Codeball AI

We build machine learning models that find bugs in code. We can be used proactively as part of the development process by both humans and AI agents to eliminate problematic code before it's submitted for review. We can also do checks at time of code review through our GitHub agent that adds comments to PRs (Pull Requests - essentially just submissions of code), to ensure nothing slips through. We allow developers to enforce their own taste on the code that either the AI or their teams contribute to the codebase by providing Recurse Rules. These are written in markdown and are descriptions of bad patterns that you don't want present in your codebase (e.g. the concept of DRY - do not repeat yourself).

Baz delivers the context and automation to review, track, and approve code changes with confidence. Baz transforms your code review and merging process by giving instant application insights and suggestions, helping you focus on building and shipping strong software. Baz organizes your pull request into Topics, so you can breeze through reviews with a clear structure. Baz uncovers breaking changes across APIs, endpoints, parameters, and more, analyzing how every piece fits together. Developers can review, comment, and suggest wherever they want. We'll make sure it's fully visible both on GitHub and Baz. The only way to predict the true impact of a code change is through structured impact analysis. Baz integrates AI and your developer tools to analyze your codebase, map dependencies, and provide actionable reviews that ensure your code’s stability. Plan your proposed changes and invite your team to review them. Easily assign relevant reviewers based on past contributions.