Autotest

Spawn agents to autonomously explore and test a live web application.

Spawn parallel agents that navigate a live web application using a real browser, find bugs, take screenshots, and optionally create GitHub issues or PRs with their findings.

paragon autotest [description] [flags]

Unlike paragon test which runs pre-written Playwright tests, autotest uses agents that explore your app autonomously — no test files needed. Each agent gets its own isolated browser instance.

How It Works

Planning — A planning agent analyzes the target app and distributes testing work across agents.
Exploration — Each agent navigates the app in a real browser, performing actions like clicking, typing, scrolling, and navigating between pages.
Reporting — Findings are compiled into a report with screenshots, reproduction steps, and severity ratings. Playwright test code is auto-generated from the agent's actions.
GitHub integration (optional) — Findings are filed as GitHub issues or bundled into a PR.

Flags

Flag	Type	Default	Description
`--url`	`string`	(required)	Target URL to test.
`--prompt`	`string`	—	What to test (e.g. `"test the checkout flow"`).
`--agents`	`int`	`1`	Number of parallel agents (1–8). Each agent gets its own browser.
`--model`	`string`	`paragon-max`	Model to use for the agents.
`--timeout`	`int`	`15`	Per-agent timeout in minutes.
`--auth`	`string`	—	Path to a cookies JSON file (browser-use export format) for pre-authenticated sessions.
`--login`	`string`	—	Login instructions for the agent in plain English (e.g. `"click Login, type user@test.com into email, type pass123 into password, click Submit"`).
`--session`	`string`	—	Team auth session name or ID stored in Supabase.
`--repo`	`string`	—	GitHub repo for issue/PR creation (`owner/repo`).
`--pr`	`bool`	`false`	Create a PR with findings instead of an issue. Defaults to `true` when `--repo` is set.
`--skip-github`	`bool`	`false`	Skip GitHub issue/PR creation even if `--repo` is set.
`--json`	`bool`	`false`	Output results as structured JSON.
`-q, --quiet`	`bool`	`false`	Minimal output.

Examples

# Basic: test a local app
paragon autotest --url http://localhost:3000 --prompt "make sure the page loads"

# Run against production with multiple agents
paragon autotest --url https://yourapp.com --prompt "test the checkout flow" --agents 4

# Test with login instructions
paragon autotest --url https://yourapp.com --login "click Login, type user@test.com into email, type pass123 into password, click Submit" --prompt "test the dashboard"

# Use a cookies file for auth
paragon autotest --url https://yourapp.com --auth ./cookies.json --prompt "test account settings"

# Use a shared team auth session
paragon autotest --url https://yourapp.com --session "staging-admin" --prompt "test admin panel"

# File findings as a GitHub PR
paragon autotest --url https://yourapp.com --prompt "test user registration" --repo acme/webapp --pr

# Skip GitHub, just see findings locally
paragon autotest --url http://localhost:3000 --prompt "test login" --skip-github

# JSON output for CI pipelines
paragon autotest --url https://yourapp.com --prompt "smoke test" --json --quiet

Authentication

Autotest supports three ways to authenticate agents with your app:

Method	Flag	When to use
Login instructions	`--login`	Simple login forms. Describe the steps in plain English.
Cookies file	`--auth`	Export cookies from browser-use and pass the JSON file.
Team session	`--session`	Shared, encrypted auth sessions stored in Supabase for team reuse.

Managing Team Auth Sessions

Use paragon autotest auth to manage shared authentication sessions:

# List all team auth sessions
paragon autotest auth list

# Capture a new session (opens a browser — log in manually, then close)
paragon autotest auth capture https://yourapp.com --name "staging-admin"

# Use the captured session
paragon autotest --url https://yourapp.com --session "staging-admin" --prompt "test dashboard"

# Delete a session
paragon autotest auth delete "staging-admin"

Output

Each finding includes:

Title and description of the bug
Severity rating (critical, high, medium, low)
Screenshots captured during the session
Reproduction steps from the agent's browser actions
URL where the issue was found
Auto-generated Playwright code to reproduce the bug

When --repo is set, findings are automatically filed as GitHub issues or bundled into a PR with the generated Playwright tests.

E2E Testing Configuration