You just have to train your model to learn the facts. Dialogflow's NLP is based on machine learning, you can add all the training data that the agent learns from and uses to improve its performance.
Dialogflow's training feature provides an interface to the model for incorporating both external and internal customer interaction logs into an agent's training phrases. You can use this feature to build a new Dialogflow agent using logs of existing customer interactions and to improve the performance of a live Dialogflow agent using its own logs.
For more information regarding the learning of model, refer the following link: