AI Agent-Based Multi-Stage Appointment Scheduling System for Clinics

Many clinics still use phone calls to schedule general consultations, vaccinations and blood tests. This process is slow and becomes more difficult for multi-stage vaccinations because each dose must follow the required interval. Workflow analysis shows that clinic staff spend significant time reviewing patient records before confirming appointments. In a simulated clinic environment with 100 reservations per week, manual scheduling produced appointment conflicts and increased scheduling time. This paper introduces an AI Agent-Based Multi-Stage Appointment Scheduling System for Clinics that checks appointment availability, balances doctor workloads, and validates vaccine dose schedules to address the lack of multi-stage scheduling and workload balancing in clinic appointment systems. A Telegram bot for patients, a Next.js/React web portal for clinic staff, and a Python FastAPI backend with PostgreSQL are used. An LLM race method accesses a local DeepSeek model and the Google Gemini API simultaneously to minimize response time while a LangGraph agent evaluates scheduling rules, doctor workload, and vaccination dependencies. The system was tested using 80 Pytest-based regression, smoke, monkey, scheduling, booking success rate, workload balancing, AI extraction, communication agent, and vaccine validation tests and 132 manual black-box functional test cases across 19 functional modules on the web portal and Telegram bot. All automated validation tests passed 100%, and manual functional verification passed 99.2% (131 of 132 cases). Results show that the proposed system addresses the main limitations of existing clinic scheduling systems by providing AI-assisted booking, workload balancing, and multi-stage vaccine validation, while allowing clinic staff to review and manage all appointments through the administrative dashboard.

AI agents, appointment scheduling, multi-stage dependency, Telegram bot, clinic management system

1. Assurance Technology Pte Ltd. (2026). Clinic Assist: Clinic management software. https://clinicassist.co [Google Scholar] [Crossref]

2. Celery Project. (2025). Celery: Distributed task queue documentation. https://docs.celeryq.dev [Google Scholar] [Crossref]

3. EasyOCR (JaidedAI). (2025). EasyOCR: Ready-to-use OCR documentation. https://github.com/JaidedAI/EasyOCR [Google Scholar] [Crossref]

4. FastAPI Team. (2025). FastAPI documentation. https://fastapi.tiangolo.com [Google Scholar] [Crossref]

5. Hannebauer, M., & Müller, S. (2001). Distributed constraint optimization for medical appointment scheduling. In Proceedings of the 5th International Conference on Autonomous Agents (AGENTS) (pp. 139–140). https://doi.org/10.1145/375735.376026 [Google Scholar] [Crossref]

6. Hasan, H., Salman, S., Abou Dargham, A. T., Mohanna, A., & Chehab, A. (2026). Toward trustworthy large language model agents in healthcare. arXiv. https://doi.org/10.48550/arXiv.2607.05055 [Google Scholar] [Crossref]

7. Health4U Solutions Sdn. Bhd. (2026). BookDoc: Healthcare appointment booking platform. https://www.bookdoc.com/ [Google Scholar] [Crossref]

8. LangChain Inc. (2025). LangGraph documentation. https://langchain-ai.github.io/langgraph [Google Scholar] [Crossref]

9. ManyChat. (2025). ManyChat: Chat marketing platform for Messenger, Instagram and WhatsApp. https://manychat.com [Google Scholar] [Crossref]

10. Marynissen, J., & Demeulemeester, E. (2019). Literature review on multi-appointment scheduling problems in hospitals. European Journal of Operational Research, 272(2), 407–419. https://doi.org/10.1016/j.ejor.2018.03.001 [Google Scholar] [Crossref]

11. PostgreSQL Global Development Group. (2025). PostgreSQL documentation. https://www.postgresql.org/docs [Google Scholar] [Crossref]

12. pytest-dev Team. (2025). pytest documentation. https://docs.pytest.org [Google Scholar] [Crossref]

13. Redis Ltd. (2025). Redis documentation. https://redis.io/docs [Google Scholar] [Crossref]

14. Ruiz Mejia, J. M., & Rawat, D. B. (2025). MedScrubCrew: A medical multi-agent framework for automating appointment scheduling based on patient-provider profile resource matching. Healthcare, 13(14), 1649. https://doi.org/10.3390/healthcare13141649 [Google Scholar] [Crossref]

15. SQLAlchemy Authors. (2025). SQLAlchemy documentation. https://docs.sqlalchemy.org [Google Scholar] [Crossref]

16. Telegram FZ-LLC. (2025). Telegram Bot API documentation. https://core.telegram.org/bots/api [Google Scholar] [Crossref]

17. Zhi, X., Zhao, H., Wu, L., Zhao, C., & Zhu, H. (2025). Reinventing clinical dialogue: Agentic paradigms for LLM-enabled healthcare communication. arXiv. https://doi.org/10.48550/arXiv.2512.01453 [Google Scholar] [Crossref]

• The Role of Artificial Intelligence in Revolutionizing Library Services in Nairobi: Ethical Implications and Future Trends in User Interaction
• ESPYREAL: A Mobile Based Multi-Currency Identifier for Visually Impaired Individuals Using Convolutional Neural Network
• Comparative Analysis of AI-Driven IoT-Based Smart Agriculture Platforms with Blockchain-Enabled Marketplaces
• AI-Based Dish Recommender System for Reducing Fruit Waste through Spoilage Detection and Ripeness Assessment
• SEA-TALK: An AI-Powered Voice Translator and Southeast Asian Dialects Recognition