# AI-Implement

## Docs

- [Environment variables for AI-Implement](https://docs.builddown.ai/configuration/environment-variables.md): All environment variables the AI-Implement orchestrator reads at startup, what each one does, and which are required versus optional.
- [AI planning phase: architecture analysis](https://docs.builddown.ai/configuration/planning.md): How the AI planning phase works, what structured architecture and test plan comments it posts to Linear, and how to enable, disable, or configure it per team.
- [Configure team-to-repo mappings](https://docs.builddown.ai/configuration/team-repo-mappings.md): How to map Linear teams to GitHub repos in the admin UI, including concurrency limits, execution mode, session mode, and provider settings.
- [Workflow template files and front matter](https://docs.builddown.ai/configuration/workflow-templates.md): How the workflow files synced to target repos work, the front matter keys they read from WORKFLOW.md and PLANNING.md, and how to run a resync.
- [Add custom pipeline steps to AI-Implement](https://docs.builddown.ai/customize/custom-steps.md): How to override built-in pipeline steps or add entirely new ones by placing TypeScript modules in the custom/steps/ directory of your AI-Implement installation.
- [Customize PLANNING.md for architecture analysis](https://docs.builddown.ai/customize/planning-md.md): How to customize PLANNING.md: control what Claude explores and what architecture and test plan comments it posts to Linear before each implementation run.
- [Use a custom Fly Machine runner image](https://docs.builddown.ai/customize/runner-image.md): How to point AI-Implement at a custom Docker runner image when your repo needs tools or language runtimes not included in the default Fly Machine environment.
- [Customize WORKFLOW.md for your codebase](https://docs.builddown.ai/customize/workflow-md.md): How to customize WORKFLOW.md: set the model, repo context, quality checklist, and lifecycle hooks Claude follows for every implementation run in your repo.
- [How AI-Implement works: the full lifecycle](https://docs.builddown.ai/how-it-works.md): The end-to-end flow from applying the AI-Implement label in Linear to a merged PR with gap analysis, including planning, labels, and gap-fill runs.
- [AI-Implement: From Linear tickets to pull requests](https://docs.builddown.ai/introduction.md): AI-Implement turns your Linear backlog into pull requests by running Claude Code against labeled issues. Your tickets are the prompts.
- [Use Anthropic API or Claude OAuth with AI-Implement](https://docs.builddown.ai/providers/anthropic.md): Configure AI-Implement to use the Anthropic API or Claude Code OAuth token as the Claude provider, with auth precedence and model selection explained.
- [Use AWS Bedrock with AI-Implement](https://docs.builddown.ai/providers/aws-bedrock.md): Configure AI-Implement to invoke Claude through AWS Bedrock using GitHub OIDC and an IAM role. No static AWS credentials are required or supported.
- [Quick start: your first AI-generated PR](https://docs.builddown.ai/quickstart.md): Set up AI-Implement locally and get your first Claude-generated pull request in about 30 minutes, from cloning the repo to watching the PR appear.
- [Admin UI reference for AI-Implement](https://docs.builddown.ai/reference/admin-ui.md): What the AI-Implement admin dashboard lets you manage, including team/repo mappings, active sessions, secrets, and the dispatch audit log.
- [Gap analysis: what Claude posts on every PR](https://docs.builddown.ai/reference/gap-analysis.md): How the gap analysis comment works, what it contains, and how to trigger a gap-fill run on an existing AI-Implement PR using the /ai-implement comment.
- [Linear labels: triggers and status indicators](https://docs.builddown.ai/reference/labels.md): The Linear labels that trigger and track AI-Implement runs, what each label means, and when each one is applied automatically by the orchestrator.
- [Configure Slack and Teams notifications](https://docs.builddown.ai/reference/notifications.md): How to configure AI-Implement to send Slack or Microsoft Teams webhook notifications when issues are dispatched and when implementation runs complete or fail.
- [Troubleshoot common AI-Implement problems](https://docs.builddown.ai/reference/troubleshooting.md): Common issues when running AI-Implement — missing PRs, stuck sessions, Bedrock errors, and notification problems — with step-by-step resolution guidance.
- [Deploy the AI-Implement orchestrator](https://docs.builddown.ai/setup/deploy.md): How to run the AI-Implement orchestrator locally for development or deploy it as a persistent service on Fly.io for production use.
- [Create a GitHub App for AI-Implement](https://docs.builddown.ai/setup/github-app.md): How to create the GitHub App that AI-Implement uses to authenticate, dispatch workflows, and open pull requests under the app's identity.
- [Prerequisites for running AI-Implement](https://docs.builddown.ai/setup/prerequisites.md): What accounts, credentials, and access you need before installing AI-Implement — Linear, GitHub, a Claude provider, and a place to run the orchestrator.
- [Connect a GitHub repo to AI-Implement](https://docs.builddown.ai/setup/target-repo.md): How to sync workflow templates into a target GitHub repo, map it to a Linear team in the admin UI, and label your first issue to trigger an AI-generated PR.