Frequently Asked Questions

Is this replacing human reviewers?

No. Burg AI is a first-pass assistant that catches obvious issues quickly. Human reviewers still provide:

• Context about project goals
• Judgment on trade-offs
• Architectural guidance
• Team knowledge

Think of it as a very fast, very thorough first reviewer — not a replacement.

Will this block merges?

By default, no. Burg AI posts comments but does not:

• Create "pending" check statuses
• Block the merge button
• Require approval

You can configure branch protection rules in GitHub if you want to require review resolution.

Does it train on my code?

No. Your code is:

1. Fetched when a PR is opened
2. Sent to the LLM provider (using your key)
3. Discarded after posting comments

We do not store source code. We do not train models on your code.

Can it push commits?

No. Burg AI only has read access to code and write access to PR comments. It cannot:

• Push commits
• Modify files
• Create branches
• Merge PRs

Does it work on monorepos?

Yes, with some caveats:

• Large PRs may hit file count limits
• Use file exclusions to focus on relevant paths
• Consider per-path custom prompts (Pro)

What languages are supported?

20+ languages including:

TypeScript, JavaScript, Python, Go, Rust, Java, C#, C++, Ruby, PHP, Swift, Kotlin, Scala, and more.

Framework-specific patterns are detected for:

React, Vue, Angular, Django, FastAPI, Express, Rails, Spring, and others.

How much does it cost?

• Free plan: $0 — 100 reviews/month
• Pro plan: $9/month — Unlimited reviews

You also pay your LLM provider for API usage (typically $0.01–$0.10 per review).

Can I self-host?

Not currently. Burg AI is a hosted service. Self-hosted options may be available in the future for enterprise customers.