> ## Documentation Index
> Fetch the complete documentation index at: https://docs.builddown.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# AI-Implement: From tickets to pull requests

> AI-Implement turns your Linear or Jira backlog into pull requests by running Claude Code against marked issues. Your tickets are the prompts.

AI-Implement is an orchestration service that connects your **Linear** or **Jira** workspace to one or more GitHub repositories. You mark an issue with the `AI-Implement` label (Linear) or set its `AI-Implement Status` to `Ready` (Jira), and within minutes Claude Code checks out the right repo, reads your codebase, implements the ticket, opens a pull request, and posts a gap analysis comparing what was built to what you asked for. Your team reviews everything in the tools they already use — Linear or Jira, plus GitHub — without learning a new interface.

## Who it's for

AI-Implement is built for software teams, not individual developers. If you already manage work in Linear or Jira and want well-specified tickets to turn into PRs without manually opening them yourself, this is designed for you.

You'll get the most value if:

* Your team runs tickets through Linear or Jira and wants AI output to land in your existing review process.
* You have focused, well-specified issues where the requirement fits in a single pass.
* You're comfortable operating a small Node.js service on Fly.io (or similar infrastructure).
* You want Claude to run inside your own CI, with your own secrets, against your own provider.

<Note>
  AI-Implement works best with clearly scoped tickets. Claude handles focused, well-specified issues well and struggles with sprawling or vague ones. The quality of the ticket is the quality of the prompt.
</Note>

## What you need to get started

Before you can run AI-Implement, you'll need accounts and credentials across four services:

* **Linear or Jira Cloud workspace** — where your issues live and where the `AI-Implement` label or two custom fields (`AI-Implement Status` and `AI-Implement Repo`) are applied
* **GitHub App** — authenticates the orchestrator to dispatch workflows and open PRs
* **Fly.io account** — where the orchestrator service runs (a single shared-cpu-1x machine is enough)
* **Anthropic API key** — or an AWS Bedrock setup with the appropriate IAM role

<Columns cols={2}>
  <Card title="Quick start" icon="rocket" href="/quickstart">
    Get from zero to your first AI-generated PR in under 30 minutes.
  </Card>

  <Card title="How it works" icon="diagram-project" href="/how-it-works">
    Understand the full lifecycle from ticket to merged PR.
  </Card>

  <Card title="Prerequisites" icon="list-check" href="/setup/prerequisites">
    Everything you need to set up before deploying the orchestrator.
  </Card>

  <Card title="Customize prompts" icon="pen-to-square" href="/customize/workflow-md">
    Tailor the WORKFLOW\.md and PLANNING.md templates for your stack.
  </Card>
</Columns>

## Key concepts

**The ticket is the prompt.** Writing well-specified tickets is something teams already know how to do. AI-Implement uses that skill — and the cross-issue structure in your ticket backlog — instead of asking anyone to learn prompt engineering.

**The PR is the work product.** Every run produces a pull request, a gap analysis comment, and a ticket-system status change. Reviewers see exactly what was attempted and where it fell short of the spec.

**One orchestrator, many repos.** A single AI-Implement service can dispatch workflows across multiple repos in multiple GitHub organizations. **Project mappings** — each one connecting a Linear team or Jira JQL to a GitHub repo — are managed in the admin UI.

**Gap-fill on demand.** After reviewing a PR, comment `/ai-implement` on it to send Claude back in for a second pass on the same branch. The gap analysis comment updates automatically.