate.

Discover Commure CoLab

In the latest KLAS First Look, Commure Ambient AI earned a strong 93.3 overall performance score, with 100% of customers saying they would buy it again*. KLAS spoke with health system leaders and doctors to understand how Commure Ambient AI performs in everyday clinical workflows. The interviews point to less time spent on documentation, stronger note quality, and a better experience for providers.

Commure serves over 100 enterprises (1% of all US physician appointments) that report more than $500M in annual net patient revenue across 60+ EHRs. If you are exploring ambient AI and want a solution that includes end-to-end RCM automation, read what stood out in the KLAS research: where the product is strongest, how it integrates, and which features teams actually adopt. Want all of the details? Download the full report here.

Performance at a glance
‍

• 93.3 overall performance score with 100% saying they would buy again and 100% including the solution in long-term plans*
  
  
• Key performance indicators: buyers gave high marks where it matters with an A+ for executive involvement, A for supporting integration goals, A- for needed functionality and ease of use, and A+ for likely to recommend*

“Commure offers an ambient scribe product to assist in medical documentation to decrease the overall provider burden that documentation usually creates. Commure Ambient AI is a true ambient scribe instead of traditional dictation software. A lot of people say they have an AI scribe, but in reality, it is a fancy dictation system, whereas Commure Ambient AI is truly in the background.” —CEO/president

Strengths customers call out
‍

• White-glove support & responsiveness: hands-on help pre-, mid-, and post-launch; quick access to the right people to resolve issues
  
  
• Continuous improvement: rapid iteration and willingness to tailor to real-world workflows rather than “set it and forget it”
  
  
• Seamless integrations: alignment with health system goals and existing tech stacks

“The technical support is a key strength for Commure, and that support is available during the onboarding and launch processes and immediately after. The vendor makes their people very readily available to assist with any issues that come up. What sets the vendor apart is their pre-, mid-, and post-launch support.” —CEO/president

“The key strengths of Commure are that they are always at the tip of the spear when it comes to new technology and improving and that they listen to how the solution is being used and adjust for that. They don’t just leave Commure Ambient AI by itself and hope for the best.” —Physician

Adoption of key functionalities
‍

Organizations interviewed reported strong uptake of capabilities that matter in daily practice, including:

• Improved collection and decreased denial rates: Built in automated coding and denials copilot resubmission tools
  ‍
• Forward-deployed engineers: On-site or virtual engineers that accelerate custom integrations and real-time problem-solving
  
  
• AI Studio: Ability to manage personalization and templates
  
  
• Multiple recordings: Ability to have multiple recordings with intelligent start/stop functionality per encounter
  
  
• Multilingual support services: Multispeaker conversational support across 60+ languages, with advanced dialect and accent handling

“I think [Commure Ambient AI] has improved the quality of life for all our providers, and it has made everybody really happy. I think it will continue with what it can do. The biggest thing is that documentation is the worst part of the job. So the fact that the tool has made that part easier and has actually improved people’s experience with documentation is huge.” —CEO/president‍

Read the full KLAS First Look report for yourself
‍

Ready to see all the details? Download the KLAS First Look to view the full KPI grades, the strengths and improvement areas in customers’ own words, and a clear snapshot of which features teams are actually adopting.

You will also get respondent profiles, integration and onboarding notes, and practical lessons you can use in your evaluation. Grab the report to decide if Commure Ambient AI fits your workflows
‍

Download the Full KLAS First Look

*Report based on limited data

Tell us a little bit about yourself—what do you like to do outside of work?

I was born and raised in San Diego, so naturally, I try to take advantage of the sunshine every chance I get. I’m a proud dad to two boys, Cooper (3) and Stetson (1), and happily married to my wife, Kennedi. Most of my free time revolves around family adventures, whether that’s navigating the zoo with my kids, chasing them around the park, or just enjoying the outdoors. When I do manage to sneak away, you’ll usually find me on the golf course or in the ocean.

As a kid, what did you want to be when you grew up?

I always knew I wanted to do something in public service. Early on, I dreamed of working in law enforcement, inspired by my dad, who served as a San Diego Police officer for 35 years. Watching the way he served his community, especially in family and community services, made a big impression on me. Over time, my interests shifted toward counseling, and I pursued a degree in Marriage and Family Therapy. Eventually, the business world pulled me in, and while it wasn’t the path I originally imagined, it’s one I’m grateful for. It’s led me to where I am today, and I wouldn’t change that for anything.

Describe a day in the life of your role.

As part of the Launch and Implementation team, I lead the West Region. My day is a balancing act between managing the needs of my own clients and supporting the broader implementation team. A lot of my time goes into unblocking bottlenecks, fine-tuning processes, and thinking about how we can scale both our product and our approach.

I try to structure my days like a sandwich, starting and ending with internal meetings or project work, with the middle of the day focused squarely on clients. I’ve learned that time spent addressing a client’s needs is just as important as time spent preparing for those conversations. Beyond client work, I carve out time to mentor and develop my team, because I believe investing in their growth pays dividends across the entire organization.

What made you decide to join Commure?

After leaving Uber in 2020, I dove into the startup world, supporting early-stage SaaS companies and even working as an independent consultant. I loved the hustle and grit of building something from the ground up, but after my second son, Stetson, was born, I started looking for a balance of stability, growth, and impact.

A former Uber colleague, Manus Burns, introduced me to Commure, and it checked every box. I was drawn to the opportunity to build scalable systems in a high-growth environment, but what keeps me here is the culture of hustle, the customer-first mentality, and the real-world impact we make. At the end of the day, what we build helps clients and directly affects patient care. That sense of purpose is powerful.

How would you describe the Commure company culture?

Fast-paced, collaborative, and energizing. No two days are ever the same, and it’s hard to find anyone here who isn’t smiling. The team is deeply aligned, and it feels like there’s one heartbeat driving us forward together.

I often describe it like stepping onto a treadmill that’s already running. If you’re not ready, it can hit you hard at first. But once you find your rhythm, the energy is contagious. What I appreciate most is that success here is shared; it’s never about the individual, it’s about what we accomplish as a team.

What advice would you give someone on their first day at Commure?

Always ask “why.” Why do we do things a certain way? Why does it matter? Why does the client care? The most successful people here are the most resourceful, those who know how to seek out context, filter information, and apply it when it matters.

I tell new team members not to overwhelm themselves by trying to master everything at once. Instead, bucket information by where it lives in the customer journey or product space. Recognize what’s important now, and set aside the rest until it becomes relevant. That approach not only keeps you sane but also ensures you’re focused on what actually drives value in the moment.

What has been your greatest accomplishment so far at Commure?

Without a doubt, building a team and watching them grow. In a high-growth environment, it’s easy to get consumed by metrics and results, but I try to pause and appreciate the people behind the work. Seeing team members develop new skills, grow in confidence, and achieve their career goals has been incredibly rewarding.

On the client side, my biggest accomplishment has been helping practices turn things around when they’re struggling. We work with clients who trust us with what I like to call the “second heartbeat” of their practice (the first being patient care), the second being their revenue cycle. Taking a client from “we might have to close our doors” to “our revenue is up, and we’re spending less time worrying about rejections,” for example, is an incredible feeling. That’s the kind of impact I want to keep making.

Interested in a career building the next generation of healthcare technology powered by AI? We are always looking for talented people across our departments.

Explore Career Opportunities

Healthcare is undergoing structural transformation. According to Commure CEO Tanay Tandon, the most consequential role of artificial intelligence today lies in concrete changes to how health systems operate versus speculative applications.

“Artificial intelligence is going to play a bigger role than people even realize in transforming the operating model and margin profile of health systems,” shared Tanay Tandon, CEO of Commure.

Across clinical and administrative domains, AI is already influencing the time clinicians spend with patients, the cost structures of provider organizations, and the quality of the patient experience.

Returning Time to Physicians by Eliminating Redundant Work

Commure’s approach begins with one of the most frequently cited burdens on clinicians: documentation. With Commure Ambient AI, health systems are reducing the need for manual note entry by capturing and structuring conversations in real time. The result is a measurable return of time to providers and staff.

“One of the most beautiful things we get to do is give physicians their time back—whether that’s at the end of the day or during the patient encounter,” Tandon shared. “A couple of hours a day, per physician. That translates into millions of dollars of productivity for a system.”

This regained time directly impacts both the financial and human aspects of clinical practice, supporting not only efficiency but also the physician-patient relationship.

Reducing Operational Waste in Revenue Cycle Functions

A second area of impact is revenue cycle management (RCM). Administrative processes, particularly those involving claims and denials, have historically required extensive manual labor. With tools like Commure RCM, health systems can now apply large language models to accelerate and simplify these functions.

“A single claim denial today might require five different people to touch it,” said Tandon. “With large language models, that can become one person reviewing the output. That’s not a five-year or ten-year vision—that’s an 18 month vision.”

By automating repetitive processes and reallocating staff time, health systems may significantly lower their cost to collect from insurance companies.

“The exciting thing there is, if we reduce the cost to collect using LLMs as part of the Commure RCM solution, we can put those dollars back on the table for health systems to serve their patients and their communities.”

Improving Patient Experience with 24/7 AI Guidance

Patients, too, face persistent friction in their healthcare interactions—particularly around scheduling, preparation, and information access. Commure Engage offers intelligent assistance to guide patients through their care journeys, regardless of time of day.

“In some cases, your LLM has the information ready to go, pulled from the EMR. It can respond via text or through a phone call with a natural-sounding voice that’s incredibly helpful to the patient and can guide them through their care journey,” said Tandon.

This continuous availability reduces no-shows and ensures patients arrive informed and prepared. As a result, care encounters become more productive for clinicians and less stressful for patients.

The Cumulative Effect: Toward a More Rational System

What unites these disparate use cases is their cumulative impact. Together they represent a meaningful shift in how health systems manage resources. Time regained for providers becomes capacity for additional patients. Dollars saved on collections may be reinvested in staffing or care delivery. Patients better supported between visits are more likely to return, adhere to care plans, and avoid preventable complications.

None of these improvements require speculative technologies or future-state projections. They are available now, contingent only on careful implementation and a willingness to reconsider legacy workflows. As Tandon’s remarks suggest, the opportunity for transformation lies not in replacing clinical expertise, but in removing the noise that obstructs it.

In short, the application of AI in healthcare operations need not be radical to be consequential. It need only be precise, pragmatic, and anchored in the actual workings of care.

Welcome to Commure Uncharted, a Q&A series where we sit down with healthcare industry thought leaders to discuss what the future of AI in healthcare could look like.

This installment, we are joined by Commure’s Chief Medical Officer, Dr. Jamie Colbert, MD, MBA, who still sees patients and works with clinicians and clients on how AI fits into care. Jamie discusses privacy and the sanctity of the exam room, explains when AI tools can help versus when a person needs to be in the loop, and shares what actually builds trust in busy workflows. He also offers a realistic take on accountability and bias and sets expectations for the next five years.

Q: Looking five years ahead, where do you see AI in healthcare? Will doctors still be face-to-face with patients?

Dr. Colbert:
It’s important to remember that AI is still in its infancy. ChatGPT has only been available for less than three years, so it is hard to predict exactly where things are going. Today, most organizations are not comfortable putting patients in front of AI without a human in the loop for anything high stakes. By high stakes, I mean clinical decisions about how to treat a patient or how to handle a symptom or concern related to their health.

However, I do expect the field to evolve. It may not be very far down the road before we feel confident that AI is drawing on the right body of evidence, providing high-quality recommendations, and handling cognitive tasks that today belong to people with 10 or 15 years of specialized training.

That being said, I do not expect AI to completely replace physicians. AI will replace many aspects of healthcare, but there will still be a need for someone to sit with you, hold your hand, and lay a stethoscope on you. There is a science of medicine, and there is an art of medicine. The humanistic component is essential. It is health care because there is care in it. In the near term, say five years, I do not see a point where we feel cared for entirely by AI.

Q: What are the most common concerns you’re hearing from patients about AI in healthcare?

Dr. Colbert:
There are a few broad categories of concern. First, there is the issue of privacy and what happens to patient information after it is shared with AI. If a large language model owned by a big tech company like Google or OpenAI is involved, what happens to the data that is recorded to generate a note or to power a chatbot? Who has access to it? Could it be used to develop new products? Could someone trace it back to them? Patients worry that the exam room is no longer a sacred space and that their words could show up elsewhere.

Another category is trust in the technology itself and whether AI can provide accurate answers. Is it trustworthy? Is it drawing on appropriate resources? Was it trained on up-to-date datasets, clinical evidence, and studies?

A third category is concern about losing the human connection. Patients value and trust their providers. They worry hospitals and health systems will try to replace that connection with technology, so they no longer have a friendly face when they are not feeling well. There is no substitute for someone holding your hand when you are in pain or uncomfortable. Even if the AI has the correct answers, being alone in a sterile room without a person to offer comfort and reassurance would feel like a loss.

However, on the whole, I find that the overwhelming majority of patients are excited about the potential of AI to help improve their healthcare experience. While they may have concerns, they are on the whole hopeful that AI will be a net benefit to them. 

Q: Do patients trust AI more when it works behind the scenes versus when it interacts with them directly?

Dr. Colbert:
It depends on how the AI is used. When AI works behind the scenes to help physicians stay current and summarize treatment options, the patient is still interacting with their doctor, and the role of the AI is more in the background. In my experience, this tends to be acceptable to nearly all patients. 

Direct interaction varies by task. For something algorithmic like scheduling, many patients are fine with an agent because it is a discrete task that gets them an appointment. When the interaction moves into clinical territory, like what to do next for pain or shortness of breath, the threshold for trust is higher, and some patients will want a person who can answer questions and handle more complex situations.

Q: What’s driving clinician hesitancy around utilizing AI tools in daily workflows?

Dr. Colbert:
A couple of reasons come to mind. Firstly, physicians have been misled in the past by technology that promised efficiency and ended up adding work. Many tools translated to more clicks and more administrative tasks, so there is skepticism about whether AI is really helping or just a shiny object that generates buzz, versus something that will truly make their jobs better and more efficient.

Trust is another issue. For a complex case that might take two or three hours of literature review, AI could summarize the research so a provider spends 20 minutes instead. That can be valuable, but clinicians need to feel confident that the model used the right studies, is current, and did not miss important evidence. The same questions apply to ambient AI. If it listens to a 20-minute conversation and condenses it into 250 to 300 words, it has to be accurate. It also has to make judgment calls about what stays in the note and what gets left out, and providers need to trust how those decisions are made.

There is also the transparency challenge. AI can sometimes feel like a black box, and a physician may not know exactly which sources the AI used to generate its response. Citation is getting better, but there are still questions.

Q: How much of the hesitation around AI comes from technical limitations versus a general fear of change and disruption?

Dr. Colbert:
They are both equally important. It depends on who you speak with and what they worry about, but each is a real barrier to broader adoption. We have not solved the workforce questions yet: where AI fits in the workflow, what changes we make to daily routines, and how those changes make physicians happier and more productive. Providers also look at the outputs that define their work, which vary by role and setting. They want tools that help increase productivity and revenue where relevant, while still letting them enjoy what they do and helping patients feel more cared for.

On the technical side, the models are still evolving. The way to address that is to keep watching them, testing them, and continuing to really poke at them. We need to understand the limitations and the biases, and make sure we do not have blinders on that cause us to miss issues that come from relying too heavily on AI. That ongoing scrutiny surfaces problems and blind spots, and over time it gives us a path to address them as the tools improve.

Q: If AI makes a mistake in a clinical setting, how should health systems think about accountability?

Dr. Colbert:
When a physician has a treatment relationship with a patient, the doctor is ultimately responsible for the care. Physicians who use AI should continue to own the information shared with patients, the visit documentation, and any AI output that directly affects care. That is why there still needs to be a human in the loop for anything that interfaces with patients. The physician is still the one who signs their name and is the one who can be sued if something goes wrong.

Q: How should health systems address potential bias when using AI?

Dr. Colbert:
One approach is to consult other sources and use AI as one tool rather than fully relying on it when there are concerns about bias. Bias can show up in many ways. If a model is more oriented to patients of a certain race or demographic, and the patient in front of you does not fit that profile, you can try to tweak the AI by introducing the patient’s unique characteristics.

If the patient has a disability, for example, make sure the system accounts for the special considerations that come with that. My hope is that as these models improve, we will better account for potential biases by acknowledging differences between patients and steering the output toward recommendations that match what makes that individual patient special, instead of generic defaults.

Q: What is one myth or fear about healthcare AI you wish we could put to rest for good?

Dr. Colbert:
The myth that AI is replacing doctors. Right now, that is not the reality, and patients/doctors should not worry about it. I am not seeing any widescale attempt to fully replace clinicians with AI. Patients should think of AI as tools that help deliver better care so they have a better experience and achieve better outcomes.

At Commure, we believe technology should empower clinicians—freeing them from the keyboard so they can focus on patients. That’s why we built Commure Ambient AI to go beyond basic note-taking and support every step of the patient journey.

As a trusted MEDITECH Alliance member since March 2025, we offer a deeply integrated, secure, and rapidly deployable solution that enhances Expanse workflows without disrupting how clinicians operate.

With our Expanse integration, notes flow seamlessly into patient records—no copy-paste required. And whether it's used in the ED, inpatient, or ambulatory settings, Commure Ambient AI delivers accurate, structured documentation in a fraction of the time, helping clinicians spend more moments where they matter most: with patients.

Workflow Highlights

1. Deep API Integration with Expanse EHR: Sync notes directly into Expanse workflows.
2. Autonomous Coding: AI generates CPT and ICD-10 codes from notes, reducing denials.
3. Rapid Patient Intake: Upload histories, generate summaries, and push them into the EHR.
4. Multi-Modal Functionality: Turn audio, images, and documents into structured clinical notes.
5. Multi-language Support: Translate multi-speaker conversations in 60+ languages.
6. Scalable, Modular Options: From self-service to specialist support, sized for any organization.
7. Enterprise-Grade Security: HIPAA-compliant encryption, role-based access, & 24/7 monitoring.
8. SSO & SCIM Provisioning: Integrate with existing authentication systems for secure access.

With Commure Ambient AI + MEDITECH Expanse, organizations can streamline every stage of the documentation journey—from intake to billing—while protecting clinician time and improving patient care.

Our Most Popular Features:

Clinical Nudges & Care Cues
‍Inline prompts help clinicians address compliance-related gaps (e.g., missing MDM statements, MIPS guidelines) or quality/HCC coding cues (e.g., “Provider should Monitor, Evaluate, Assess, or Treat the patient’s Type II Diabetes Mellitus with Neuropathy”).

Autonomous Coding
‍AI suggests appropriate CPT and ICD-10 codes based on encounter content. Alerts users to documentation gaps that could lead to undercoding or denials.

ED & Hospitalist Notetaking
‍Pre-visit summaries, note carry-forward, ambient note generation, dictation, discharge summaries, and patient assignment lists.

Some of our happy MEDITECH customers include:

How does the MEDITECH Expanse-Commure Ambient AI Integration Work?

Customers can leverage the MEDITECH Expanse Integration via Commure Ambient - available on mobile, web, and chrome extension as well directly embedded within the MEDITECH Expanse Now mobile app.

In Expanse, Clinicians begin by opening a PDOC template directly on their workstation. This initial step requires them to navigate through template options and select the appropriate documentation format for their specific encounter type. Once the template is selected, they proceed to capture the patient visit using Commure's Ambient AI technology. If there are 2 or more documents leveraged in the encounter, a third step involves choosing an existing PDOC template within the AI application itself. Finally once the note is generated, the last step enables editing the note, prior to syncing it to Expanse via APIs. In this step, the generated note appears with a distinctive Yellow Flag indicator in Expanse, allowing providers to review the AI drafted note before finalizing the documentation.

The Expanse Now mobile workflow takes a more straightforward approach. This pathway optimizes for speed over visibility and enables clinicians to maintain their existing Expanse Now workflows. Clinicians record their patient visit directly within the Expanse Now application environment, eliminating some of the desktop navigation requirements. The AI-generated note and recording automatically upload to Expanse via integration, without requiring preview or manual confirmation steps.

This trade-off delivers faster hand-offs between documentation and clinical care. While some clinicians prefer the streamlined approach, others prefer the opportunity to review and refine their documentation before it becomes part of a permanent medical record.

Integration Pathways

We offer a number of ways to connect with and integrate notes from Commure Ambient AI to MEDITECH Expanse.

‍

HL7 (Backend Integration)

• This pathway operates entirely behind the scenes, requiring no clinician-facing interface. Notes transcribed by Scribe flow into Expanse IDM and appear in the “Documents” tab of Expanse.

• HL7 is ideal for acute-care and ambulatory settings but is not suited to fast-paced ED workflows. The single-block structure preserves rich clinical sections while making structured data available..

‍

v2 API (Early-Access)

• The current v2 API requires that a PDOC document already exist, so a clinician must open or create that document before launching Scribe. It supports four primary sections—HPI, PE, ROS, and AP—though additional subsections can be mapped inside each.

• Because this interface is in early access, it requires MEDITECH approval, adherence to a deployment guide, and Expanse version 2.1.70 or 2.2.58.

‍

Colossus Selenium (Front-End Automation)

• Instead of an API, this option automates the Expanse UI through Selenium, mimicking a user typing directly into PDOC template fields. It enables far deeper, custom write-back than the v2 API but obliges the clinician to launch Scribe inside the EHR.

• Note that Colossus Selenium is unavailable for on-prem Expanse installations.

‍

Colossus DOM Injection (Chrome Extension)

• Similar to Selenium but faster, DOM Injection writes structured content straight into the browser’s Document Object Model. This method achieves the same field-level write-back as with Selenium.

• As with Selenium, it substantially surpasses API depth while remaining limited to cloud-hosted Expanse environments.

‍

MDS (Batch Upload Service)

• MDS functions as a back-end batch uploader that needs no user interaction with Expanse.

• While it reliably covers gaps the other methods cannot, uploads are slower and carry higher operational cost, making MDS the “last-mile” contingency for exceptional cases.

Development Roadmap

The V3 Expanse-Commure development roadmap maintains the familiar single-tap patient assignment, while improving the overall clinician experience. This ensures that the transition to the new API enhances rather than disrupts established workflows.

The core improvement centers on visit capture efficiency: clinicians will capture patient visits in the Commure App once, with the AI note uploading seamlessly through V3 endpoints. This eliminates redundant data entry and reduces the opportunity for transcription errors.

The most significant advancement will be full write-back capability to structured fields within Expanse, eliminating the copy-paste workflows. This enhancement will allow AI-generated content to populate discrete data fields automatically, from vital signs to assessment categories.

Additionally, V3 APIs will feature intelligent handling of edge cases, automatically resolving scenarios involving zero, one, or multiple existing documents per encounter. This automation eliminates the manual decision-making currently required in complex documentation scenarios.

V3 Rollout will follow a phased pilot approach, ensuring smooth adoption and maximum efficiency for MEDITECH + Commure users.

Note: While these V3 API enhancements represent our development roadmap, we have not finalized V3 upgrades at this time. Current integrations operate on the proven v2 API framework.

Concluding Thoughts

The Commure Ambient AI + MEDITECH Expanse integration is more than a documentation tool — it’s a bridge between clinicians and the data they need, exactly when they need it. By embedding Ambient AI capabilities directly into MEDITECH workflows, providers can eliminate manual note entry, streamline patient intake, accelerate coding, and maintain clinical accuracy without sacrificing face‑time with patients.

Looking ahead, our V3 API roadmap promises even deeper integration with full structured‑field write‑back, intelligent document handling, and faster, frictionless visit capture — all while maintaining the familiar workflows that clinicians already trust. Our continuous innovation ensures that no matter how care delivery evolves, Commure and MEDITECH customers will remain on the leading edge of efficiency, accuracy, and patient‑centered care.

With Commure Ambient AI and MEDITECH Expanse together, you’re not just transforming documentation, you’re transforming every step of the patient journey. Reach out to learn more.

‍

Welcome to Commure Uncharted, a Q&A series where we sit down with healthcare industry thought leaders to discuss what the future of AI in healthcare could look like.

We are excited to be joined by Dr. Jean-Luc Neptune, MD, MBA. Dr Neptune has seen plenty of tech waves hit healthcare, but says this one feels different. As Executive Medical Director at Commure, he’s deep in the conversations shaping the future of AI-powered care. In this Q&A, he breaks down what’s more than just hype and how AI is reshaping trust, risk, and the role of the physician.

Q: What makes this wave of AI more transformative than past tech shifts in healthcare?

People forget how disruptive the mass adoption of the Internet was 20 years ago. It gave patients access to previously hard-to-access information, helped them look up symptoms or treatments, and shifted how they interacted with providers, for better and worse. But it didn’t really change how doctors practiced medicine.

What’s different now is that AI, especially the advances we’ve seen since the pandemic, is starting to shift how doctors actually think, diagnose, and recommend treatment.

We’re getting close to a point where patients could have healthcare encounters that are handled entirely by AI, without a human involved.

That kind of interaction would be a major shift from anything we’ve seen before.

If you had asked me five years ago whether a computer could handle an inbound patient question with 95% satisfaction, I would’ve said not a chance. But we’re on the verge of that now. We may not be ready to let AI run fully on its own, but the tech is at a point where it could handle a lot more than we’re currently allowing.

Q: Where do people most misunderstand AI’s role in clinical care?

The biggest thing people miss is how fast this technology is evolving. We tend to think about rate of change in linear terms, but tech often evolves in an exponential fashion. There have been decades of work behind the scenes on AI, and now it's finally starting to show up in real clinical settings. What feels advanced today will likely look basic in five to ten years or less. Most people aren’t prepared for how different things could look in a short period of time.

Q: As AI takes over more of the technical (administrative) tasks, what will define a great doctor?

What makes a great doctor hasn’t really changed; it’s still about communication. Patients remember the doctors who listened and connected with them. But the profession has long prioritized memorization and clinical reasoning. That’s what gets rewarded in medical school and residency.

As AI takes over more of those tasks, the real value will shift to how well a doctor can communicate, build trust, and leverage information.

When you encounter a brand-new patient in the clinic and you don’t know anything about that person, it takes skill and presence to collect what you need to make a diagnosis and build a care plan.

Beyond communication, doctors will need stronger management skills. Today, a typical primary care physician manages 2,000 to 3,000 patients. With the right technology to scale our clinical efforts, that number could grow massively - why not to 10,000 or more? AI can help identify who needs attention and when, but doctors will have to think more like care managers, not just clinicians. That shift isn’t emphasized in training today, but it’s going to become essential.

Q: Will physicians shift from diagnosing to orchestrating care?

I think you’d have to be naive to believe there won’t be a day when computers are better at diagnosis than people. We’re in the middle of that transition now as providers and patients are starting to see the potential, but are still adjusting to the idea.

At some point, maybe sooner than we expect, patients will trust the machine’s answer more than the doctor’s. Patients will ask their doctor, “What did the computer say?”

This mental shift happened long ago in areas like weather forecasting, where no one asks for a human opinion; they just check the model. Even as a physician, I’ve reached a point where I want to know what the AI thinks. When my wife had a mammogram recently, we opted for the AI readout (which cost an extra $25) because I believe it can add real value.

If AI handles more of the diagnostic work, then physicians will need to focus on what happens next. That means making sure patients get their medications, stay on their treatment plans, and understanding why they’re not following through if they aren’t. It also means shifting attention from what happens in the office to what’s happening outside the office. Patients spend most of their time outside the clinic, and that’s where their care often breaks down.

Q: With the rise of 24/7 AI-driven care, how do you see continuity of care evolving? Can technology really support long-term patient relationships?

As long as it’s clear that the technology is being used to support the care team, not replace it, patients are generally comfortable. When I worked at Memora (which was acquired by Commure in December 2024), that was always our message: this is a tool that helps your providers take better care of you. People were open to that and willing to engage.

As the technology improves, it becomes easier to imagine a different kind of patient experience. Instead of brief check-ins every couple of months, we could move toward continuous care, with your providers always present in the background.

In an ideal future, your doctor will be monitoring your status around the clock. Most of the time, nothing of clinical importance happens. But when something does (for example, your blood pressure spikes or your diabetes gets out of control), that’s the day your care team gets notified and steps in. That’s the kind of real-time responsiveness we’ve never had at scale, and that’s where this technology has real potential to raise the quality of care.

Q: Who’s accountable when AI gets it wrong: the doctor, health system, or developer?

That’s the big question, and it’s one I rarely see people address, probably because most people have never had to purchase malpractice insurance and think through the medicolegal questions associated with practicing. I purchased my own malpractice insurance for a number of years when running my mental health/substance use startup, and I can tell you that it really impacts your thinking and the risks you’re willing to take as a provider.

Right now, if there’s a bad clinical outcome, the physician and the provider organization are almost certainly going to get sued. But what happens when that bad outcome occurs because of a bad recommendation from an AI system?

If it’s a malfunctioning product, I know there’s a product liability framework that can be used to address any harms done to a patient, but it’s something we’re going to have to reckon with, especially as we move toward AI-only interactions.

In my opinion, we are already seeing this liability concern slowing adoption rates. Physicians don’t think in aggregate; they think in individual outcomes. One mistake can ruin a career, so providers tend to be very cautious in how they embrace new tools.

In the tech world, a 98% success rate is considered excellent. In healthcare, however, 98% isn’t good enough if the remaining 2% leads to real harm.

Q: What do you see as the most important opportunities—and risks—that AI brings to healthcare right now?

It’s a really exciting time, but big shifts like this can be unsettling. One of the many concerns we hear from customers is about job loss. That’s understandable, many people live with real financial insecurity, and the idea that new technology could make large parts of their workforce obsolete is hard to hear.

But AI also gives us a chance to finally address some of the biggest issues in healthcare. Thirty million people in the U.S. are uninsured. For many of them, even a solution that’s 90% as good as seeing a doctor, but costs $10 a month, could be life-changing. Too often, we treat “not perfect” as unacceptable when in reality, a lot of people have no access at all. We’re already seeing people use tools like ChatGPT to self-diagnose, which provides way more accurate results than when people first started using Google as an alternative to speaking with their physician. That’s not ideal (I think patients should be working with providers to access health resources), but it’s a signal that people are ready to engage if the tools are there.

Cost is the next challenge. We’ve been talking about rising healthcare costs since I was in business school over two decades ago, and they’ve only continued to rise. If we can use machines to deliver care more efficiently, we have a real shot at making the system more sustainable.

And then there’s quality. Doctors are human; we make mistakes, we fall behind on guidelines. AI can help raise the baseline by making sure we’re working with the best available information. There are still plenty of tough questions to answer, but the momentum is real. AI isn’t going away, and you can’t put the genie back in the bottle, so we have to figure out how to make it work.

At this year’s MUSE Inspire Conference, Dr. Geoffrey Burnham, Hospitalist Medical Director at Medical City Dallas, one of the largest hospitals in HCA’s system, joined Commure’s Chief Business Officer, Hersh Solanki, for a fireside chat at Commure’s Product Showcase: “Seamless, Smart, Ambient: Redefining Healthcare Workflows with Commure and MEDITECH.”
‍
As a proud MEDITECH Alliance partner, Commure kicked off with a live demo of Ambient AI, a MEDITECH-vetted solution that seamlessly integrates with Expanse. The conversation then pivoted to Dr. Burnham’s first-hand insights into developing and rolling out Ambient AI, and the impact it’s already having. 

What started as a pilot program with one physician has now expanded to the Medical City Dallas team and across the rest of the facilities within the HCA North Texas division, with roughly 200 users in total. According to Dr. Burnham, the change has been fast, meaningful, and driven by a strong partnership between clinicians and Commure’s engineers.

Since deploying Commure Ambient AI, providers in the North Texas division have experienced: 

From accurate documentation and improved reimbursement to more time for meaningful patient care, Dr. Burnham shares how this MEDITECH-integrated solution benefits every stakeholder.

“There’s the provider, there’s the patients, and then there’s the hospital itself.”

Focusing More on Patients with Faster Notes

Dr. Burnham explained why he was eager to try ambient documentation in the first place: “One of the things I've always kind of despised about medicine is writing notes.”

Dr. Burnham is not alone in this perspective. In a recent survey, 62% of providers pointed to administrative work as their top source of burnout. Dr. Burnham shared that since its roll out, Commure Ambient AI has made a tangible difference in how he and his team approach documentation at Medical City Dallas. "I know everything I'm doing is getting captured and I just kind of have to put that little bow on it and I'm done.”
‍

That extra face time has had a ripple effect across the patient experience: “I never want patients to feel like I'm rushed.  This helps make sure they don’t.”

Driving Better Coding and Billing, For the Provider and the Hospital

Beyond just saving time, Commure Ambient AI directly impacts billing and reimbursement by improving the quality and completeness of documentation. It does this by acting as a built-in safety net for coding:

“[Ambient AI] helps with my coding too. Sometimes I’ll catch something I missed, like a patient mentioning they were constipated, and realize I forgot to order Miralax. It gives me little reminders.”

The end result? More accurate documentation, better reimbursement, and more time for meaningful patient care.

“I don’t have to rush through my day. I can actually sit there, spend the time I need with the patient.”

Co-Creating the Product in Real Time

What made this rollout different, Dr. Burnham emphasized, was how closely he was able to collaborate with Commure’s engineering team.

“I was a “guinea pig” with HCA’s Digital Transformation and Innovation team.  I started working with Commure about a year ago... we took it from the beginning and built it into what it is now.”

He had a direct line to the Commure’s Forward Deployed Engineering (FDE) team, even after hours:

“I’d be texting them at 1:00 in the morning with ideas and feedback and a couple of them would still be awake because they’re okay with it. That’s when I was writing my notes.”

That real-time support helped accelerate development and adoption, according to Dr. Burnham: “It took us two to three weeks and then I could start signing those notes for my patients in the hospital and feel comfortable doing so.”

From that starting point, his team helped shape key features like History & Physical (H&Ps) specific templates, discharge summaries, and embedded feedback tools to the engineering team, which were often improvements that Commure’s FDE team implemented in just a matter of weeks.

Boosting Trust and Adoption Through Transparency

For many providers, handing off documentation to AI raises important concerns about accuracy and accountability. Dr. Burnham acknowledged that building trust was a key part of adoption, and that transparency was critical in making that possible.

“The last thing any clinican wants is any kind of legal issue where it’s like, ‘Okay, you documented this in the note.’ You’re like, ‘No, that wasn’t me, that was the AI.’ But when you have those track changes and you can see what’s going on, you can trust in the product.”

That’s where Commure Ambient AI’s “track changes” view comes in during the clinician’s review. Providers can see a side-by-side comparison with red and green highlights and strike-through formatting. “That transparency is critical for trust,” he said. “If the AI took this out of my last note and added this to my current note, then I know it has everything I need, and I can move on.”

The impact of this close partnership and solution is catching on as the North Texas division adopts Ambient AI at all sites, and providers are eager:

“Most providers were asking us, ‘When can we get this? Is it our turn yet?’ The adoption rate has been great.”

What’s Next: Further Enhancing and Iterating at Speed

Looking ahead, Dr. Burnham sees even more potential. He outlined several needs and future features:

• Discharge summary optimization
• Automated admission order sets
• Medication formulary mapping
• Color-blind accessible diff view
• Summarization of outpatient encounters and inbox messages

Some of these features are already in development, including order queueing and real-time voice queries into MEDITECH.

Dr. Burnham shared, “There’s a lot more we can do, but the pace we’re moving at is faster than I ever expected in a system of this size, with an EHR of this size.”

‍

Advice for Other Health Systems Considering AI

For leaders exploring ambient documentation or clinical AI tools, Dr. Burnham offered straightforward guidance:

“Having the folks who are willing to partner with you... that’s what you need to build a great product.”

He underscored the importance of involving providers early and often, and building a system that allows feedback in real time. All levels of the organization need to be bought-in, from senior levels of leadership down to end-users.

“The easier that is, the easier the change can be made... because we all practice differently, we all train differently. No one of us writes notes the same.”

Reclaiming Time in Medicine with Ambient AI

Commure Ambient AI has helped transform documentation from a burden into a streamlined, provider-friendly process at Medical City Dallas. But perhaps most importantly, it’s given time back to clinicians, so they can give more of it to patients.

As Dr. Burnham summed it up, “I think probably for most of us, 10% of your day is actually practicing medicine and the other 90% is writing notes or doing billing. This helps shift that balance back to where it should be.”

‍

Learn More About Ambient AI for MEDITECH