.png&w=256&q=75)
🤝 Top Collaborators
.png&w=640&q=75)
.png&w=640&q=75)
🤓 Latest Submissions
ChangeGuard AI
Problem: Developers review code changes manually, but security and reliability risks can be hidden inside seemingly small changes. Finding these issues before merge can require significant review time and may still result in missed risks or rework. Solution: ChangeGuard AI is an AI-powered code-change risk analyzer that analyzes Git diffs and produces a structured risk assessment. It identifies an overall risk level and score, explains individual findings with severity, identifies affected files, suggests safer alternatives, and recommends tests that should be considered before merging. Target users: Software developers, code reviewers, development teams, and engineering teams that want a faster and more structured way to assess code changes. How it works: A developer opens the web application, enters an analysis title, and provides a Git diff. ChangeGuard AI sends the change for AI-powered analysis and presents the results in a clear review-oriented interface. Previous analyses can also be revisited through the history view. Technology: The application uses React with Vite and Tailwind CSS for the frontend, FastAPI and SQLite for the backend and persistence, and IBM watsonx.ai for AI-powered analysis. The application is deployed as a publicly accessible web application. What makes it unique: Instead of only generating a general explanation of a code change, ChangeGuard AI organizes the analysis around practical code-review decisions: risk level, specific findings, affected files, safer alternatives, and recommended tests. This turns an AI analysis into a structured workflow that developers can use before merging changes. The goal is to reduce manual effort in initial risk assessment, help developers identify potential issues earlier, and provide actionable information for the next stage of code review.
27 Sep 2026
