The Children’s Aid Society of Toronto (CAST) is responsible for delivering high-quality child welfare services and supporting frontline workers who make complex, time-sensitive decisions affecting child safety and family wellbeing. While CAST has invested heavily in improving documentation practices and data systems, frontline staff still lack practical, accessible tools that help synthesize narrative case notes and administrative information into clear, actionable insights. As service needs grow and cases become more complex, CAST is exploring responsible, trauma-informed ways to integrate decision-support technologies that complement professional judgment. This project supports that priority by designing and prototyping an early-stage AI-supported decision-support tool tailored for ongoing case management. Building on CAST’s existing data infrastructure, the project focuses on translating CAST-identified needs into concrete interface features, usability requirements, and prototype components that can be tested in a controlled environment. By emphasizing participatory design and iterative feedback, the project ensures alignment with frontline workflows and organizational values. The anticipated benefits include improved decision consistency, reduced information overload for workers, clearer visibility into case trajectories, and foundational evidence needed for future, larger-scale evaluation studies. This project advances CAST’s strategic goal of developing responsible, evidence-informed innovations that enhance service quality and support better outcomes for children and families.