Farol, the open source tool that maps a pull request's risk before approving it
A Harvard study of more than 700 companies and 300 million work events found that AI agents increase generated lines of code by 30%, commits by 20% and pull requests by 23%, without significantly changing the pace of feature resolution. Winnin released farol, a free open source CLI and GitHub Action (MIT license) that analyzes the full program with real compilers and delivers a risk verdict before the reviewer opens the diff.
In 40 seconds
- The Harvard study notes that human review became the bottleneck amid the higher volume of AI-generated code.
- farol analyzes the full program with the TypeScript type checker, go/types and the Python ast, and produces deterministic reports.
- The report includes what the change reaches, a verdict (fast track, quick review or careful review) with a 0 to 100 score, and where to start the review.
IASummary generated by artificial intelligence from a story by El Ecosistema Startup. It may contain errors: the original source prevails.




Comments
Be respectful. Comments reported by several people are hidden until a moderator reviews them.
You do not need an account to read, only to comment. Sign in with a code sent to your email or with your Google account. We only show the name you choose, never your email.