RecovryAI announced the U.S. Food and Drug Administration (FDA) awarded Breakthrough Device Designation to its Virtual Care Assistants (VCAs).

The physician-prescribed, patient-facing clinical artificial intelligence (AI) is designed to support patients during post-op recovery. This milestone coincides with Recovry AI’s emergence from stealth after over two years of product development and clinical evaluation.

The company’s VCAs were engineered to extend continuity of care from hospital discharge into recovery at home. The physician-prescribed AI delivers recovery guidance based on established clinical protocols and escalate deviations from expected recovery patterns to the care team with full clinical context.

The company’s initial VCA targets total joint arthroplasty, with the architecture designed to grow across procedural domains.

RecovryAI is chasing FDA authorization under a novel Class II pathway for patient-facing software as a medical device (SaMD). The company has engaged the FDA through a pre-sub process since 2024 to align on clinical evidence requirements, with full submission planned later this year.

If authorized, the decision would create a new device classification and special controls governing future devices in this category.

“Healthcare innovation will not scale without trust,” said Scott Walchek, CEO and co-founder of RecovryAI. “Most healthcare AI today lives in two lanes: clinician-facing tools like decision support and ambient documentation, and consumer health and wellness applications. Patient-facing AI inside the care pathway is different. It guides behavior and carries clinical responsibility. In this lane, trust is underwritten by FDA authorization. Without it, there’s no durable basis for safety, accountability, reimbursement, or real scale. From day one, we built within a regulatory framework and embraced the rigor clinical deployment requires.”

The company is conducting its pivotal study evaluating the Virtual Care Assistants’ safety and system behavior in total joint arthroplasty recovery. The multi-site study includes OrthoArizona, one of the nation’s largest orthopedic practices, and Mercy Medical Center in Baltimore, Md., among other participating sites.

Data from RecovryAI’s limited pilot phase showed the VCA system behavior “generally aligned” with physician judgment, supporting advancement into the pivotal study.

“Deploying generative AI in a regulated clinical environment requires a structured medical reasoning framework,” said Dr. Richard Watson, co-founder and chief science officer of RecovryAI. “We designed our platform to continuously evaluate patient-reported information against expected recovery trajectories, deliver procedure-specific guidance when recovery is progressing appropriately, and escalate deviations to the prescribing physician’s care team with the complete patient interaction history and relevant clinical context. That architecture allows the AI to manage routine, low-acuity concerns while ensuring that clinicians retain oversight and exercise final medical judgment.”