LAS VEGAS—Epic is further enhancing its artificial intelligence capabilities and capabilities, touting how its AI tools deliver measurable results beyond just reducing documentation time.
The company reports that health systems are seeing earlier diagnoses, fewer denials, and an improved patient experience.
At the 2026 Health Information Management Systems Society (HIMSS) Global Health Conference & Exhibition, which opened on Monday, Epic previewed its future AI roadmap with new capabilities across clinical, patient-facing and operational workflows.
The electronic medical records giant announced Tuesday that it plans to release a fully integrated platform for creating and monitoring AI agents that reason and operate across workflows. Agent Factory allows organizations to customize agents using a visual builder, equip them with local policies and knowledge bases, and deploy them on their own timelines, Epic said in a press release.
At the JPMorgan Healthcare Conference in January, Phil Lindemann, vice president of data and research at Epic, previewed Agent Factory as a platform that allows organizations to build their own AI agents within Epic.
“Epic plans to build an entire library of ready-to-use, system-embedded agents on the platform that are fully integrated into the user’s experience. And they said, “Epic, you need to give us a playground, a sandbox, a place where we can invent and reimagine.” That’s what Factory is intended to be,” Lindeman said of JPM’s Fierce. told Healthcare.
Epic is developing a number of new AI features. The company plans to deploy conversational AI for clinicians as part of its Art clinical assistant, which includes an AI scribe tool. During patient visits, conversational AI uncovers answers to clinician and patient questions. AI tools can handle direct questions like, “Art, what are the trends in this patient’s blood pressure?” It can also answer inferred questions based on the context of the conversation, Epic said.
During UGM in August, the company announced an AI scribing solution called “Art for Clinicians” and a generative AI co-pilot for the revenue cycle called “Penny” that assists with coding and denial prosecutions. We also announced a patient-facing AI solution called Emmie that helps patients schedule and prepare for medical visits.
Based on this, as part of the new AI capabilities, Art and Emmy will collaborate to build a visit agenda, bringing together questions and priorities from patients and clinicians into one view, according to Epic.
Another new feature is the diagnostic checks built within Art. It assists clinicians in differential diagnosis by analyzing patterns in patient symptoms, medical history, and outcomes and suggesting potential next steps based on actual patient data.
Epic is also building on its new generation AI model family, Curiosity, with plans to create a new family of healthcare infrastructure models trained on anonymized real-world patient records. This model helps predict upcoming medical events across diagnosis, medication, treatment, and outcome.
More than 85% of Epic’s customers are currently using Epic AI, the company said. As health systems and providers bet on specific use cases for AI, the discussion has moved from theoretical possibilities to measurable results and return on investment.
“AI is starting to show real results. Obviously there’s a lot of hype, but the reality is starting to happen,” Lindemann said at JPM in January.
Epic focuses on key customer outcomes as AI reduces paperwork, improves diagnostics, and lowers costs.
The company says clinicians at multiple organizations are now able to complete discharge summaries 20% to 30% faster by using Art’s draft hospital course notes. At Riverside Health in Virginia, Art’s inpatient insights help clinicians reduce time spent on documentation and communication tasks by up to 32%.
Epic also claims that the use of AI allows patients to receive treatment more quickly. At The Christ Hospital, Art extracts incidental findings from radiology results to drive follow-up, achieving a 69% early detection rate for lung cancer (compared to the national average of 46%).
In March, Houston Methodist became the first organization to use Chart with Art for bedside nursing workflows. Epic plans to release Chart with Art for home care workflows in April.
Additionally, organizations report significant improvements in pre-approvals by implementing Epic’s AI into their revenue cycles and operations. By using Penny, Epic’s revenue cycle AI tool, Summit Health reduced drug pre-approval submission time by 42% and accepted 92% of AI-generated responses without editing.
The health systems most actively using Penny have reduced coding-related rejections by more than 20%, preventing revenue loss due to claim rejections and reducing the need for staff to spend time reworking claims, Epic executives said.
Epic’s patient-facing AI, Emmie, instantly answers simple patient questions and reduces the burden on healthcare systems. At Rush University Medical Center, Emmy consistently reduced billing-related customer service messages by 58%.
Emmy also has trouble managing her commitment schedule. At Ochsner Health, patients have rescheduled more than 14,900 appointments with Emmie, making scheduling more convenient and saving nearly 750 hours of staff time.
Sutter Health has teamed up with Epic to become the first organization to use Ask Emmie, MyChart’s conversational AI assistant that answers patients’ health questions based on their medical records. Sutter and Epic worked closely on testing and refining it prior to launch. The conversational AI assistant is currently available to an initial group of users, but Epic says it plans to make it more widely available in the coming weeks.
