This paper describes a new coverage methodology developed at IBM's Haifa Research Lab. The main idea behind the methodology is a separation of the coverage model definition from the coverage analysis tool. This enables the user to define the coverage models that best fit the points of significance in the design, and still have the benefits of a coverage tool. To support this methodology, we developed a new coverage measurement tool called Comet. The tool is currently used in many domains, such as system verification and micro-architecture verification, and in many types of designs ranging from systems, to microprocessors, and ASICs.