AI Medical Receptionist Modernizing Doctor Appointments

A virtual medical receptionist named "Cassie," developed through research at Texas A&M University, is transforming the way patients interact with health care providers.

Cassie is a digital-human assistant created by Humanate Digital, a startup founded by three Aggies, including Dr. Mark Benden, professor in the Texas A&M School of Public Health and director of the Center for Worker Health.

The artificial intelligence-powered avatar can speak more than 100 languages, including American Sign Language, and uses facial recognition to mimic human emotions, making interactions feel more natural and comforting.

Cassie is being tested in several clinics to assist with administrative tasks such as checking in patients, requesting medical records and guiding users through paperwork. "We're not trying to replace doctors or nurses," Benden said. "We're focused on the administrative side - tasks that are repetitive, time-consuming and not the best use of a clinician's time."

At the 2025 Texas A&M New Ventures Competition last month, Humanate took home the grand prize, including $35,000 in funding and multiple investment offers, for its work on the Cassie technology.

A key differentiator from early research is that Cassie was developed to be emotionally responsive, using facial recognition to read the user’s expressions and adjust its tone accordingly. "Our goal is to provide a happy digital human to have a conversation with you. She can smile, interact, tell dad jokes — even mimic your mood. But if you’re on a serious topic, like a cancer diagnosis, she can become more serious, more focused,W Benden said.

Unlike traditional kiosks or chatbots, Cassie offers a two-way interaction that feels more like a conversation than a transaction.

Benden said the technology has potential applications in pediatric care - Humanate is developing a cartoon-style avatar named Oliver to help children navigate medical procedures. "Oliver would guide a child through something that might be kind of scary and stay with them throughout, on a mobile device, for comfort and engagement," Benden said.

Cassie was conceived during the COVID-19 pandemic as a tool to train remote workers but has since evolved into a sophisticated AI assistant thanks to advances in large language models and a key partnership with AI technology innovator NVIDIA.

"We started this five years ago to figure out a way to train remote office workers with the same confidence and quality we would have if we had a professional trainer in the room," said Benden, who co-founded Humanate with Carlos Rodriguez, company CEO and an A&M engineering graduate; and Leslie Jebson, who earned his MBA from Mays Business School and serves as company consultant.

"Before large language models, we had to guess what AI assistants might say and manually enter those responses," Benden said. "Now, Cassie can understand various accents and multiple languages, and provide more flexible and intelligent responses."

Rodriguez said Humanate Inc. is revolutionizing the patient-to-clinician interaction. "Our agentic AI technology is automating labor intensive work flows to increase access and produce better healthcare outcomes," he said.

Cassie is a potential solution to a growing problem in health care: administrative overload and staffing shortages, especially in rural or underserved areas. "These are jobs that turn over very often - 200 to 300% in a typical year," Benden said. "They're lower paying, and most days are pretty much the same; humans don’t necessarily like those kinds of jobs, and that’s why turnover is high."

Cassie can work 24/7 without breaks, sick days or distractions.

While Cassie may not immediately lower health care costs for patients, the technology can help clinics operate more efficiently - particularly those in financially vulnerable areas.

"A lot of smaller clinics - especially without federal money - don't make sense to run as a business; you would close them," Benden said. By reducing administrative burdens and freeing up clinicians to focus on patient care, Cassie could help stretch limited resources further.

"I think we can improve the quality of care, get more doctor-and-nurse time with the patient instead of with paperwork," he said.

The project advanced when Humanate collaborated with NVIDIA to run large-scale simulations that enhanced Cassie’s capabilities. This partnership helped move the technology from a research prototype to a deployable product. Humanate has licensed the Texas A&M-filed patent for its receptionist-focused AI, one of the early filings in the emerging field of agentic AI.

"If that patent pans out, then we hold something that’s highly significant in the field," Benden said.

For Texas A&M, Cassie represents more than just a technological achievement - it’s a testament to the university's role in fostering innovation with real-world impact. "We think health care is primed for this," Benden said. "They need to be disrupted because they're struggling to meet the needs."

Rodriguez hopes Cassie will not only streamline operations but also improve the patient experience - especially for those who find traditional systems confusing or impersonal. "We've had an amazing response from patients. Some of the older patients, in particular, have written to us and said, ‘It’s so much easier for me to talk to Cassie than to try to navigate confusing websites and mountains of paperwork,’" Rodriguez said. "That’s been very encouraging."

About Texas A&M Innovation

Texas A&M Innovation at College Station works with a diverse array of partners - including entrepreneurs, investors, technology incubators, and large enterprises - to improve lives by commercializing innovations from The Texas A&M University System. Texas A&M research generates more than 300 new technologies each year, providing abundant and varied opportunities for industry collaboration.

Most Popular Now

AI also Assesses Dutch Mammograms Better…

AI is detecting tumors more often and earlier in the Dutch breast cancer screening program. Those tumors can then be treated at an earlier stage. This has been demonstrated by...

RSNA AI Challenge Models can Independent…

Algorithms submitted for an AI Challenge hosted by the Radiological Society of North America (RSNA) have shown excellent performance for detecting breast cancers on mammography images, increasing screening sensitivity while...

AI could Help Emergency Rooms Predict Ad…

Artificial intelligence (AI) can help emergency department (ED) teams better anticipate which patients will need hospital admission, hours earlier than is currently possible, according to a multi-hospital study by the...

Head-to-Head Against AI, Pharmacy Studen…

Students pursuing a Doctor of Pharmacy degree routinely take - and pass - rigorous exams to prove competency in several areas. Can ChatGPT accurately answer the same questions? A new...

NHS Active 10 Walking Tracker Users are …

Users of the NHS Active 10 app, designed to encourage people to become more active, immediately increased their amount of brisk and non-brisk walking upon using the app, according to...

New AI Tool Illuminates "Dark Side…

Proteins sustain life as we know it, serving many important structural and functional roles throughout the body. But these large molecules have cast a long shadow over a smaller subclass...

Brain Imaging may Identify Patients Like…

By understanding differences in how people’s brains are wired, clinicians may be able to predict who would benefit from a self-guided anxiety care app, according to a new analysis from...

Deep Learning-Based Model Enables Fast a…

Stroke is the second leading cause of death globally. Ischemic stroke, strongly linked to atherosclerotic plaques, requires accurate plaque and vessel wall segmentation and quantification for definitive diagnosis. However, conventional...

The Human Touch of Doctors will Still be…

AI-based medicine will revolutionise care including for Alzheimer’s and diabetes, predicts a technology expert, but it must be accessible to all patients. Healing with Artificial Intelligence, written by technology expert Daniele...

Stepping for Digital Rewards

Walking is well known to have significant health benefits, but few people achieve the daily recommended steps. Fortunately, mobile health (mHealth) applications have emerged as promising tools to promote physical...

AI can Find Cancer Pathologists Miss

Men assessed as healthy after a pathologist analyses their tissue sample may still have an early form of prostate cancer. Using AI, researchers at Uppsala University have been able to...

AI, Full Automation could Expand Artific…

Automated insulin delivery (AID) systems such as the UVA Health-developed artificial pancreas could help more type 1 diabetes patients if the devices become fully automated, according to a new review...