Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.ironbee.ai/llms.txt

Use this file to discover all available pages before exploring further.

Prerequisites

  • Node.js 22 or later — check with node --version
  • An AI coding client: Claude Code or Cursor

How it works

1

Sign up at console.ironbee.ai

Create your account. This gives you access to the dashboard and generates the API key the CLI needs.
2

Install the CLI

npm install -g @ironbee-ai/cli — installs the ironbee command globally.
3

Log in

ironbee login — opens your browser, completes the OAuth flow, and writes your API key to ~/.ironbee/config.json automatically. One-time per machine.
4

Set up your project

ironbee install — auto-detects your AI client (Claude Code or Cursor) and wires up hooks, MCP servers, and the verification skill.
5

Start your app and let the agent work

Run your dev server, then give the agent a task. IronBee intercepts task completion and requires the agent to verify its changes before finishing.
6

View results in the Console

Every session — tool calls, screenshots, verdicts, timing breakdowns — appears in the IronBee Console in real time.

Step 1 — Create your account

Go to console.ironbee.ai and sign up. Your account gives you access to the dashboard and generates the API key the CLI needs to ship session data.

Step 2 — Install the CLI

npm install -g @ironbee-ai/cli
Verify the installation:
ironbee --version

Step 3 — Connect the CLI to your account

Run ironbee login from any directory. It opens your browser at console.ironbee.ai, asks you to confirm, and writes your API key and collector URL to ~/.ironbee/config.json automatically.
ironbee login
The browser opens, you confirm, and the terminal prints:
✓ Logged in successfully!
  Console   https://console.ironbee.ai
  Collector https://api.ironbee.ai/collect
  Config    ~/.ironbee/config.json
You can skip ironbee login and set your credentials by hand instead. Copy your API key from Console → Settings → API Keys, then run:
ironbee config set collector.apiKey <your-api-key> --global
The collector URL defaults to https://api.ironbee.ai/collect — no need to set it unless you are self-hosting.

Step 4 — Set up your project

Navigate to your project directory and run:
cd your-project
ironbee install
IronBee auto-detects your AI client and writes:
  • Hook configuration — the client calls IronBee automatically when the agent finishes
  • Verification skill/rules — the agent knows the verification workflow
  • MCP server entriesbrowser-devtools, node-devtools, and backend-devtools
  • Permissions — grants the agent access to devtools tools
If you are using Cursor, you need one extra step after install: go to Settings → Tools & MCP and confirm all three MCP servers (browser-devtools, node-devtools, backend-devtools) are enabled. See Cursor setup for details.

Step 5 — Start your application

IronBee needs a running application to verify against. Start your dev server as usual:
npm run dev

Step 6 — Let your agent work

Open Claude Code or Cursor and give the agent a task. When it finishes editing code, IronBee intercepts the completion and requires verification:
  1. The agent navigates to the affected pages in a real browser
  2. It takes screenshots, checks the console, and tests functionality
  3. It submits a verdict — pass or fail
  4. If it fails, the agent fixes the issues and re-verifies
You will see the session appear in the IronBee Console in real time.

Step 7 — View your results

Open the IronBee Console and navigate to your project. You will find:
  • The session with all activity recorded
  • Screenshots and browser interactions from each verification cycle
  • Pass/fail verdict with evidence
  • Timing breakdowns — how long the agent spent coding, verifying, and fixing

What’s next?

CLI configuration

Customize verify patterns, retry limits, and devtools settings.

Enable backend verification

Add Node.js or backend protocol verification for backend code changes.

GitHub Action

Verify changes automatically on every pull request.

Explore the console

Understand sessions, verifications, findings, and recommendations.