An experienced forecaster can use several different types of knowledge in forcing. First, there is his theoretical understanding of meteorology, which is well entrenched in current numerical models. A second type is his “local knowledge,” gained over years of experience, of how weather is likely to form in his forecast area. This kind of local familiarity is not easily captured with traditional numeric techniques, but might provide additional insights for prediction that someone unfamiliar with the area might not have. A third type of knowledge is how to interpret forecast tools already in use. This might include knowledge of the tool's limitations and how it works in a particular locale. Capturing these types of knowledge is important in building computing systems that can serve as intelligent consultants to forecasters. This paper describes a prototype system, called METEOR, that incorporates all these types of knowledge to predict the location, severity, and motion of convective storms in Alberta; METEOR interprets contoured maps of a synoptic-based instability index and of surface equivalent potential temperature. It also gathers additional information about a variety of ongoing weather conditions from three portions of surface aviation reports: the cloud cover section, the obstructions visibility, and the observations provided in the “remarks” section. Interpreting remarks made by human observers, while useful to a forecaster experienced with local weather conditions, can be too time consuming for people to do in real-time and too complex for traditional computing methods to handle. However, METEOR interprets these remarks and keeps track of where various weather activities are occurring and how they are changing over time. At present, METEOR's final forecast is a prediction of likely areas of storm initiation, direction of motion, and intensity, plus summaries of current conditions and their implications for storm development.