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

> ## Agent Instructions
> Automate.ax automations are TypeScript programs.
> Use Bun for installation and command examples.
> Use Automate.ax for the product name and automate.ax for the package, CLI, and domain.
> Treat documented public APIs as current; do not invent transitional or deprecated names.

# Start with a coding agent

> Build, deploy, authorize, and test an Automate.ax automation with a coding agent.

Describe the automation you want in one prompt. Your coding agent uses the Automate.ax API reference and command-line tool to build it.

Start with this prompt:

```text wrap theme={null}
Using https://docs.automate.ax/llms.txt, build, deploy, and test an automation that <what you want>.
```

For example, notify Slack from Linear, Asana, and Trello:

```text wrap theme={null}
Using https://docs.automate.ax/llms.txt, build, deploy, and test an automation that posts in Slack #chat whenever a Linear issue, Asana task, or Trello card is completed.
```

## What happens next

1. **Connect your agent to Automate.ax.** The agent starts the Automate.ax login flow and opens your browser. You sign in to Automate.ax and authorize the agent's command-line session.
2. **The agent writes the automation.** It creates an Automate.ax project and writes the automation from your prompt. You don't need to edit files or run commands.
3. **The agent deploys it.** Automate.ax checks the code and starts the deployment.
4. **Set parameters and accounts.** The agent opens **Parameters & Accounts** when the automation declares project-specific values or uses Slack, Google, Linear, or another service. Set the requested values, assign an account you already connected, or connect a new one. Automate.ax resumes after every requirement is ready.
5. **The agent completes one-time setup.** If the automation needs a new resource, such as a spreadsheet, the agent creates it, removes any temporary setup code, and deploys the finished automation.
6. **The agent tests it.** It starts a safe run, checks the execution and result, then reports what's live and how to run it again.