Government Officer (ASN) has the obligation to develop competencies for a minimum of 20 learning hours / year. However, not all ASNs can take part in training as a form of competency development due to the limited quota of face-to-face (classical) training available. The latest regulations provide alternative non-classical learning that does not have to be face-to-face including e-learning, distance learning and self learning. Self learning can be used by students to improve their competency using a variety of learning resources available both conventional and based on information technology. In this paper, one of the tools to support self learning will be discussed in the form of intelligent tutoring system design using a chatbot in the prepackaged goods training (BDKT). The design uses the framework of Design Science Research, starting from setting goals, designing chatbot conversational flow, developing applications using chatfuel, demonstration through simulations via Facebook Messgenger and Blackbox Evaluation. The resulting prototype has been able to follow the flow of the conversation that was designed and can be used as a support for self learning anytime and anywhere as long as it is connected to the internet.