Getting started
Onboarding
This setup guide will walk you through the initial set up for Runbooks. If you plan to use the self-hosted option, please contact [email protected].
Create an account: https://app.aviator.co/auth/login
Follow the onboarding flow to connect to the Aviator GitHub app, authorize one or more repositories that you want to use with Runbooks. You can always add more repositories later.
Workflow
Aviator Agents workflow is divided into 3 phases:
Planning
Execution
Review
Planning
This is the phase where you work with the agents to plan out a work.
Once a repository is connected, go to the Runbooks dashboard: https://app.aviator.co/runbooks/new
On the chat prompt, describe briefly the task that you want to collaborate with the agents on, and select the repository to start with.

This will create a new chat session, where the agents will build a Runbook after analyzing the code. Building the Runbook is a multistep process. During this process, the agents will:
Fetch the code from GitHub
Inspect the query
Analyze the code base to build the context
Understand dependencies
Ask clarifying questions
You can provide feedback via the chat interface or modify the Runbook manually. Runbooks follow a specific pattern and the agents will validate it on every edit.
Execution
Runbooks are typically executed step by step. You can execute the next step by simply clicking "Execute Next" button on the steps view.
This will trigger internally trigger Claude code in the background. You should be able to view all the activity logs in the chat dashboard. Once the step is completed, agents will create one or more PRs and share the links within the corresponding Runbook step.
If you choose to execute all steps, you can click the dropdown and select "Execute all". This will enqueue all steps that will run sequentially creating stacked PRs.
Review
For any PRs generated by the agents, you can review the changes directly in GitHub similar to how you review a PR created by a developer.
After a review is submitted, the agents will analyze all the comments and make corresponding edits.
You can go back and forth with the agents requesting multiple iterations to improve the code. Once you are satisfied with the changes, you can merge the PR manually or using MergeQueue.
Last updated
Was this helpful?