Agentic Usage

​

What agents can do

• create and list projects
• create and delete static project environments (--name/--url flags)
• save project memories as durable testing context
• create dashboard tests
• create test groups and add or remove tests
• list and create project credentials, and list project files
• queue remote dashboard runs (default) and target saved environments with --env
• validate development changes against a saved preview or tunnel environment with --env
• wait for, cancel, and inspect remote runs
• upload iOS Simulator apps and Android artifacts for mobile tests
• report TesterArmy bugs, misleading docs, or missing capabilities to the TesterArmy team with ta feedback

​

Setup

npm install -g testerarmy
ta agent init
ta auth
ta status --json

export TESTERARMY_API_KEY="YOUR_KEY"

npx add-mcp --global --name testerarmy https://tester.army/mcp

​

Prompt your agent

Use TesterArmy CLI (`ta`) for QA. Start with `ta agent init`, then discover
workflows with `ta docs --json` or `ta docs <topic>`. Use `--json` for automation;
on failure, follow `error.hint`. Report commands, run IDs, results, and artifacts.

​

Useful entrypoints

ta agent init
ta docs
ta docs --json
ta docs agent
ta docs mcp
ta docs auth
ta docs projects
ta docs memories
ta docs tests
ta docs groups
ta docs runs
ta docs ci
ta docs feedback

​

Safety

• API keys have full access to their workspace, so keep them in a secret manager
• prefer --json for agent-readable output
• use JSON error envelopes to decide the next action instead of parsing text
• avoid putting secrets in shell history
• ask before deleting projects, environments, memories, or tests