In this paper, we develop a behavioural queuing model with feedback for a chat service system, in which managers determine capacity sizing to maximise profit. We explicitly take into account customer repeated and queuing behaviour, which implies that the satisfied customers might return and have an impact on the arrival rate. For this case, customer satisfaction as perceived in terms of waiting time changes according to the capacity sizing. We define the staffing optimality of the chat service system as the number of agents maximising the profit, including the income from customers and the costs from agents. Using a numerical analysis, we make certain comparisons with the traditional models that do not consider repeated customer behaviour. Furthermore, we indicate how managers allocate the optimal staffing with various customer behaviour mechanisms.