Skip to main content
IronBee is your AI QA engineer. It verifies code changes the way a QA engineer would: it opens the running application, exercises what changed, and reports what works and what doesn’t, with the evidence to prove it. It also reviews your pull requests the way a careful teammate would, reading each change against the rest of the code. You can use any of these, or all of them:
  • Code review on your pull requests. Install the IronBee GitHub App, or connect a GitLab group or a Bitbucket workspace, and IronBee reviews every pull request or merge request in the repositories it covers. Its findings land as comments on the pull request and in the console.
  • Code security on your repositories. On the same GitHub, GitLab or Bitbucket connection, an owner or an admin can turn on scheduled security scans of a repository’s default branch. What a scan finds is kept as records in the console, for your team to decide on.
  • On your deployments and pull requests. Connect Vercel or Netlify, or add the GitHub Action, the GitLab component or the Bitbucket Pipe, and IronBee verifies each preview deployment, pull request or merge request on its own infrastructure. The result lands on the pull request, on the deployment, and in the console.
  • Inside your AI coding agent. The IronBee CLI gives Claude Code, Cursor and Codex the tools to verify their own changes in a real browser, a running backend or a terminal before they call the work done.

The problem

AI coding agents are fast, but they lack accountability. An agent can write hundreds of lines of code, declare success, and move on without ever checking if the browser renders correctly, if the API responds as expected, or if anything broke. Teams using agentic development today face:
  • Silent regressions that only surface in code review or production
  • No evidence that a change was actually verified
  • No insight into how the agent spent its time, what it struggled with, or where it kept failing

What IronBee does

Code review on every pull request

Every pull request or merge request gets a review with inline comments, suggested fixes, a summary and a check that can hold a merge. Your team’s rules and memories steer it.

Security scans of the default branch

Turn code security on for a repository, and IronBee scans its default branch on a schedule. Each record says where the problem is, how it could be used and how to fix it.

Verification on every change

Every preview deployment on Vercel or Netlify, every push or pull request with the GitHub Action, every merge request or push to the default branch with the GitLab component, and every pull request or push with the Bitbucket Pipe starts a verification run. An agent reads the change and exercises it against your running app.

Verification inside your agent

With the IronBee CLI, your AI coding agent verifies its own changes with real tools. In assist mode you ask for a verification; in enforce mode the agent can’t finish until the verification passes.

Evidence for every run

Every verification run is captured and available in the console: the recording, screenshots, actions, network requests, traces, and logs. Watch a run live while it’s in progress.

Results where you work

Results land on the pull request or merge request as a check, inline comments on the findings and a comment, as a Vercel deployment check or on the Netlify deploy page, and in the console. The GitHub Action, the GitLab component and the Bitbucket Pipe can also fix what they find.

Security

Never collects prompt content, file content, tool output, credentials (API keys and authentication tokens), or any PII beyond your org-configured email. Your code and secrets stay on your machine.

How it works

Code review on your pull requests

  1. A pull request opens or gets a push in a repository the IronBee GitHub App covers, or in a GitLab or Bitbucket repository you picked.
  2. IronBee reads the change against the rest of the repository, with your rules and memories.
  3. It posts a review with a comment for each finding, adds a summary, and sets the IronBee review check, on GitLab a pipeline status where IronBee writes one, or on Bitbucket a build status. Every review and finding also appears under Code review in the console.
See Code review of pull requests.

On your deployments and pull requests

  1. A preview deployment on Vercel or Netlify, a push or pull request with the GitHub Action, a merge request or push with the GitLab component, or a pull request or push with the Bitbucket Pipe starts a verification run.
  2. An agent on IronBee reads the change, then verifies it. A web app is opened in a browser and exercised like a user would. An API is called directly and its responses are checked against the contract.
  3. The verdict and its evidence land on the pull request, on the deployment, and on the project’s Verifications tab in the console, where you can also follow the run live.
See How integrations work.

Inside your AI coding agent

This is enforce mode. In the default assist mode, the same verification runs when you or the agent ask for it with /ironbee-verify, and nothing blocks the agent. Every session and its verification cycles are available in the console. See How verification works.

Supported AI clients

Next steps

Quickstart

Connect GitHub, GitLab, Bitbucket, Vercel or Netlify, or set up the CLI.

Key concepts

Projects, verification runs, environments, sessions and verdicts.