This study introduces agent-case embeddings, a general purpose tool for detecting the variety of solutions produced by evolutionary algorithms. They can also be used to explore the geometry of the space of problems agents are attempting to solve. Agent-case embeddings permit comparison of solutions evolved with different representations by directly comparing phenotypes. Use of agent-case embeddings require that multiple instances of the problems solved by the agent be available or contrivable. Three examples of agent-case embeddings are derived for apoptotic cellular automata, agents playing the iterated prisoner’s dilemma, and simple virtual robots performing the Tartarus task. The use of agent-case embeddings is shown to permit visualization of the diversity of evolved agents, demonstrate the impact of changing algorithm parameters, and explore the impact of different representations on evolutionary search. The algorithm parameters explored include: population size, elite fraction, and choice of variation operators. Agent-case embeddings are used to demonstrate that a novel technique called single-parent crossover can localize evolutionary search in a small part of the adaptive landscape in a controlled manner.