It is widely recognized that requirements engineering is a knowledge-intensive process and cannot be dealt with using only a few general principles. Since knowledge plays a crucial role in software development, software engineers have to describe and organize various aspects of knowledge before the program can be written. A recent w ork by Robillard reveals that software development can be further improved by recognizing the relevant k n o wledge structures. In this paper, we propose the use of task-based conceptual graphs (TBCG) framework as a basis for automating software development. By structuring and operationalizing conceptual graphs, TBCG speci cations can be transformed into executable programs automatically. T o construct a conceptual model, task-based speci cation methodology is used to serve a s t h e m e c hanism to structure the knowledge captured in conceptual models whereas, conceptual graphs are adopted as the formalism to express task-based speci cations and to provide a reasoning capability for the purpose of automation. Once task-based conceptual graphs have been constructed and veri ed, a blackboard system will automatically transform TBCG speci cations into a software system composed of database schemas, knowledge base, and user interfaces. A meeting scheduling system is used as an illustrative example to demonstrate our approach.