This paper describes the algorithmic basis and development of FRACSAT (FRACtionated Spacecraft Architecture Toolkit), a new approach to conceptual design, cost-benefit analysis, and detailed trade studies for space systems. It provides an automated capability for exploration of candidate spacecraft architectures, leading users to near-optimal solutions with respect to user-defined requirements, risks, and program uncertainties. FRACSAT utilizes a sophisticated planning algorithm (PlanVisioner) to perform a quasi-exhaustive search for candidate architectures, constructing candidates from an extensible model-based representation of space system components and functions. These candidates are then evaluated with emphasis on the business case, computing the expected design utility and system costs as well as risk, presenting the user with a greatly reduced selection of candidates. The user may further refine the search according to cost or benefit uncertainty, adaptability, or other performance metrics as needed.