This paper illustrates how the combination of teacher and computer guidance can strengthen collaborative revision and identifies opportunities for teacher guidance in a computer-supported collaborative learning environment. We took advantage of natural language processing tools embedded in an online, collaborative environment to automatically score student responses using human-designed knowledge integration rubrics. We used the automated explanation scores to assign adaptive guidance to the students and to provide real-time information to the teacher on students’ learning. We study how one teacher customizes the automated guidance tools and incorporates it with her in-class monitoring system to guide 98 student pairs in meaningful revision of two science explanations embedded in an online plate tectonics unit. Our study draws on video and audio recordings of teacher-student interactions during instruction as well as on student responses to pretest, embedded and posttest assessments. The findings reveal five distinct strategies the teacher used to guide student pairs in collaborative revision. The teacher’s strategies draw on the automated guidance to personalize guidance of student ideas. The teacher’s guidance system supported all pairs to engage in two rounds of revision for the two explanations in the unit. Students made more substantial revisions on posttest than on pretest yet the percentage of students who engaged in revision overall remained small. Results can inform the design of teacher professional development for guiding student pairs in collaborative revision in a computer-supported environment.