Pacecar

Security & privacy

We don't train models on your private code.

Pacecar reviews diffs from your GitHub org. Buyers should know what we send, what we retain, and that we do not use providers that train on your data.

Short version: we do not use providers that train on your data. We do not train foundation models on your private repos. We do retain PR and review records so we can evaluate and improve the product. Public code is a different story — we may use it when permitted.

Full legal terms: Privacy Policy. Also: GitHub App permissions, review checklist, subprocessors.

Direct answers

What engineering leaders ask first

Do you train models on our codebase?

Not on private customer repos. Pacecar does not use Customer Content from private repositories to train, fine-tune, or otherwise improve foundation models — ours or a provider’s. If we train or fine-tune anything, we use public or otherwise permitted data. Separately, we retain reviews so we can tune prompts, checklists, and product quality — that is not the same as training a foundation model on your private code.

Do inference providers train on our code?

No. We do not use providers that train on your data. That is separate from what Pacecar retains on our side after the review runs.

Do you store our reviews?

Yes. We retain review artifacts (findings, related PR metadata, and the diff context needed to judge the review) so we can measure precision/recall, debug bad comments, and improve the product over time. That retention is intentional product-quality work — not permission to train foundation models on your private codebase.

Where does the code go?

GitHub notifies Pacecar on PR open/update. We fetch the diff via the GitHub App, send it plus our checklist to an inference provider that does not train on your data, post a review comment (and collapse the prior one on later pushes), and retain the review record for quality evaluation and operations (billing, comment updates).

Data path

How a review moves data

No paste into a consumer chatbot. Diffs stay inside the App → inference → PR comment path.

  1. 01

    GitHub webhook

    Your org’s GitHub App install notifies Pacecar on PR open and push.

  2. 02

    Diff over GitHub API

    Pacecar reads the pull request diff with the permissions you granted at install.

  3. 03

    Inference

    The diff and checklist go to an inference provider that does not train on your data.

  4. 04

    Comment + quality store

    Findings post back to the PR. We retain the review record so we can evaluate and improve the product — without training foundation models on your private code.

What we keep

Retain for quality. No training on private IP.

We do retain

  • GitHub App install and account linkage
  • Billing and usage events for reviews that ran
  • Review artifacts — findings, PR metadata, and diff context needed to evaluate and improve the product

We do not

  • Train or fine-tune foundation models on Customer Content from private repositories
  • Use inference providers that train on your data
  • Sell your private code or use it outside running and improving the review product

Uninstall the GitHub App anytime to stop reviews and revoke Pacecar’s access to your organization. On request, we delete relevant Customer Content within 30 days (Privacy Policy).

Responsible disclosure

Report a vulnerability

If you believe you have found a security issue in Pacecar, email security@pacecar.sh. Include enough detail to reproduce the issue. Please give us a reasonable window to investigate and fix before public disclosure. We will not pursue legal action against good-faith research that avoids privacy violations, service disruption, and data destruction.

Review every PR without surrendering the codebase.

Install Pacecar on your GitHub organization. Same checklist on every open and update — without training models on your private code.

Install on GitHub

Free to install. You only pay when reviews run.