Skip to main content
Ito is an AI-powered runtime code review agent that runs in a real browser. When a pull request is opened or updated, Ito automatically tests your app and reports any bugs it finds — directly on the PR, with video evidence and reproduction steps. Here’s what happens from the moment you open a PR to the moment you see results.

​
The automated testing pipeline

1

A pull request is opened or updated

When you open a new PR or push new commits to an existing one, GitHub sends a webhook event to Ito. Ito reviews eligible pull requests automatically when the repository’s Automation settings are active.Draft pull request coverage is configurable per repository. If automatic draft reviews are off, comment @itoqa on a draft PR to request a one-time review of its latest commit.
2

Ito receives the webhook

Ito picks up the event and queues a new test run. The dashboard immediately reflects the incoming run with a Running… status on the PR row.
3

A test environment is provisioned

Ito spins up an isolated test environment for the run. This ensures each PR is tested independently and results aren’t affected by other runs happening in parallel.
4

The AI agent explores your app in a real browser

The Ito AI agent opens your app in a real browser and starts exploring it. The agent focuses on user flows affected by the changes in the PR — it clicks through the UI, fills out forms, navigates between pages, and exercises both desktop and mobile scenarios.The entire session is recorded as a video.
5

Bugs are identified and classified

When the agent encounters unexpected behavior — an error, a broken flow, a visual regression — it records the finding and classifies it by severity:
  • Critical — blocks core functionality or breaks key user flows
  • High — impacts important features or significantly degrades the user experience
  • Medium — noticeable issues that affect usability but don’t block core flows
  • Low — minor issues or edge cases with limited user impact
Ito also checks whether each issue was introduced by the current PR or was already present beforehand, so you can focus on what the PR actually changed.
6

A test report is posted as a PR comment

When GitHub comments are enabled for the repository, Ito posts a test report directly on the pull request. The report shows what Ito tested, the overall result, and any findings, so you have context without leaving GitHub.
Ito posts a passing report when all tests pass. When Ito finds issues, it also adds applicable inline comments on the relevant GitHub diff lines. If Comments is off, results remain available in the Ito dashboard for your review.
7

Full results appear in the dashboard

The Ito dashboard at app.ito.ai shows the complete picture for every PR:
  • A list of all test cases with pass/fail status
  • A video recording of the full browser session, seekable to the exact moment an issue occurred
  • Step-by-step reproduction instructions for each bug
  • Code analysis pointing to the specific files and line ranges relevant to the finding

​
What you get for every run

Video recording

A full recording of the browser session. When you select a test case in the dashboard, the video seeks to the exact timestamp where the issue occurred.

Reproduction steps

A numbered list of actions the agent took to trigger the bug, so you can reproduce it manually or share it with your team.

Code analysis

A written explanation of why the bug likely occurred, with links to the relevant files and line ranges in your codebase.

Severity ratings

Each finding is rated Critical, High, Medium, or Low, so you can prioritize fixes before merging.

​
Frequently asked questions

Ito automatically reviews eligible pull requests when they are opened or updated. Eligibility depends on the repository’s Automation settings and applicable author, seat, trial, billing, bot, and draft-PR rules.
The agent performs AI code review by manually testing your app in a real browser. It navigates your UI, clicks buttons, fills out forms, and moves through user flows. It uses a real browser, so it exercises your app exactly as a user would — including JavaScript execution, network requests, and rendering.
Yes, when GitHub comments are enabled for the repository. Ito posts a passing test report that confirms what tests it ran that passed. Inline comments are only added to the Test Report comment for bugs and issues found in one of Ito’s tests for that PR commit.
Yes. Ito tracks whether each failing test case was introduced by the current PR or was already failing. Pre-existing failures are shown separately in the dashboard so you can focus on what your changes actually broke.