Quickstart

Pick the surface that fits how you want to work — they all drive the same agent.

Web app

1. Open the Agentiqa web app and sign in.
2. Create a project by entering the URL of the app you want to test (and a name).
3. Open the Assistant and ask for what you want — for example "Test the signup flow" or "What can you test here?"
4. Review the agent's scope and plan checkpoints, then confirm the findings it reports.

Cloud execution runs the browser on Agentiqa's infrastructure — nothing to install.

Desktop app

1. Download the desktop app (see Desktop App) and sign in.
2. Create a project with your app's URL.
3. Ask the Assistant to test it. The desktop app drives a built-in headed browser, so you can watch the agent work.

The desktop app has the full capability set — see Desktop vs Web.

CLI

Requires Node.js 18+ (Node 20 recommended).

# Explore a URL with the agent (in-process engine)
npx -y agentiqa@latest explore "Find bugs on this page" --url https://example.com

# Run saved test plans against the hosted cloud engine (CI-friendly)
AGENTIQA_SERVICE_KEY=sk_... npx -y agentiqa@latest run --engine https://engine.agentiqa.com

See the CLI guide and the generated CLI reference. To run a labeled subset or run plans in parallel, see Labels and Parallel runs.

Coding agent

Already working in Claude Code, Cursor, or Codex? Drive Agentiqa from there: your coding agent explores, you review the draft plan in chat, and it saves and runs the plan for you — the same agent proposes, you curate loop, on the command line.

1. Install the Agentiqa plugin. In Claude Code:

   /plugin marketplace add Agentiqa/agentiqa-plugin
   /plugin install agentiqa@agentiqa

2. Create a project-scoped service key in Project Settings → CLI Service Keys and expose it to your agent's shell as AGENTIQA_SERVICE_KEY (never paste it into chat).

3. Ask your agent to test something — for example "Explore the checkout flow and draft a plan." It runs the exploration, shows you the draft, and on your explicit approval saves the plan (tp_…) and runs it.

See Agent skill for the full explore → review → save → run → revise loop, other coding agents (Cursor, Codex), and how the plan hands off to CI.

GitHub Action

Run your saved plans in CI and gate the job on the outcome:

- uses: agentiqa/qa-action@v1
  with:
    service-key: ${{ secrets.AGENTIQA_SERVICE_KEY }}

See the GitHub Action guide and CI Integration.