Healthcare appointment scheduling suffers from persistent operational bottlenecks due to manual coordination, fragmented legacy systems, and high administrative overhead. These inefficiencies constrain provider availability and degrade patient access to care. This paper presents CareConnect, a safety-first conversational agent for healthcare logistics automation leveraging large language model (LLM) function calling, retrieval-augmented generation (RAG), and layered deterministic safety guardrails. The system orchestrates eight domain-specific tools to support appointment booking, modification, cancellation, and facility information retrieval while enforcing strict scope constraints that prohibit medical advice or diagnosis. Safety-critical situations are handled through deterministic short-circuit mechanisms for emergency detection and medical intent refusal.
We evaluate CareConnect on a comprehensive benchmark of 680 task-oriented scenarios spanning end-to-end workflows, multi-turn interactions, and edge cases. Experimental results demonstrate a 91.8% task completion rate with a median per-request latency of 2.2 seconds, 96.0% safety compliance on the dedicated safety-critical evaluation subset, and an average operational cost of $0.0324 per appointment, yielding a significant cost reduction compared to manual human scheduling. These findings show that carefully scoped and rigorously safeguarded LLM-based agents can reliably automate complex healthcare operational workflows while maintaining safety guarantees and achieving substantial cost efficiency. The source code and system implementation are publicly available at GitHub CareConnect.
Blogger's Review: CareConnect effectively addresses the efficiency issues in medical scheduling by combining the power of LLMs with stringent safety measures, showcasing the tremendous potential and application prospects of AI in healthcare. Its efficient automation processes and economical operational costs provide strong support for the future intelligence of healthcare services.