Bug Fix Flow AI

Problem: Debugging is a repetitive and time-consuming part of software development. Developers often need to manually locate the relevant file, understand the root cause of a bug, implement a fix, write a regression test, and run the test to verify that the solution works. Even for small bugs, these steps can create unnecessary context switching and rework. Solution: BugFix Flow AI is a lightweight AI-assisted debugging workflow designed to bring these steps together into a single guided process. The developer provides a description of the bug and the path to a codebase. The system analyzes the relevant source files, identifies the likely root cause, proposes and applies a minimal fix, generates a regression test, and runs the test using pytest. A structured report then presents the identified root cause, applied fix, and regression-test result. The project is demonstrated using a sample Python calculator application containing an intentional bug in its average calculation. BugFix Flow AI identifies the incorrect divisor, applies the correction, generates a regression test, and validates the result successfully. Target users: Software developers and students who want to reduce repetitive debugging work and validate fixes more efficiently. The MVP intentionally focuses on a simple end-to-end debugging workflow using Python, Gradio, Groq API, and pytest rather than adding unnecessary infrastructure. The project demonstrates how an AI-assisted workflow can reduce manual debugging steps while keeping the developer involved in reviewing and validating the changes.