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.

IronBee ensures that AI coding agents verify their changes before completing a task. When an agent edits code, it cannot finish until it exercises the affected paths through real tools — navigating pages in a browser for frontend changes, or connecting to a running Node process for backend changes — and submits a passing verdict. No more “it should work” — every change is tested.

​
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 tested
  • No insight into how the agent spent its time, what it struggled with, or where it kept failing

​
What IronBee does

Enforced verification

The agent must exercise affected code paths with real tools before it can mark a task complete. Browser navigation, screenshots, console checks, and network monitoring are required — not optional.

Session analytics

Every coding session is recorded — time spent coding vs. fixing, pass/fail rates per file, retry counts, and tool usage. The console turns raw session data into actionable insights.

AI-powered analysis

After each session, IronBee runs semantic analysis to surface findings and recommendations — what went wrong, what patterns keep appearing, and what to do next.

CI/CD integration

The IronBee GitHub Action brings the same verification loop into your pull request workflow — automatically verifying changes, fixing issues, and posting evidence on every PR.

Automatic recommendations

After each session, analysis findings are turned into directives that are injected back into the agent’s context — it learns from past mistakes automatically without manual intervention.

​
How it works

Your code change
      │
      ▼
 AI agent edits files
      │
      ▼
IronBee intercepts completion
      │
      ├─ Browser cycle: navigate → screenshot → check console → submit verdict
      │
      ├─ Node cycle (opt-in): connect → set V8 probes → exercise → read snapshots
      │
      └─ Backend cycle (opt-in): HTTP/gRPC/GraphQL/WebSocket → verify responses
            │
            ▼
      Pass → task completes
      Fail → agent must fix and re-verify
All session data — tool calls, verifications, verdicts, timing — is sent to the IronBee Collector and made available in the Console.

​
Supported AI clients

ClientStatus
Claude CodeSupported
CursorSupported
CodexPlanned
OpenCodePlanned

​
Next steps

Quick start

Install the CLI and run your first verification in five minutes.

Key concepts

Learn the terminology: sessions, verifications, cycles, verdicts, and more.