Meet Laurah Turner: The AI Visionary Behind Two Sigma Labs

Some people arrive at artificial intelligence through trend, timing, or opportunity. Laurah Turner arrived there much earlier.

“My PhD actually was using artificial intelligence,” Turner says, though “we didn’t really refer to it as artificial intelligence back then.” Long before today’s AI boom, she was building machine learning models, working with complex statistical systems, and developing the kind of analytical foundation that now sits at the center of the field. “I’ve been doing this for a while,” she says. “I kind of always been doing this throughout my education and into my career.”

Today, Turner is helping shape the future of AI at the University of Cincinnati in ways that are both ambitious and grounded in practical need. She serves as associate dean for artificial intelligence and educational informatics in the College of Medicine, and as founding director of Two Sigma Labs. In her faculty role in the Department of Biostatistics, Health Informatics, and Data Science, she leads what she describes as “a very interdisciplinary lab” focused on developing AI tools and studying how those tools can improve learning.

At the center of Turner’s work is a concept she calls precision medical education. Borrowing from precision medicine, which tailors treatment to the individual patient, precision education aims to tailor learning to the individual student. Historically, she argues, that level of customization has been out of reach. It required more time, more faculty, and more human attention than most institutions could provide. AI, she believes, can help close that gap by making it possible to create “a learning environment and educational experience that is customized to the individual learner."

That idea is already taking shape inside Two Sigma Labs. One of the lab’s signature efforts is a suite of AI-powered patient simulations designed to give medical learners an on-demand place to practice. In traditional medical education, students often work with standardized patients—actors trained to portray medical conditions and difficult interpersonal situations. Those experiences are valuable, Turner says, but they are also expensive, space-limited, and infrequent. Her lab’s alternative is a virtual setting where learners can interact with AI patients, practice diagnosis, perform virtual exams, order labs and tests, and receive personalized feedback in a lower-stakes environment.

The goal is not to replace human teaching, but to expand opportunities for repetition, experimentation, and growth. “There’s a lot of performative pressure on learners,” Turner says, which often means they do not get enough chances to drill skills, make mistakes, and improve. Her platform is designed to create what she calls “a safe space for them to fail forward."

The technology behind that experience is sophisticated, but Turner describes it plainly. The system uses a multi-agent architecture: one agent plays the patient, another manages labs and tasks, another handles the physical exam, and an orchestrator oversees the encounter. Additional monitoring agents help ensure the system behaves reliably and reduce the risk of “hallucinations or bad things." Learners can engage through text or voice, order an X-ray and receive an actual image, and then receive “very specific very personalized feedback” tied directly to the decisions they made during the interaction.

The payoff, Turner says, is not just convenience. It is access.

She sees AI as a tool that can democratize high-quality medical education for learners who might otherwise be excluded from it. A student in a rural hospital may not have access to simulation centers or specialty training environments, but they may still have a computer or smartphone. That, in Turner’s view, opens the door to more personalized support in places that need it most. It also allows learners to practice both common cases they need to master and rare conditions they may never encounter during training but still need to understand.

Turner is equally excited about what comes next. Among the projects emerging from Two Sigma Labs, she points to ambient technologies as especially promising. These systems could capture audio from real patient encounters—through wearable devices or smartphones—and generate customized feedback for learners afterward. In current medical education, she notes, students are supposed to be observed by faculty during patient visits, but in practice only “about 15 to 20% of all encounters get observed." Feedback often comes much later, sometimes weeks after the interaction, making it far less useful as a teaching tool. Turner’s aim is not to remove faculty from the process, but to augment scarce human supervision with timely, actionable support.

Still, she is clear-eyed about the risks.

These technologies, she says, are exciting but also “slightly terrifying because nothing’s been done like this before.” She describes the broader AI landscape as “still kind of the wild west,” especially in education and health care, where governance standards and validation protocols are still catching up to the pace of innovation. AI systems, she argues, cannot simply be deployed and forgotten. They must be continuously monitored for functionality, bias, robustness, and alignment with human value.

That sense of responsibility has shaped how Turner and her colleagues build. Asked about her lab’s methodology, she does not romanticize it. “It was a lot of just trial and error trial and error trial and error,” she says. Over time, that experimentation became a protocol. She credits the lab’s interdisciplinary structure for making that possible: physicians, designers, learners, AI engineers, and data scientists working together, asking different questions, and forcing one another to think more rigorously. “Both of them are equally valuable and necessary,” she says of the clinicians’ and data scientists’ perspectives.

Turner’s advice to people getting started with AI is notably simple: use it.

Courses, podcasts, and prompting guides can help, she says, but “there’s nothing that’s going to replace just going and working with the models." Her guidance is practical rather than grand. “Get your toes in the water,” she says, and “put it on your phone” so that AI becomes part of daily life rather than an abstract concept.

That philosophy extends beyond the lab. AI is part of Turner’s work life, but also part of her home life. “We do lots of little agents for lots of things in my house,” she says. One of the most memorable examples is a homework bot she built for her daughter. It helps with math, is “infinitely patient,” and, importantly, “it’s not allowed to tell her the answers.” Then comes the line that makes the technology feel instantly human: “She likes it better than me."

Turner also speaks with evident gratitude about the University of Cincinnati, where she says the institution’s mission and its people have made this work possible. Her lab draws students and faculty from design, engineering, information technology, computer science, and medicine. That interdisciplinary model, she says, is essential to the lab’s success. So are the learners themselves. “Learners are the Cornerstone and the reason that we develop these technologies,” she says.

What lingers after a conversation with Laurah Turner is not only the scale of what she is building through Two Sigma Labs, but the range of places where she sees AI making a difference. In her vision, AI can help a medical student practice a difficult case, support a rural learner far from a simulation center, provide more immediate feedback after a patient encounter, and even assist with math homework at the kitchen table.

In Turner’s hands, AI is not a distant abstraction or a flashy promise. It is a tool for making education more personal, more accessible, and more humane. And at a moment when much of the public conversation around artificial intelligence swings between hype and fear, that may be the most compelling vision of all.