This work is dedicated to the development of a simulation model of a Dynamic Scheduling for Field Service Management (FSM) system. FSM as a system with a large number or interacting agents, evolving over time, has difficulties when planning operations dynamically. Multi agent-based systems as a part of distributed artificial intelligence, allows us to use an effective approach of simulating the work of the system and adjust its parameters to achieve the best performance in terms of increasing the speed of customer service, reducing transport and time costs. All this leads to improved quality of technical support and service and, as a result, customer satisfaction. Most of the current scheduling models on the market are centralized. This paper exposes a way to use a multi agent-based approach to shift the scheduling system from centralized control to decentralized decisions made by agents. The implemented model allows us to check the model of dynamic scheduling with the real data under a real-time environment and it allows us to test interactions between the agents of different types.