> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.tester.army/llms.txt.
> For full documentation content, see https://docs.tester.army/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.tester.army/_mcp/server.

# Agentic Usage

Give your coding agent access to the TesterArmy CLI when you want it to set up
and run QA without leaving your development loop.

The CLI is designed to be self-discoverable. Agents can start with `ta --help`
and use subcommand help to figure out the exact workflow.

## What agents can do

With an API key, an agent can:

* create and list projects
* save project memories as durable testing context
* create dashboard tests
* run tests locally or remotely
* wait for remote runs and inspect run history
* upload iOS Simulator apps for mobile tests

## Setup

Install and authenticate once:

```bash
npm install -g testerarmy
ta auth
ta status --json
```

For non-interactive sessions, set:

```bash
export TESTERARMY_API_KEY="YOUR_KEY"
```

## Prompt your agent

```txt
Use the TesterArmy CLI (`ta`) to set up and run QA for this project.
Start with `ta --help`, use subcommand help as needed, prefer JSON output,
and report the commands you ran plus run IDs and results.
```

## Useful entrypoints

```bash
ta --help
ta projects --help
ta memories --help
ta tests --help
ta tests run --help
ta runs --help
```

## Safety

* use scoped API keys when possible
* prefer `--json` for agent-readable output
* avoid putting secrets in shell history
* ask before deleting projects, memories, or tests