Traditional long-term condition recall systems relied on repeated manual calls, letters and SMS reminders. These processes were time-consuming, inconsistent across sites and often frustrating for staff. Younger adults in particular struggled to engage, finding it difficult to book appointments during working hours. Operational pressures meant that non-responders absorbed significant administrative time, and staff were concerned that patients with the greatest needs were being overlooked.Primary care teams serving over 500,000 patients co-designed an innovative agentic AI-supported recall process that automated initial invitations at-scale and gathered clinical information before appointments were booked. Patients able to complete a digital review could do so at their convenience. Staff then received a clear list of individuals who needed personal follow-up, allowing them to prioritise time for patients requiring support. A key strength was the clarity and consistency of the new workflow. Initial staff concerns included the perception that some patients might be disadvantaged if they could not engage digitally. However, staff found that the streamlined digital flow freed capacity for deeper, more personalised conversations with patients needing additional help. Safety checks were embedded at critical points and concerns about clinical safety addressed in DTAC, DPIA and DCB0129/0160-aligned safety assessment.Existing recall models focus on volume rather than prioritisation. This approach differed by using digital automation to reduce low-value work while improving equity. The hybrid model—automated where appropriate, manual where needed—allowed teams to redistribute effort rather than simply accelerate existing tasks.Concerns about digital exclusion diminished when staff saw extremely high patient acceptance and the solution helped to identify and support vulnerable patients more proactively. Future development will focus on expanding to other conditions and refining templates to reflect multimorbidity.This experience demonstrates that digital automation can enhance—not replace—relational care when implemented with clear workflows and ongoing staff involvement. The approach aligns with broader primary care goals of access, continuity and personalised care.With 68% immediate digital uptake, Agentic-AI recall offers a practical, transferable method for modernising LTC management. Intelligent risk stratification and prioritisation resulted in a 41% reduction in appointments, offering a sustainable solution to operational pressures internationally.