We describe the capabilities of a knowledge-based system to automatically generate a collection of electronic notebooks containing various forms of online documentation and reports. This system is a subsystem of a larger knowledge-based system called SciNapse. SciNapse's raison d'etre is to transform high-level simulation problem specifications into executable numerical programs. The electronic notebooks are generated from the same domain knowledge bases that the system uses to perform its primary tasks. These online notebooks are of two different kinds: reference materials and reports. Reference materials are generated from the latest version of the knowledge base, which includes the classes that drive the system, and a network of objects representing meta-information about the system. The reference materials document the system's capabilities and help users understand what the system can do. Reports are generated from the instances created by a run of the system. They document the transformations the input specification underwent in becoming code, and are intended to help a user understand what the system has done.

The authors describe the automatic generation of finite difference codes for solving the Black-Scholes and related equations for option valuation using the SCINAPSE software synthesis system. Analysts can specify codes at a very high level that mirrors the mathematical description of the problem. A typical option pricing specification occupies less than a half page. From such concise input, the system automatically generates validated, documented codes of several hundred lines of either C or Fortran in minutes, codes of several thousand lines in about an hour.

Algorithm design is a challenging intellectual activity that provides a rich source of observation and a test domain for a theory of problem-solving behavior. This paper describes a theory of the algorithm design process based on observations of human design and also outlines a framework for automatic design. The adaptation of the theory of human design to a framework for automation in the DESIGNER system helps us understand human design better, and the implementation process helps validate the framework. Issues discussed in this paper include the problem spaces used for design, the loci of knowledge and problem-solving power, and the relationship to other methods of algorithm design and to automatic programming as a whole.

The analysis and execution of partial algorithm descriptions is an important part of the algorithm design process (as is borne out by studying the behavior of human algorithm designers). In this paper, we describe a language for representing partially designed algorithms and a process, developmental evaluation, that can discover useful knowledge to guide design. Using these and other results from our research in artificial intelligence, we are building a system, DESIGNER, that automatically designs algorithms. This paper also compares developmental evaluation to execution and analysis techniques used for testing complete programs and for validation of abstract specifications; concepts similar to those found in developmental evaluation are thus shown to apply to all stages of the software life cycle.

A refinement paradigm for implementing a high-level specification in a low-level target language is discussed. In this paradigm, coding and analysis knowledge work together to produce an efficient program in the target language. Since there are many possible implementations for a given specification of a program, searching knowledge is applied to increase the efficiency of the process of finding a good implementation. For example, analysis knowledge is applied to determine upper and lower cost bounds on alternate implementations, and these bounds are used to measure the potential impact of different design decisions and to decide which alternatives should be pursued. In this paper we also describe a particular implementation of this program synthesis paradigm, called PSI/SYN, that has automatically implemented a number of programs in the domain of symbolic processing.