Mastery-based assignments typically provide students with multiple opportunities to improve their performance, but getting students to take advantage of these opportunities is difficult. We report on the implementation of a two-part series of nudges designed to improve students' engagement with and performance on mastery-based assignments in high-enrollment, introductory undergraduate courses. Students received one or two email-based nudges for each assignment, providing both decision information and decision assistance. Delivered via email by a digital coaching system that provides tailored support to students, we evaluated the effectiveness of viewing versus not viewing these personalized nudges across introductory courses in mathematics, computer science and engineering over five terms at our large, research-intensive university. We used multilevel modelling with a sample of 30,693 assignment scores nested within 79 assignments and 5349 undergraduate students to explore the relationship between students' viewing the nudges and their scores while controlling for performance in other courses and students' baseline proclivities to read email from the coaching system. We find that viewing versus not viewing nudges is significantly related to improved outcomes. Viewing the first of the two-part nudge series is associated with a 3% increase in scores on average. Importantly, we found a significant interaction with prior academic performance such that students with the lowest average academic performance across all courses are predicted to benefit the most--up to 9%--from nudging. Positive impacts are observed in most courses where nudges were implemented and are found to be most impactful for later versus earlier assignments within a term. We discuss the implications of these results for supporting students' decision-making within mastery-based assignment schemes and suggest future research for tailored nudges to support student success.