Create or customize an Agent instance

Customize the AI Code Review Agent to match your workflow needs.

By default, Bito's AI Code Review Agent comes with a pre-configured instance that's ready to use. This default Agent is seamlessly integrated into your PR workflow and supported IDEs, so you can start benefiting from its capabilities right away.

However, if you need tailored configurations for specific repositories or workflows, you can create new Agent instances or customize existing ones to suit your needs.

This guide will walk you through how to create or customize an Agent instance, unlocking its full potential to streamline your code reviews.

Creating or customizing AI Code Review Agents

Once Bito is connected to your GitHub/GitLab/Bitbucket account, you can easily create a new Agent or customize an existing one to suit your workflow.

1. To create a new Agent, navigate to the Code Review Agent page and click the New Agent button to set up a tailored instance.

2. If you’d like to customize an existing agent, simply go to the same page and click the Edit button next to the Agent you wish to modify.

Once you have selected an Agent to customize, you can modify its settings in the following areas:

1. General settings

Agent name

Assign a unique alphanumeric name to your Agent. This name acts as an identifier and allows you to invoke the Agent in supported clients using the @<agent_name> command.

Agent description

Provide a concise description of the Agent's purpose, such as the use case or project it will support. This makes it easier to manage multiple Agents.

2. Customization options

Bito provides three tabs for in-depth Agent customization:

a. Review

In this tab, you can configure how and when the Agent performs reviews:

• Automatic Review: Toggle to enable or disable automatic reviews when a pull request is created and ready for review.

• Automatic Incremental Review: Toggle to enable or disable reviews for new commits added to a pull request. Only changes since the last review are assessed.

• Batch Time (hours): Set the wait time (0 to 24 hours) for batching new commits before triggering a review. Lower values result in more frequent incremental reviews.

• Draft Pull Requests: By default, the Agent excludes draft pull requests from automated reviews. Disable this toggle to include drafts.

• Automatic Summary: Toggle to enable automatic generation of AI summaries for changes, which are appended to the pull request description.

• Change Walkthrough: Enable this option to generate a table of changes and associated files, posted as a comment on the pull request.

b. Filters

Use filters to exclude specific pull requests or files from automated workflows:

• Files and Folders: A list of files/folders that the AI Code Review Agent will not review if they are present in the diff. You can specify the files/folders to exclude from the review by name or glob/regex pattern. The Agent will automatically skip any files or folders that match the exclusion list. This filter applies to both manual reviews initiated through the /review command and automated reviews.

• Source or Target Branch: This filter allows users to skip automated reviews for pull requests based on the source or target branch. It is useful in scenarios where automated reviews are unnecessary or could potentially disrupt the workflow. This filter applies only to automatically triggered reviews. Users should still be able to trigger reviews manually via the /review command.

For more information and examples, see Excluding Files, Folders, or Branches with Filters.

c. Tools

Enhance the Agent’s reviews by enabling additional tools for static analysis, security checks, and secret detection:

• Secret Scanner: Enable this tool to detect and report secrets left in code changes.

By leveraging these customization options, you can optimize your Agent for your specific workflow and ensure a streamlined code review process. Save your changes once you have finished customizing your Agent to activate the new settings.