What if we re-designed obesity management from scratch?

GLP-1 drugs (part of a broader group of medicines called incretin analogs) mimic natural human hormones that regulate appetite, glucose metabolism, and satiety. 

In clinical trials, drugs such as high-dose semaglutide (Wegovy) and tirzepatide (Zepbound), average 15–22% weight loss, and up to 20% reduction in cardiovascular events like stroke and heart attack¹, and benefits for kidney function, liver disease, and systemic inflammation.

At the same time, real-world outcomes have been more mixed—driven largely by discontinuation and difficulty maintaining weight loss long-term: 

• 50-70%^{2, 3} of patients stop treatment within 12 months

• After completing treatment, individuals struggle to sustain weight loss ⁴ 

The reasons are multifactorial: side effects, cost, access barriers, insufficient clinical support, and the behavioral complexity of long-term weight management.

Healthcare analytics date back to at least 1854, when John Snow traced a cholera outbreak in London to a contaminated water pump—work widely credited as founding modern epidemiology.⁵

More than 170 years later, we can capture more about your health than ever through lab tests, genomics, imaging, and wearables. But when it comes to deciding what to do next, most tools still describe what happens to people on average. 

They're not built to help you and your care team understand what's likely to happen to you, or how different treatment choices might change that.

Breakthroughs in generative AI now enable us to construct rich representations of an individual’s clinical profile and model its evolution over time—often called "digital twins."

We simulate forward trajectories that capture latent signals across multiple dimensions: weight, cardiometabolic biomarkers, renal and hepatic function, inflammatory markers—identifying downstream risks before they surface in traditional diagnostics and assessing different courses of treatment.

Obesity is a chronic, multifactorial disease—shaped by genetics, biology, environment, behavior, and psychosocial context—that intersects deeply with identity, mental health, and social experience.

Weight stigma is pervasive, affecting quality of care, employment, and emotional wellbeing.^{6, 7, 8} Patients who experience bias are less likely to seek care and more likely to discontinue treatment.⁹

Onsera goes beyond prescribing to focus on sustainable behavior change, meeting patients where they are—not where the system assumes they should be.

Our model integrates clinical support, behavioral coaching, care navigation, and patient engagement. We address both the physiological effects of anti-obesity medications—satiety, glycemic control, metabolic improvement—and the psychological work of building motivation, overcoming barriers, and forming lasting habits.

Human connection remains central to effective care.

Our approach to deploying provider-facing AI tools is to complement the care teams rather than replace them. Our tools surface relevant patient context, prioritize outreach, and handle routine coordination, so care teams can focus on what matters most.

• Healthcare systems — enabling value-based care, closing funding gaps, shifting spend from treatment to prevention

• Payers — predictable spend, measurable ROI, investment in care

• Patients — affordable medication access, personalized care, disease prevention