Commure Up Close: Kaila Drives Measurable Growth Through Data-Driven PR and Marketing Programs

North East Medical Services (NEMS) is one of the largest community health centers in the United States serving the medically underserved population offering linguistically competent and culturally sensitive healthcare services in many languages and dialects, but off the shelf AI technology couldn’t handle real-world conversations that switch languages, dialects, and even topics mid-sentence. To solve this, NEMS Chief Information Officer, Murali Athuluri, turned to Commure. What followed was a close partnership with Commure’s Forward Deployed Engineering (FDE) team to build a fully integrated Ambient AI solution, customized for their workflows, embedded within Epic, and built to support every voice in the room.

“What inspired me to work with Commure: Forward Deployed Engineering.” – Murali Athuluri, Chief Information Officer, NEMS

Watch the testimonial video below and read the article summarizing his keynote session at this year’s Commure Nexus to learn more about why they chose Commure, the experience working with Commure’s FDE team, and the impact of Ambient AI on clinician time.

Why NEMS Needed a Tailored Approach to Ambient AI

NEMS is dedicated to providing linguistically competent healthcare services in many languages and dialects including English, Cantonese, Mandarin, Spanish, Vietnamese, Burmese, Tagalog, and Hindi. Traditional off-the-shelf Ambient AI solutions couldn't meet their unique needs.

Murali framed the problem clearly: "Our mission is to provide culturally sensitive and linguistically competent care...Any AI solution must be able to serve the voice in the language of the patient."

What made this particularly challenging, Murali explained, was the need for "a personalized ambient solution for NEMS and for every provider that works for NEMS," that also integrated seamlessly with Epic. The solution had to work fluidly across encounters that often blend languages, switch dialects, and even topics mid-conversation: 

"We're having patients having conversations in Chinglish i.e. Chinese and English at the same time. We're talking about baseball. We're talking about their children, their daycare issues, and we’re also talking about their knee pain or chronic blood pressure."

How Forward-Deployed Engineering Was a Game-Changer

Forward Deployed Engineering (FDE) is a software delivery model where engineers are embedded directly within organizations, working closely with frontline staff and IT teams. Unlike traditional software and IT approaches that rely heavily on distant project management, FDE emphasizes on-site collaboration, rapid prototyping, and iterative design.

Before selecting Commure, NEMS carefully evaluated multiple vendors. “Commure distinguished itself by deeply understanding and integrating into the real moments of care—where providers and patients connect. Their ability to deliver a truly seamless, compassionate solution at the point of care made them the clear choice.”

Murali recounted how Commure’s team didn’t just understand the challenge but integrated themselves fully into the solution: "Max Krueger [Head of Forward Deployed Engineering at Commure] and team would show up after 7 p.m. encounters, sit with the doctors along with the patient and figure out exactly how it needs to work." That level of commitment set a new bar for partnership. It wasn’t just about delivering software; it was about co-creating care experiences tailored specifically for NEMS.

Max Krueger, Head of FDE at Commure, highlighted the importance of the physical proximity of end users to the process, describing FDE as "a contact sport. It's being on the ground so that we're able to quickly understand the problems and quickly iterate a solution for these physicians, administrators, and patients." 

Partnership in Action: FDE’s Impact at NEMS

Since beginning their partnership in October 2023, Commure’s engineers have continued to work closely alongside NEMS' clinicians, turning late nights spent with physicians and providers into early wins via custom-tailored high-impact solutions.

One major achievement was developing support for more than 20 sub dialects of Cantonese and handling real-time multi-language switching during patient encounters. Murali noted, "We were able to deliver ambient solutions eloquently in Cantonese, Mandarin, Vietnamese, Spanish, Tagalog, Hindi, and others."

The partnership has already yielded measurable results:

• Over 13,000 ambient encounters documented across multiple languages.
• More than 50 providers are actively using Commure Ambient AI daily.
• An average of 5.2 minutes saved per patient encounter.
• Significant improvement in provider-patient interactions and a marked reduction in documentation workload, achieving what NEMS refers to as 'keyboard liberation.'

Murali shared the transformative impact, saying, "Our doctors are spending more time looking into the eyes of the patient and delivering what they truly meant to deliver. Joy of Medicine!"

Commure’s Ambient AI Technology Now Integrated into Epic Toolbox, Enhancing Clinical Efficiency and Patient Care

Epic remains an essential system of record for NEMS with core workflows particularly for data safety and compliance. However, Commure Ambient AI is leveraged to extend the functionality of Epic to fulfill specific patient experience goals, particularly compassionate and linguistically competent ambient documentation.

Murali emphasized, "If there is a workflow optimization that we can achieve by going out to the external market, we will push the boundaries of Epic to make it happen."

What followed was a collaborative effort that extended the functionality of Epic. Commure’s engineering team worked closely with NEMS to integrate Ambient AI directly into Epic modules—including Haiku and custom flow sheet fields—enabling advanced documentation experiences without disrupting provider workflows.

In a decisive move to advance clinical innovation, Murali (Muralimohan) Athuluri, Chief Information Officer, directly engaged Epic leadership to champion the integration of Commure’s Ambient AI technology. “I spoke to Epic and said, ‘This is one partner—Commure—where the collaboration truly works for us, with proven results to show for it,’” said Athuluri.

That advocacy led to the development of productized integrations that embed Commure’s Ambient AI seamlessly into Epic’s infrastructure. As a result, Commure Ambient AI is now officially available in the Epic Toolbox under the Ambient Voice category.

This integration marks a significant milestone in the evolution of ambient clinical intelligence. By reducing documentation burden and streamlining workflows, it empowers clinicians to focus more fully on patient care—enhancing both provider satisfaction and patient outcomes.

Rather than working around Epic, NEMS and Commure worked through it, demonstrating that health systems don’t have to choose between compliance and innovation. With the right partner, they can have both.

Lessons for Health Systems: Scale, Strategy, and Mindset

The NEMS-Commure collaboration demonstrates the power and scalability of Forward Deployed Engineering. More than a technical strategy, FDE represents a shift in mindset, prioritizing provider and patient experiences and iteratively co-developing solutions.

Dhruv Parthasarathy, CTO at Commure, summarized this mindset clearly: "Customization is what we love. I get more customization over my coffee at Starbucks and my pizza at Domino's than software running my health system. That has to change."

EHRs like Epic, while critical, should serve as a robust foundation upon which innovation and differentiation are built. Health systems must define their strategic priorities clearly and partner with innovators who can co-create tailored solutions to enhance patient experience, provider satisfaction, and operational efficiency.

The partnership between NEMS and Commure proves what is possible when software is built with providers rather than just for them through true co-innovation. See how FDE can transform your health system.

Discover What's Possible with Ambient AI

Since ChatGPT became a household name in 2023, generative AI has made strides in re-shaping nearly every industry: healthcare is no exception. In just the last year, AI adoption among U.S. physicians has surged from 38% to 66% (up 78% from 2023), with health systems deploying AI to automate documentation, streamline operations, and proactively manage revenue. With generative AI gaining clear traction in healthcare, health systems must thoughtfully partner to adopt solutions that work with their systems and can drive measurable impact across clinical, financial, and operational workflows.

This post explores how forward-thinking healthcare organizations are deploying generative AI today, with examples across three high-impact areas: documentation, denials management, and Agentic AI.

What Is Generative AI in the Context of Healthcare?

Generative artificial intelligence (AI) refers to algorithms (often built on large language models (LLMs)) that can create new content such as text, code, audio, video, and more. In healthcare, generative AI powers a range of use cases: generating clinical notes from patient encounters, drafting patient instructions, summarizing medical histories, assisting with intake, generating appeal or referral letters, and helping revenue cycle teams identify and correct claims issues. These capabilities are transforming how work gets done across the entire healthcare ecosystem.

Unlike narrow automation tools, generative AI is flexible and adaptive. The key to success in healthcare isn’t generic capability; it’s domain-specific context. Generic models can introduce risk if they fail to understand medical terminology, misinterpret clinical nuance, or violate data standards. That’s why Commure builds AI specifically for healthcare, with native understanding of clinical language, healthcare data standards like HL7 and FHIR, and the operational realities of care delivery.

Healthcare Generative AI Use Cases

1. Reclaiming Time with Ambient AI

Clinical documentation is one of the most time-consuming burdens for providers, with physicians spending an average of 15.5 hours per week on paperwork and administrative tasks. Ambient AI helps solve this by passively listening to patient-provider conversations and generating structured medical notes in real time. No prompts, no typing, and no follow-up dictation required.

Commure Ambient AI integrates directly with leading EHRs, allowing clinicians to validate and finalize notes with just a few clicks. This eliminates after-hours documentation and reduces workflow disruptions from toggling between systems, two common causes of burnout. By streamlining this process, providers can focus fully on patient care and finish charting before the end of the day.

2. Fixing Denials Before They Happen

Denials are one of the most overlooked drivers of revenue leakage in healthcare, with more than 50% of denied claims never being reworked. The problem is rarely clinical; it's administrative. Poor documentation, coding inconsistencies, and missing attachments can all lead to delayed or denied payments.

Generative AI helps address the root causes of denials before they occur. Commure’s RCM product analyzes prior claim history, payer rules, and current documentation in real time to surface missing elements or inconsistencies before submission. It also learns from previous denials to proactively catch issues others would miss.

This approach transforms denials from a reactive cleanup problem into a preventative quality control process. The result: less rework, fewer delays, and millions saved. At one health system, Commure uncovered over $3.2 million in annual losses due to preventable denials—about 5% of total ARR. These savings were achieved not by cutting corners, but by tightening up workflows and reducing friction between clinical and billing systems.

3. Agents as the Glue Across Workflows

Commure Agents represent the next evolution of generative AI, with agentic AI. They move beyond passive LLM tools to become autonomous, goal-driven systems tailored specifically for healthcare. While traditional generative AI responds to user prompts, agentic AI takes it a step further: identifying tasks, orchestrating actions across systems, and executing complex workflows end-to-end.

These agents aren’t generic. Each one is purpose-built for a specific function, such as verifying insurance, scheduling patient appointments, or managing intake, and is configurable to align with each organization’s policies, EHR environment, and operational structure. They complete tasks faster and proactively anticipate what needs to happen next, based on real-time data and historical patterns.

By embedding agents across clinical, financial, and operational teams, Commure gives health systems a scalable way to automate intelligently without relying on fragmented, inflexible tools. The result is a more connected enterprise, where frontline teams are supported, not overwhelmed, and where automation adds precision instead of complexity.

Why Purpose-Built AI is a Necessity

Off-the-shelf generative AI tools may seem appealing, but they rarely hold up to the complexity of healthcare. Clinical nuance, regulatory requirements, and system interoperability demand more than just a general-purpose chatbot or note generator.

That’s why Commure takes a fundamentally different approach—pairing powerful AI models with Forward Deployed Engineering teams who work side by side with healthcare organizations. These teams dive deep into each customer’s workflows, systems, and pain points to configure, adapt, and optimize the AI for real-world use. The result isn’t a one-size-fits-all product; it’s a tailored solution built for the realities of care delivery, billing, and operations.

Generic models can hallucinate, introduce compliance risk, or fail to meet documentation standards. But Commure’s purpose-built AI systems are trained on healthcare-specific data, continuously improved in the field, and deployed with safeguards that ensure accuracy and clinical alignment.

Commure Agents aren’t layered on top of healthcare tools such as EHRs and other IT systems; they’re integrated into them and supported by hands-on engineering that ensures they perform across the entire healthcare enterprise.

Unlocking Efficiency at Scale with Generative AI

Generative AI isn’t just another tool—it’s a strategic foundation for scalable transformation. When embedded across clinical, financial, and operational workflows, it enables health systems to work faster, reduce administrative overhead, and extend the impact of every team. With purpose-built, agent-driven solutions, organizations can move beyond isolated automations toward a unified approach that improves care delivery, operational performance, and financial outcomes.

Explore how Commure is leading this shift across the full spectrum of healthcare operations.

‍
Speak to an AI Expert

Today we are excited to share that Commure has raised $200 million in growth financing from General Catalyst’s Customer Value Fund (CVF). The funding will be used to meet the surging demand for our full-stack AI platform, which spans revenue cycle management (RCM), Ambient AI clinical workflows, and practice management solutions. Our portfolio of solutions include:

• Revenue Cycle Management (RCM): From eligibility checks to payment posting, we streamline the entire billing process with AI, to help make health systems more efficient and profitable.

• Ambient Documentation and Workflows: Real-time note generation, autonomous coding, and clinical guidance to reduce after-hours charting (plus clinician burnout) and increase documentation quality.
  ‍‍
• Practice Management OS: A cloud-based operating system with AI agents that unify patient scheduling, engagement, and task orchestration across fragmented EHRs.

How are we using the investment?

CVF enables fast-growing companies that operate a proven, repeatable go-to-market approach. Our annual recurring revenue has doubled three years in a row, with one of the largest ambient AI rollouts in the country underway at HCA Healthcare.

We will use the investment to:

• Product development to deliver more product innovations faster. We’ll focus on deepening automation and intelligence throughout our portfolio. 
• Go-to-market expansion to reach more providers, faster. We’ll speed up implementations to reduce time-to-value for our customers. And we’ll expand access to our platform across new health systems. 
• Customer onboarding and success to ensure every deployment achieves real outcomes. We want to drive measurable improvements in financial and clinical performance.

Ready to transform your health system?

Join more than 130 health systems, support hundreds of thousands of clinicians, and power billions of dollars in annual revenue cycle volume.  Whether you're looking to boost revenue cycle efficiency, reduce documentation burden, or modernize practices management, let's talk!
‍

‍Schedule a Demo

You likely had several options — why did you choose Commure?

Sidharth Raguraman, Product Manager (BS in Computer Science/Business Administration + MS in Computer Science ‘20): I was really bought in on the mission of improving how healthcare is delivered in America. During the interview process, I was impressed by how deeply embedded the team was — team members spent time in hospitals, spoke with doctors daily, and treated provider and patient happiness as their north star. I also appreciated how every employee was seen as a leader, responsible for driving outcomes, owning decisions, and building with a strong sense of autonomy. It felt like a place where I could grow quickly while working on something that truly matters.

Shubham Maheshwari, Software Engineer (MS in Computer Science ‘24): What drew me to Commure was the culture of ownership. From the very beginning of the interview process, it was clear that this is a place where engineers are trusted to take initiative and drive meaningful work. That kind of environment really stood out to me.

Ansh Mehta, Software Engineer (MS in Computer Science ‘24): Commure’s mission to build technology that is obsessively focused on how healthcare can be improved for everyone involved, including patients, doctors, and the admin staff is incredible. The chance to explore areas like product and research while still growing as an engineer was super exciting to me. It felt like a place where I could really stretch myself and contribute in meaningful ways from day one.

Lucas Huang, Software Engineer (BS in Computer Science + MS in Applied Data Science ‘23): It’s one thing to build interesting software, but knowing that your work as an engineer can directly impact someone else’s health journey is powerful, and it made Commure stand out from the very start. What really sealed the deal, though, was the people. From the first interview, it was clear to me that this was a team that emphasized empathy, both professionally and personally. 

Tyler Neilon, Senior Revenue Operations Analyst (BA in International Relations: Global Business, Minor in Business Economics ‘18): I had originally found Athelas’ novel blood testing device (Athelas One) and became very interested in its story. After reading more about the company and the leadership, I felt that there was significant potential in the company to reshape the healthcare landscape beyond just the device they had invented. The mission of reshaping healthcare for patients and practitioners is really felt and believed in by everyone at the company, and it shows with everyone I spoke with and have met since. Then you take a look at who the leaders and backers of our company are and what they believe, and it leaves no doubt about the goals for the company. I thought that was very powerful. Commure has a very broad mission, but is doing it very methodically and through different avenues of technology that will reshape the entirety of the industry.

‍

‍

How have you grown?

Sidharth: I’ve had the chance to work with some incredible designers at Commure, and it’s taught me a lot about what it takes to build truly delightful user experiences. I’ve learned how thoughtful design can simplify complex workflows, reduce cognitive load, and make a product feel intuitive, even in a space as dense as healthcare. They’ve also helped me be a better advocate for users, ask the right questions during product discovery, and approach problems with empathy.

Shubham: I’ve learned how to break down complex problems, write scalable code, and make thoughtful technical decisions. At the same time, I’ve become more confident working cross-functionally—whether it’s aligning with the operations team or discussing trade-offs with teammates. The fast-paced, collaborative environment has really pushed me to improve every day.

Ansh: Being my first job out of school, the growth has been huge. I’ve learned so much—not just in terms of writing better, cleaner code, but also in how to collaborate effectively across teams and communicate clearly. Whether it’s sprint planning, code reviews, or brainstorming with the product team, I’ve really leveled up both my technical skills and how I work with others. It’s been a great environment to learn by doing, with a lot of support along the way.

Lucas: Growth has come in so many different ways here. I came to Commure with the initial goal of expanding my technical depth as significantly as possible, and I’ve enjoyed the constant learning cycle of picking up cutting-edge technologies and applying them to real-world challenges. I can honestly feel the difference: ideas and questions that I used to express in hushed tones are now shared with earned confidence and as straightforward suggestions.

Tyler: The mission being as big as it is and the pace at which we want to achieve it gives you so many opportunities. I have been able to take on a ton of responsibility in a short amount of time and get to learn and work with some of the best and brightest in their respective roles. I really like being a problem solver with little limitations on what to work on.

‍

‍

What’s something you love about your team that has nothing to do with work?

Sidharth: One thing I really love about my team is how supportive everyone is, not just at work, but outside of it too. Whether someone’s training for a marathon, competing in martial arts, or experimenting with a new recipe, there’s always genuine encouragement and interest. It creates a culture where people show up for each other as full humans, not just coworkers, and that makes the work environment feel a lot more meaningful.

Shubham: Everyone on the team is incredibly helpful—no matter how many questions I have, there’s always someone willing to take the time to walk me through things. Beyond that, I’m constantly inspired by how talented and driven the people here are. It’s motivating to be surrounded by such high-caliber individuals.

Ansh: Honestly, it’s how easy it is to connect with everyone beyond just work. Whether it’s sharing random memes, grabbing lunch, or just catching up on life during stand-ups, the team has such a fun, down-to-earth vibe. It makes the day-to-day so much more enjoyable when you’re working with people you genuinely like being around.

Lucas: Our spontaneity! You might see a random message in the boba order channel at 12:43 PM. Or on NBA playoff game night someone drags in a projector and all of a sudden we're shouting at the Warriors between code reviews. I definitely consider myself more of an introvert, but it’s been so effortless to feel welcomed at Commure. The open-office setup truly facilitates these spontaneous moments, and they knit the whole team together in a way where trust is second nature and taking social initiative is easy.

Tyler: There are plenty of people who have varied interests and want to connect on things outside of work. I’ve been able to connect with people over sports, travel, skiing, and plenty of other things.

‍

‍

What would you tell another USC student considering Commure today?

Sidharth: Commure is one of the best places for a new grad. It’s rare to be given this much trust and responsibility so early in your career. You’re not just shipping features - you’re making a real impact on American healthcare and building products you can genuinely be proud of.

Shubham: If you’re looking to make a real impact and want to keep learning every day, Commure is the place to be. It’s a fast-moving environment where your work truly matters—and you’ll grow a lot, both technically and professionally.

Ansh: I’d tell them—go for it. If you're looking for a place where you can make a real impact, take ownership early, and learn from some seriously talented people, Commure is an amazing choice. It’s a great environment to grow fast, explore different areas beyond just engineering, and work on something that actually matters in the real world.

Lucas: Take the leap! If meaningful work, constant professional growth, and a supportive community are priorities, I honestly believe Commure has exactly what you’re looking for. It's difficult to find a role where you can genuinely look forward to getting started each morning, but with the impact and learning opportunities here, I find the work inspiring in a way that is truly unparalleled. Plus, the excitement and kindness in the people at Commure are contagious—don't hesitate.

Tyler: If you want to work at the intersection of technology and healthcare, and know you helped change the healthcare industry. This is one of the most exciting places to work.

Ready to take the next step and start transforming healthcare? We’d love to learn about your background and share more about Commure.
‍

Explore Career Opportunities

Healthcare organizations stand on the brink of a major transformation. According to Dhruv Parthasarthy, CTO of Commure, the nature of healthcare companies is changing fundamentally. "What looks like a health system today will look a lot more like a technology company tomorrow," Dhruv explains. This evolution echoes shifts already witnessed in other sectors. Just as Amazon reshaped retail and cloud computing, and YouTube redefined media, healthcare organizations will soon recognize technology as a core capability, akin to clinical quality today.

Watch the full interview with Dhruv below or read the key takeaways, which detail Commure's commitment to helping health systems make the transition to technology-driven enterprises.

Empowering Health Systems to Build Like Tech Companies

Commure's approach to enabling this transformation revolves around a layered technology architecture. At its foundation lies a robust, unified data layer. Dhruv emphasizes, "We really believe that having a really excellent data abstraction layer is the foundation of a good technology business." This unified foundation ensures clarity, accuracy, and accessibility across healthcare applications.

Building on top of this data layer, Commure facilitates seamless application integration. Dhruv highlights that "We're designing all our data abstractions to make it such that health systems can easily deploy either our applications...or their applications." Additionally, Commure leverages advanced large language models (LLMs) for unprecedented customization capabilities.

This philosophy represents a shift from traditional health IT, where systems are typically siloed, difficult to integrate, and require extensive manual customization. Commure is flipping that model. Rather than forcing health systems to conform to a rigid software product, the platform is designed to empower them to create and evolve their own digital infrastructure with ease. The goal isn’t just better software, it’s to equip health systems with the tools and flexibility they need to think and operate like modern technology organizations.

Designing for Safety, Iteration, and Scale

Healthcare technology development inherently grapples with a crucial paradox: rapid innovation versus stringent safety requirements. "The safety margin has to be really large...think auto industry times 10," explains Dhruv. To navigate this, Commure employs a unique simulation-based approach, refining solutions within small, agile practices first.

These smaller healthcare practices act as innovative testbeds, enabling Commure to rapidly prototype and refine before broader implementation. Dhruv describes this strategy clearly: "These small practices enable us to do cutting-edge work...and then take that same technology up to the biggest health systems in the world."

Complementing this technical strategy is Commure's quality-focused engineering culture. Drawing parallels with another industry leader, Dhruv asserts, "Apple as a culture is so meticulous...that's the same approach we're trying to take in healthcare." This level of precision is critical when technologies move from fast-moving clinical environments into large, complex health systems. Every detail, from how the software behaves under edge-case conditions to how it's documented for enterprise teams, must meet the highest bar. Commure’s engineering culture ensures that what works in a small clinic scales to large health systems.

Purpose-Built for Healthcare, Not Ported from Elsewhere

Healthcare isn’t just another vertical; it’s an ecosystem shaped by decades of deeply embedded workflows, regulatory complexity, and high-stakes decisions. Generic software often breaks down when applied to these environments because it lacks the clinical, operational, and compliance-specific logic needed to function effectively.

Commure’s approach is grounded in the belief that building software for healthcare requires the same level of domain knowledge clinicians bring to patient care. Dhruv puts it plainly: "We are a software company focused on healthcare. The same level of knowledge and awareness that clinicians have for their health systems, we have for their products and their use cases." This isn’t just a design preference; it’s a safeguard, minimizing costly implementation missteps, reducing user friction, and ensuring new technologies align with the way care is actually delivered. That knowledge is reflected in everything from how interfaces are designed to how data standards like HL7 and FHIR are handled natively from day one.

LLMs Will Reshape Clinical Work and Software Itself

Commure recognizes that LLMs dramatically lower the barriers and costs associated with software development and customization. But the impact of LLMs extends beyond coding.

Most of the industry is still focused on early applications like documentation assistance and voice-to-text transcription. But Dhruv foresees LLMs evolving into far more powerful tools: indispensable clinical co-pilots that support reasoning, recall, and recommendations at the point of care. "You won't have to know every little piece of data...that'll all be something an LLM uses," Dhruv predicts.

These systems can surface relevant medical literature, synthesize scattered patient information, and adapt to organization-specific protocols. Ultimately, this technology democratizes access to world-class healthcare, enhancing clinician capabilities and reducing burnout.

A Long-Term Transformation, Not a Quick Sale

Commure isn’t chasing quick wins or short-term implementations. Its focus is on building enduring partnerships that support longterm transformation. Dhruv emphasizes, "We're not really looking for 'buy this and we're out of here in the next year.'" Instead, Commure aims to work alongside healthcare organizations as they evolve into modern, tech-enabled enterprises.

This philosophy is reflected in the length and depth of its customer relationships. "Some of our earliest customers are now 20 years into their journey with us," Dhruv notes. That kind of longevity requires not just great products, but mutual trust, adaptability, and a shared commitment to innovation.

Commure’s platform is built to support this journey, helping health systems develop core technology capabilities that will serve them not just today, but for the next decade and beyond. Ready to see what the next healthcare powered by AI looks like in action?
‍

Speak With an AI Expert

Denied claims are one of the most overlooked drivers of revenue loss in healthcare. During an on-site discovery session, Commure found that one healthcare organization lost $3.2 million annually, or 5% of its ARR, due to unpaid outstanding balances. This was simply the result of a lack of infrastructure in place to efficiently triage, correct, and resubmit denied claims.

This is a both a grim and common state of affairs for healthcare practices. A recent study of 280 hospitals across 23 states found that:

• Adjudication of claims cost hospitals over $25.7 billion in 2023, marking a 23% increase over what was reported the previous year.
• Nearly 70% of denials were ultimately overturned, but only after several costly rounds of review. This means that healthcare practices incurred roughly $18 billion in unnecessary expenses.

Clearly, the inefficiencies of current systems contribute heavily to this enormous amount of wasted time and resources.

In response to this issue, Commure built out a proprietary AI Denial Automation System that automates away over 80% of denied claim reprocessing. This system decreases labor costs on denial resubmissions, increases claim resubmission volume, and significantly improves denial re-approval rates.

Understanding Insurance Claim Denials

Here’s a quick refresher on the relevant part of the lifecycle of a claim, illustrating just how many steps are involved and, consequently, how many opportunities there are for human error and for a claim to get stuck in process.

Payers deny claims constantly for all kinds of reasons. Figure 1 depicts the general flow of the section of the claim submission process in which denials occur.

Payers then send their decisions and any payments in the form of remittances. If the claim was denied, either fully or partially, they indicate the reasons for the denial with Claim Adjustment Reason Codes (CARCs) and Remittance Advice Remark Codes (RARCs).

While there are overall trends as to which CARC/RARC combinations most commonly occur, different practices often see spikes in denials for CARCs and RARCs unique to their practice or field. This is why Commure tailors automatic denial tracking and resubmission to each practice, rather than taking a one-size-fits-all approach.

We can see this phenomenon occur in the following sample data from two sites during Q4 of 2024. Figure 2 shows that nearly half of all denials for this practice come from CARC 59, the code for apparently concurrent procedures that get billed as individual procedures.

Figure 3, on the other hand, reveals that nearly three quarters of this practice’s denials are due to CARC 104, which indicates that a provider sent inadequate or incomplete supporting documentation for the services they rendered.

The potential lost revenue exceeds $250,000 in one quarter just from that single CARC. For a practice with $6.7 million ARR, needlessly losing $1 million a year because of missing documentation is painful.

In all cases involving manual claim recon and denial resubmission, humans are both far slower and more prone to error than machines and AI proactively detecting potential errors and executing established rules and flows. The longer claims take to process, the more expensive they get for the practice.

Some of the revenue lost to unworked denials will be written off, damaging the practice’s financial health. Some will be pushed onto patients, who end up paying or going into debt over getting medical care for which they should not be held liable. When denials are accepted not worked and resubmitted, patients and practices both lose.

This is why cheap and effective automation of both the initial claim submission process and denial resubmission process is increasingly crucial for healthcare practices. This is also where Commure’s proprietary rules engines and AI solutions shine.

How Large Language Models (LLMs) Can Prevent Denials Before Submission

What are LLMs?

Large language models (LLMs) are deep learning models trained on huge amounts of text data that can then perform a variety of natural language processing (NLP) and analysis tasks, including translating, classifying, and generating text. Due to the sheer breadth of their knowledge base, they can provide reasonably accurate answers to queries, even in the absence of specifically labeled examples.

Data Ingestion & Analysis

At Commure, we train our LLMs on a massive corpus of historical claims, payer denial responses, and policy documents. Our AI agent can fetch EOBs, work denials, and complete other repetitive tasks. They automatically leverage the resources of supporting LLMs and engines. For example, we utilize an LLM that tests data we extract from EHRs, and another that empowers human staff with precise recommendations for coding denials and rejections (Figure 4). The agents parse through payer documents and surface these coding recommendations with a 95% QA pass rate.

We use these agents to ingest encounter-level data from EHRs, remittances, and insurance responses to build a knowledge graph that can:

• Surface payer-specific denial patterns.
• Run deep research across structured and unstructured payer documents to extract specific policy nuances.
• Recommend compliant CPT, ICD, and modifier codes based on past success rates.

Pre-submission Validation

Commure’s LLMs validate claims in real-time by identifying missing fields, incorrect codes, and misaligned documentation. Submissions are automatically reviewed against payer-specific rules and historical data, with our AI agent, Scout, flagging errors and proposing corrections before submission.

In one workflow, for example, Scout automates submission integrity QA by validating claim formatting and billing rules—tripling QA coverage and significantly improving first-pass acceptance rates.

Integration with Existing Systems

Commure embeds LLM-based validation directly within systems like our database, Normandy, and external EHRs such as Athena and AMD. These tools automatically pull and reconcile patient, payer, and encounter data, ensuring seamless pre-submission verification.

Automating Denial Management and Resubmission

Automated Denials Explanation Analysis

Commure’s LLMs extract denial reasons from insurer responses, mapping them to specific errors in the original claims. In order to stay a step ahead, we also scrape payer policies and preemptively create rules in the rule engine to prevent denials based on recent payer policy changes.

In real-world deployments, Scout uses standardized templates to generate concise denial notes (Figure 5) that are automatically added to claims—automating 40% of related tasks with over 2,000 AI-generated notes weekly.

Intelligent Claim Modification

Scout and Denial Copilot suggest fixes based on prior approvals of CARCs/RARCs and payer policy interpretation. Whether it’s a missing authorization or a modifier mismatch, AI tools generate corrected claims and route them for immediate resubmission.

The authorization debugging workflow, for example, identifies prior auth numbers within EHRs and auto-resubmits if found. In cases where prior auth cannot be found, it can initiate AI calls to validate whether prior auth is required for the billed procedures, if the payer has it on file, and then reprocess the claim if applicable. LLMs will also summarize the key points of the phone call.

Figure 6, below, shows daily automatic claim modifications and resubmissions for a particular practice over a one-month period.

Autonomous Resubmission Process

Commure integrates with clearinghouses and portals via APIs and robotic workflows. For Medicare appeals, Scout extracts medical records, generates the appeal package, and submits it via portals like Novitas—achieving $127K in billed charge automation with zero human error.

AI Agents: Automated Calls for EOB Procurement

When an ERA is not received within the predefined SLA, our AI agents initiate automated outbound calls to payers to retrieve the ERA and extract any associated denial codes. This integration minimizes manual intervention in the A/R follow-up process. As of this writing, the system executes approximately 1,500 calls daily—automating 80% of related workflows and delivering annualized savings of $195,000, with continued efficiency gains expected.

Deep Dive Into Automated Denial Management

Let’s take a closer look at Commure’s process for rules establishment and management automation for the tens of thousands of denials that pour in every day.

As mentioned above, LLMs can customize our engines to evaluate, categorize, and resolve claim denials through rule-based logic and insurance detection mechanisms. We do this for each of our partner practices. This section breaks down how denials are classified and how we use structured batch submissions, enriched patient data, and external eligibility checks to drive intelligent claim resubmissions.

Denial Categorization by RARC/CARC/Payer

Every claim that enters our resubmission pipeline is first evaluated to determine the type of denial it encountered and track which payers consistently send which kinds of denials:

• Coverage-related denials (identified by specific CARC and RARC codes) are prioritized for automated eligibility verification.
  • For example, (CARC) CO 22 indicates denial due to care that may be covered by another payer per coordination of benefits. All CO 22 denials will therefore enter this category and corresponding workflow.
• Other denial types may be resolved through standard workflows without invoking insurance detection.
  • Diagnosis and modifier code denials are good examples here.
  • Note that once eligibility and coverage are established, all other possible reasons for denial are analyzed and remedied at once. The claim is then sent through our engine again in a dry run prior to resubmission.

For coverage denials, our engine checks for updated patient insurance information (PII) and validates it with real-time eligibility checks. If active coverage is confirmed, a new claim submission is created. If not, the system prepares to engage insurance detection.

Change in Submission Payloads

When a denial progresses to resubmission—especially one influenced by insurance detection—the claim payload must adapt dynamically. Key components updated in the payload include:

• Insurance company ID (determined via match against historical claims or clearinghouse results)
• Subscriber/dependent information (pulled from eligibility response or existing PII)
• Coverage priority (inferred based on denial type, existing insurance, and returned coverage)

We leverage an [upsert_verify_and_submit_claim_correction] endpoint, passing a [fields_to_update_dict] to make direct, surgical updates to claims without requiring custom rules engine invocations. This approach mirrors how manual claims are currently corrected.

Listening for and Acting on Denial Batches

Our system processes denied claims in batches of 500, drawn via [_get_denied_claims_to_analyze]. These are inserted into a tracking table [resubmission_batches], where each claim is marked with [has_run_completed = False]. Claims are processed individually, and this flag is updated accordingly.

Once all claims in a batch are marked complete, we check—under DB-level locking—that no [has_run_completed = False] entries remain. Only then do we trigger insurance detection for that batch, ensuring batch integrity and avoiding duplicate processing.

Insurance Detection Flow

For claims reaching the insurance detection stage, the following workflow is used:

1. Tracking:
   • Unique patient/DOS combinations are logged in [insurance_detection_resubmission_tracking], preventing duplicate inquiries within a defined time frame.
   • If a matching entry exists but lacks a usable result, the system skips resubmission and awaits response.
2. Submission:
   • Claims eligible for detection (new or failed past attempts) are batched into a [.COV] file and sent to our clearinghouse via SFTP.
   • Each request is logged in [insurance_detection_batches], and individual inquiries are stored in [insurance_detection_checks], linked by [batch_id].
3. Ingestion and Matching:
   • Periodic jobs parse clearinghouse response files into [insurance_detection_check_details], using file name correlation for mapping.
   • These results determine next steps for each claim.

Automated Resubmission Logic

When eligibility results are returned, we assess whether a claim can be auto-resubmitted:

• Active coverage with a match score of [STRONG], [PROBABLE], or [PROBABLE_NO_ADDRESS] is required.
• We map clearinghouse payer data to our internal insurance company records, using:
  • Historical claims at the site
  • Encounter billing type (PROFESSIONAL, INSTITUTIONAL, WC)
  • Payer name and clearinghouse payer ID
• Priority logic distinguishes between primary and secondary claims based on denial reasons and available coverage.

If subscriber or dependent information is missing, fallback strategies pull PII from our database, provided the relationship is verifiable. If any required fields are missing and cannot be inferred confidently, we escalate the claim to manual review.

This streamlined, rule-driven approach allows our LLMs to intelligently manage denials, adapt submissions, and reduce manual overhead, while maintaining strong safeguards around data accuracy and claim validity.

Overcoming Implementation Challenges

Commure ensures full compliance with HIPAA, GDPR, and payer-specific mandates by implementing:

• End-to-end encryption
• Role-based access control
• Detailed audit logs

Data Security and Privacy Risks

All patient data processed by Scout is encrypted in transit and at rest. The system’s architecture follows zero-trust principles and ensures minimal human access to PHI.

Model Accuracy and Explainability

LLM-driven decisions are made transparent via audit trails, human-readable recommendation logs, and QA pipelines that validate every automated task. Denial Copilot and EOB Copilot include explainable AI features, with manual override options.

Adoption by Healthcare Providers and Insurers

To build trust, Commure delivers measured rollouts and demonstrates measurable cost savings—e.g., $100K+/year from eligibility detection automation alone
‍

The Future of AI in Insurance Claims Processing

As models improve, we anticipate:

• Real-time adjudication: AI-powered negotiation and approvals during patient encounters.
• Proactive coverage detection: Automated and highly accurate eligibility checks before services are rendered.
• Expansion beyond claims: Fraud detection, personalized billing plans, and real-time patient financial education.

The trajectory is clear: AI will soon be a copilot across all of RCM—not just denials.

Commure is reshaping medical claims processing with scalable, accurate, and autonomous AI agents. By preventing denials before submission, streamlining rework, and integrating deeply with existing systems, Commure reduces costs, enhances accuracy, and improves outcomes for providers and patients alike.

With 80% of RCM already automated and a roadmap to reach 95%, Commure invites industry stakeholders to explore what AI-driven claims processing can unlock for the future of healthcare.
‍

Explore AI-Driven RCM

Many thanks to all the engineers who lent their expertise for this blog post: Rithesh Shetty, Jasu Mandakh, Yash Wani, Jasdeep Grover, Jordan Chow, and Thuy Ngo. You all do incredible work.

The healthcare industry is experiencing a rapid shift in how clinical documentation is handled, driven by mounting pressure to reduce clinician burnout, close revenue gaps, and streamline operations at scale. Traditional approaches like manual note-taking and point-solution scribes no longer meet the demands of modern healthcare delivery.

AI-powered documentation tools have been gaining traction to help relieve that burden. But not all solutions are equal. Two terms frequently used in this space—AI Scribe and Ambient AI—describe fundamentally different approaches. One offers a tactical fix; the other, a platform-level upgrade.

This post breaks down the difference between the two, how each functions, and why more health systems are shifting to ambient AI that integrates deeply with EHRs, ties into revenue workflows, and delivers measurable impact across both the front line and back office.

What Is an AI Scribe?

An AI Scribe is a digital tool that uses speech recognition and natural language processing to generate clinical documentation from doctor-patient conversations. These tools are typically standalone apps that record the visit, transcribe the audio, and produce a draft note for the provider to review and sign.

Most AI Scribes are built to assist only during the visit. They don’t integrate deeply with EHRs, they don’t support pre-visit preparation, and they don’t automate downstream tasks like coding, quality reporting, or referrals. As a result, they operate outside the core clinical and financial systems, requiring providers to make manual edits to ensure accuracy or completeness.

For many health systems, AI Scribes serve as an entry point into ambient-style documentation. But because they are disconnected from broader workflows, they’re difficult to scale and often add parallel processes that limit enterprise-wide impact.

What Is Ambient AI in Healthcare?

Ambient AI in healthcare is technology that automatically generates clinical documentation and supports provider workflows before, during, and after the visit, without requiring manual note-taking.

Unlike AI Scribes, which focus solely on transcription, Ambient AI is designed to support the entire clinical workflow. It integrates directly with the EHR to enable real-time documentation, pre-visit context gathering, and post-visit automation like coding and referrals.

This level of integration turns Ambient AI into more than a documentation tool by drafting notes, surfacing relevant patient data, suggesting codes, and reducing manual overhead for providers. Across the industry, clinicians using ambient AI tools report time savings of anywhere from 25% in the case of A&A Women's Health to 41% for Dignity Health. Burnout levels are also decreasing, with one industry report noting a 60% drop in self-reported burnout after adoption (which correlates directly to increased retention).

Where AI Scribes offer a point solution, Ambient AI functions as an operational layer that can scale across departments, connect with downstream systems, and drive long-term efficiency across both clinical and financial workflows.

AI Scribe vs. Ambient AI: A Side-by-Side Comparison

Now that we've outlined what each tool does, here’s how they compare directly. The table below breaks down the major differences between AI Scribes and Ambient AI across common decision-making factors:

At Commure, we’ve developed a tiered approach to Ambient AI that gives health systems flexibility based on their needs, workflows, and desired level of support. The chart below outlines the differences between our three tiers so teams can see exactly what each level offers in terms of time savings, automation, and human-in-the-loop services.

Why Ambient AI Is the Right Tool for the Future

The documentation burden isn’t going away, nor is the pressure on health systems to improve efficiency, reduce burnout, and operate with leaner resources. While AI Scribes can help with note-taking, they don’t address the broader workflow challenges. Ambient AI goes further, streamlining documentation and tightly integrating with the systems clinicians already use.

A platform-powered approach to Ambient AI is what unlocks its full potential. When ambient tools are embedded within the EHR and connected to back-office functions like autonomous coding and revenue cycle workflows, they save time while helping to close the loop between documentation, billing, and reimbursement. This end-to-end visibility and automation is essential for health systems trying to scale care while maintaining financial stability.

If your organization is still relying on narrow scribe tools, it may be time to evaluate whether they’re built for where healthcare is headed. The next wave of documentation technology is already here—and it’s ambient.

Explore how Commure Ambient AI can help your team work more efficiently, reduce burnout, and deliver better care.
‍

See How Ambient AI is Different

For our inaugural healthcare leadership summit, Commure Nexus, connection, innovation, and collaboration were the main focus. By bringing together more than 50 healthcare leaders, clinicians, technologists, investors, and partners under one roof, we created a space to confront some of healthcare’s toughest challenges—together. 

“It’s been really great to see all of the top hospital systems that are here, who have already been working with Commure so we can see what all the possibilities are.” – Gian Varbaro, MD, MBA, Chief Medical Officer & VP, Ambulatory Services, Bergen New Bridge Medical Center

‍

Throughout the day, leaders heard from some of the most forward-thinking voices in healthcare and technology:

• Hemant Taneja, CEO and Managing Director of General Catalyst, and Tanay Tandon, CEO of Commure, kicked off the day with a visionary keynote on cutting-edge innovations in agentic AI, ambient AI, workflow automation, and enterprise intelligence technologies that are shaping the future of healthcare.
• Dr. Stephen Klasko shared a futurist’s forecast of AI’s role in healthcare technology in the next ten years, and the profound impacts that will have on how care is delivered. 
• Dr. Jamie Colbert, Chief Medical Officer of Commure led a panel discussion with Executives from HCA Healthcare, Bergen New Bridge Medical Center, and Compassus. They shared practical lessons and insights from partnering with Commure and deploying Ambient AI across EHR environments and care sites. 
• Murali Athuluri, Chief Information Officer of North East Medical Services, joined Dhruv Parthasarathy, Chief Information Officer of Commure, and Max Krueger, Head of Forward Deployed Engineering at Commure, to discuss how the Commure’s co-development model accelerates real-world impact.
• Dr. Ashish Atreja, a Professor of Medicine at UC Davis and Founding Chair of Valid AI, and Ian Shakil, Commure’s Chief Strategy Officer, explored how platform-based Ambient AI is streamlining documentation, coding, and clinical efficiency.
• Dr. Naqi Khan, Lead Physician Executive for Healthcare and Life Sciences Solutions at Amazon Web Services (AWS) closed the main sessions with a keynote on the power of AI, ML, and cloud infrastructure to transform healthcare at scale.

Commure Nexus was a chance to step out of the everyday, listen deeply, and build with intention and urgency.

“Commure Nexus is such a special event because it brings together Commure’s best and brightest builders with healthcare’s top executives—all in one place. We’re collaborating closely, going on a listening tour of the real-world problems these leaders face every day. And in the next 48 hours, our teams are shifting immediately into building mode. Speed-above-all-else for our customers—faster than anyone thought possible.” – Deepika Bodapati, COO, Commure

‍

When people come together, so do ideas, vision, and a shared drive for change. Commure Nexus is just the beginning of forging deeper, cross-industry partnerships—and we’re already looking forward to what’s next.

Watch the highlights below and stay tuned for deeper session recaps and speaker interviews over the next several weeks.