How Explain My Build works

How does Explain My Build read my code?

You give it your code in one of two ways, depending on how private your project is:

• Public GitHub URL. Paste the link. We read the repo on our server to generate your artifacts, then delete it — the code is never stored.
• Private repo or local folder. Run it entirely in your browser, or via the CLI, so the code never leaves your machine. Nothing is uploaded.

Once it has the code, it maps your app: the routes and screens, the data models, the auth flow, the environment variables, and the third-party services it connects to. This works across apps built by Lovable, Bolt, v0, Replit, Cursor and more, because they all produce readable code.

What do I get, and what does it cost?

From one code read you get three artifacts, on a simple free-plus-one-paid model:

The end-user guide add-on includes a share link and access code, an in-app Help widget, and a portable export. It's $19/month, or $12/month founding for the first 100 customers. Cancel anytime. See pricing for the exact breakdown.

What does "cited to real code" mean?

It means every factual claim in your artifacts is tied back to the specific file (and often the specific lines) it came from. When the guide says "users can only see their own records," that statement points to the actual access rule in your code that makes it true.

This exists to keep the tool honest. If it can't find code to support a claim, it doesn't make the claim — it flags or refuses it instead of guessing. That's the opposite of a generic AI summary that will confidently describe features you don't have. Citations also let you verify anything yourself, and they make the fix-list actionable: each issue points at the exact place to fix.

How is my code kept private?

Privacy depends on which path you choose, and both are honest about their trade-offs:

• Public repo: read on our server, then deleted. We don't retain it.
• Private repo or local folder: processed in your browser or via the CLI, so the code and the audit results never leave your infrastructure.

This second path is also how the CI-native continuous audit runs: it grades your build and flags regressions — "what got worse since the last scan" — without your code leaving your pipeline.