Large-scale, classroom-based experiments using adaptive instructional software pose somewhat unique challenges for experimental design and deployment. One reason for this is that adaptive software allows students to advance through the curriculum at different rates and encounter content at different times, meaning that content targeted for experimentation is often reached asynchronously by students within the same classroom. In addition, many pedagogical approaches subject to experimentation will require multiple "touch points" with students throughout a course. Nimble experimental methods necessitate that experiments are able to take place at any time during the school year, so a robust experimentation system may need to be aware of the student's educational experience(s) prior to the experiment, both to permit students to be excluded from the experiment (if desired by the researcher) if they have previously been taught the target content, and to ensure that the pedagogical approach taken during the experiment is consistent with that which has been experienced by the student before and after the experimental period. The UpGrade A/B testing platform (Ritter et al., 2020) is designed to help experimenters navigate these issues. This paper discusses several key design considerations for conducting digital experiments within adaptive educational software: ordering and sequencing, coordination of experimental activities, and exclusion criteria. Following this is an illustration of how these principles were applied in two recently-conducted large-scale experiments.