Methods for designing and building perceptual agents should be clean, powerful and practical. But no methodology satisfies all three criteria, yet. Our methodologies are evolving dialectically. The symbolic methods of Good Old-Fashioned Artificial Intelligence and Robotics (GOFAIR) constitute the original thesis. The antithesis is reactive Insect AI. The emerging synthesis, Situated Agents, needs formal rigor and practical tools. A robot is a hybrid intelligent dynamical system, consisting of a controller coupled to its body. The Constraint Net (CN) model of Zhang and Mackworth is a unitary framework for building hybrid intelligent systems as situated agents. Most other robot design methodologies use hybrid models of hybrid systems, awkwardly combining offline computational models of high-level perception, reasoning and planning with online models of low-level sensing and control. In CN, the designer specifies the robot’s vision, control and motor systems uniformly as online systems. The constraint-based architecture for agent perceiver/controllers consists of multi-layer constraint-satisfying modules. If the perceptual and control systems are designed as constraint-satisfying devices then the total robotic system, consisting of the robot symmetrically coupled to its environment, may, sometimes, be proven correct. In some cases, a controller may be synthesized from a constraint-based specification. This framework has co-evolved with applications to several robotic tasks, including the the challenge of building various visually-controlled robot soccer players. The dynamics of intelligence can be captured by constraint-satisfying hybrid systems.