This study investigated the effect of different methods of guidance with anchored instruction on students' mathematical problem-solving performance. The purpose of this research was to iteratively design a learning environment to find the optimal level of guidance. Two iterations of the software were compared. The first iteration used explicit instruction upfront followed by practice problems, and the second iteration provided structured problem-solving guidance as needed to solve the problems within the software. Pilot testing was conducted with 32 fifth-grade students from two inclusive classrooms observed a year apart within a small Midwestern, urban school. A parametric analysis of covariance was used to compare the problem-solving performance of the students who used the two different iterations. Enhancing anchored instruction with structured problem-solving guidance on an as-needed basis significantly improved students' problem-solving performance on conceptually easy problems, but not for more complex problems. The implications of this research illustrate the importance of iteratively designing and developing learning environments to take into consideration the needs of a particular situation.