Setup

Get started with AI-powered code reviews for your GitHub, GitLab, and Bitbucket repositories.

Automate code reviews with AI. CloudThinker analyzes Pull Requests, identifies bugs and security issues, and provides actionable feedback—saving hours of manual review time.

---

What you get

• AI-powered detection of bugs, security vulnerabilities, and code quality issues
• Instant feedback on Pull Requests without waiting for manual reviews
• Seamless integration with GitHub, GitLab, and Bitbucket repositories
• In-line comments directly on your Pull Request with actionable recommendations
• Two review modes: Fast for quick single-agent reviews, Advanced for deep multi-specialist analysis
• CI/CD pipeline monitoring that analyzes failed builds and posts findings
• Incremental reviews on subsequent commits — only new changes are re-reviewed

---

Prerequisites

• A GitHub, GitLab, or Bitbucket account with repository access
• Familiarity with Git workflows and Pull Requests/Merge Requests
• A CloudThinker workspace
• Organization Owner permissions (required for installing the GitHub App on an organization)

Installing CloudThinker to a GitHub Organization requires Organization Owner permissions. If you are not an owner, please request an owner to install the app.

---

Quick start

1. Connect Repository

   Link your GitHub or GitLab account and select repositories to monitor.

2. Create Pull Request

   Open a new PR on your connected repository—CloudThinker detects it automatically.

3. Review Findings

   View status in CloudThinker and detailed findings directly on your PR.

---

Step-by-step guide

Step 1: Connect repository

1. Open Code Review

   Go to Code Review from the navigation menu.

   
2. Start setup

   Click Get Started with Code Review to open the setup wizard.

   
3. Choose provider

   Select GitHub, GitLab, or Bitbucket as your Git provider.

   
4. Choose authentication method

   For GitHub, click Install App to proceed with the GitHub App installation.

   For GitLab, choose your preferred authentication method:

   OAuth (Recommended)

   Click Install App to authenticate via OAuth. This is the simplest option for GitLab.com users.

   Access Token

   Use a Project Access Token or Group Access Token for self-hosted GitLab instances or if you prefer manual token management.

   Why use Project/Group tokens?

   • Comments appear from a bot user, not your personal account
   • Tokens are scoped to specific projects or groups
   • Easier to manage and revoke access

   Connection Details:

   1. GitLab URL: Enter https://gitlab.com for GitLab.com, or your self-hosted instance URL (e.g., https://gitlabexample.com)
   2. Token Type: Select Project Access Token (single project) or Group Access Token (all projects in a group)
   3. Access Token: Paste your generated token

   Self-Hosted GitLab Support: CloudThinker supports GitLab self-hosted instances running version 12.0 and above.

   How to create a Project Access Token

   1. Go to your project → Settings → Access Tokens
   2. Click Add new token
   3. Set role to Developer or higher
   4. Select scope: api
   5. Set an expiration date (recommended)
   6. Copy the generated token

   How to create a Group Access Token

   1. Go to your group → Settings → Access Tokens
   2. Click Add new token
   3. Set role to Developer or higher
   4. Select scope: api
   5. Set an expiration date (recommended)
   6. Copy the generated token

   Role Requirements: The token must have Developer role or higher to post code review comments. Guest and Reporter roles cannot post comments on merge requests.

5. Authorize and select repositories

   Authorize CloudThinker and select the repositories you want to enable for code review.

   
6. Complete setup

   Select your repositories in CloudThinker and click Complete to finish setup.

   

Setup Successful! Once you see your repositories listed, CloudThinker is now monitoring your Pull Requests and Merge Requests.

---

Step 2: Create Pull Request

1. Open your repository

   Navigate to your connected repository on GitHub or GitLab.

2. Create a Pull Request

   Create a new Pull Request with your code changes. CloudThinker will automatically detect the PR and start the AI-powered review.

   

---

Step 3: View results

1. Check status in CloudThinker

   View the review status for all your Pull Requests in the CloudThinker dashboard.

   
2. View findings on GitHub/GitLab

   Open your Pull Request to see the AI-generated summary and in-line code comments with detailed recommendations.

   

   

---

Review modes

CloudThinker offers two review modes that you can configure per repository:

Mode	Description
Fast	Single-agent review. Faster completion, ideal for small PRs and quick feedback.
Advanced	Specialist forking — the review is split across four specialist agents (security, performance, correctness, patterns) for deeper analysis. Best for critical repositories.

You can switch between modes in your repository settings at any time.

---

Pipeline monitoring

CloudThinker can monitor your CI/CD pipelines for failures and automatically analyze failed job logs.

When a pipeline fails, CloudThinker:

1. Detects the failed pipeline run
2. Fetches and analyzes the failed job logs with AI
3. Posts findings and suggested fixes directly on the PR

Pipeline monitoring can be toggled on or off per workspace. It is enabled by default.

---

Filter configuration

Control which PRs CloudThinker reviews using author and branch filters:

• Author filters: Include or exclude specific authors from reviews (whitelist/blacklist)
• Branch filters: Include or exclude branches matching specific patterns

PRs that match an exclude filter are marked as FILTERED and skipped entirely.

---

Incremental reviews

When you push new commits to an open PR, CloudThinker performs an incremental review — only the new changes are analyzed, not the entire PR. This keeps reviews fast and focused on what actually changed.

---

Tips

• Write clear PR descriptions to help the AI understand your changes.
• Keep PRs focused and small for better review quality.
• Review AI suggestions carefully before implementing.
• Address high-severity issues first.
• Avoid creating massive PRs or ignoring security warnings.
• Add @cloudthinker:ignore to your PR description to skip the AI review for that PR.