COVID-19 is a contemporary virus with a fatal syndrome that had not been seen in the last century. The virus evolves in people of all ages in all areas around the world. As the increment of cases is growing up rapidly the worry of people is increasing, which makes it very hard for healthcare departments and governments to solve people's queries. AI solution is suggested, where a simulation of frontdesk assistance. Chatbots are easy to use and simulate a human conversation through text via smartphones or personal computers. Chatbot applications can improve patient information, monitoring, or treatment adherence. The architecture is a simple neural network consisting of a single hidden layer and the sigmoid function is trained by textual data organized by multiple data organization methods. A simple GUI is provided to the classifier to be tested practically. Data used is a collection of questions and their answers about COVID-19. The approach has achieved acceptable results considering speed, and accuracy. Practical predictions were true with acceptable accuracy.