There is growing concern that it is too difficult or costly to substantially improve the academic skills of children who are behind in school once they reach adolescence. But perhaps what we have tried in the past relies on the wrong interventions, failing to account for challenges like the increased variability in academic needs during adolescence, or heightened difficulty of classroom management. This study tests the effects of one intervention that tries to solve both problems by simplifying the teaching task: individualized, intensive, in-school tutoring. A key innovation by the non-profit we study (Saga Education) is to identify how to deliver “high-impact tutoring” at relatively low cost ($3,500 to $4,300 per participant per year). Our first randomized controlled trial (RCT) of Saga’s tutoring model with 2,633 9th and 10th grade students in Chicago public schools found participation increased math test scores by 0.16 standard deviations (SDs) and increased grades in math and non-math courses. We replicated these results in a separate RCT with 2,710 students and found even larger math test score impacts—0.37 SD—and similar grade impacts. These effects persist into future years, although estimates for high school graduation are imprecise. The treatment effects do not appear to be the result of a generic “mentoring effect” or of changes in social-emotional skills, but instead seem to be caused by changes in the instructional “technology” that students received. The estimated benefit-cost ratio is comparable to many successful model early-childhood programs.