Clinical trials seeking to delay or prevent the onset of type 1 diabetes (T1D) continue to face challenges. There is just one recently FDA-approved therapy, teplizumab, to delay progression from stage 2 to stage 3 T1D, in addition to insulin replacement therapy, the current principal management tool but not a cure for T1D. To increase the efficiency of T1D clinical trials, this project aimed to inform T1D clinical trial design by developing a disease progression model-based clinical trial simulation tool. This tool consists of three components: disease, trial, and drug. The disease progression was simulated based on our published quantitative joint model predicting time to T1D onset, which was developed using extensive individual-level data collected from the TrialNet Pathway to Prevention and The Environmental Determinants of Diabetes in the Young (TEDDY) natural history studies. The trial component includes inclusion/exclusion criteria, the number of subjects in each arm (i.e., placebo and treatment), trial duration, assessment interval, and dropout rate. Given that no data was available to develop a drug model, we implemented a function that can be adopted for assumed drug effects. To increase the size of the population pool to simulate, we generated virtual populations while maintaining the covariation distributions shown in the natural history data using multivariate normal distribution and ctree machine learning algorithms. As an output, a power calculation was implemented, which summarizes the probability of success, showing a statistically significant difference between the two arms. In our tool, power curves can also be generated through iterations. This tutorial describes how we developed the tool and instructions on simulating a planned clinical trial, along with two case examples. The web-based tool is publicly available: http://coplin8.cop.ufl.edu:3838/t1d/.