Direktorat Jenderal Anggaran (DJA) is an organizational unit within the Ministry of Finance with the task of providing an information system related to budgeting performance. The dynamics of policy changes that have occurred recently have resulted in changes to the information system that has been developed by DJA. DJA has socialized the existing business processes and systems, but many users still ask questions through the DJA customer service channel which can only respond during business hours. This research will propose a solution for optimizing these services by creating a chatbot based on Natural Language Processing using the Rasa Open Source framework, which will be installed on one of the DJA's core systems, namely the Performance Monitoring and Evaluation Application. The chatbot will spontaneously answer user questions related to the application. The data used in this study are Frequently Asked Questions (FAQ) data, knowledge base Kemenkeupedia, Focus Group Discussions (FGD) and Performance Monev Application data taken via the API (Application Programming Interface). The results of this study are Chatbot FAQs embedded in the performance monitoring and evaluation application. The intent prediction test produces an accuracy value of 0.986, a weighted precision value of 0.973, a recall of 0.986, and an f1-score of 0.980 then the response prediction produces an accuracy value of 0.980, a weighted precision value of 0.986, a recall of 0.980, and an f1-score of 0.980. This shows that the chatbot is able to identify intent very well and respond appropriately to the user.