AI-BASED CODE GENERATION AND SELF-TESTING SYSTEM

Software development often requires programmers to write repetitive code, understand unfamiliar requirements, and spend considerabletime identifying and correcting errors. Recent advances in artificial intelligence have enabled systems to generate source code fromnatural-language instructions. However, generated code may contain syntax errors, incorrect logic, insecure patterns, or incompletehandling of edge cases. This paper proposes an AI-Based Code Generation and Self-Testing System that accepts a programming task innatural language, generates a candidate solution, prepares or selects test cases, executes the code in a controlled environment, and analysesthe results. The proposed workflow combines prompt interpretation, code generation, static validation, test-case generation, sandboxedexecution, and feedback-based refinement. The system is intended to support developers and learners by reducing repetitive effort andproviding an initial validation cycle. It does not replace code review or guarantee correctness; execution safety, test coverage, modellimitations, and human verification remain important. This paper presents a proposed methodology and evaluation plan. Quantitativeperformance claims should be added only after implementation and testing.