Skip to main content
Zero test scriptsReal Playwright browserAI-generated Gherkin flows

Point it at a URL.
Walk away.

The Autonomous Exploratory Tester logs into your application, crawls every page, generates Gherkin test flows using AI, executes each one in a real browser, and triages every failure into a structured bug report — all without a single line of written test input.

Autonomous Exploratory Tester 5 credits
Application URL *
https://your-application.com
Username / Email
admin@company.com
Password
••••••••••
Advanced  ·  Max pages: 8  ·  Depth: 2
Credentials never stored — used only to drive the run
5
Fully automated phases
Login · Crawl · Discover Flows · Execute · Triage Bugs — every step handled by the agent
25
Pages crawled per run
Configurable scope from 1 page up to 25, with crawl depth control from 1 to 4 levels
0
Test scripts required
Provide a URL and optional credentials — AI generates and executes every test flow
How It Works

Five automated phases. Zero written input.

From the moment you hit Launch to the moment bugs appear in Jira or ClickUp, every step is handled by the agent.

Phase 01

Login

The agent opens your application URL in a real Playwright browser and heuristically locates the login form — finding the password field, username/email input, and submit button without any written rules. It fills your credentials, submits the form, and confirms success by checking for a URL change, appearance of a logout link, or disappearance of the password field.

Works on public apps with no login form too — the agent detects the absence of a password field and proceeds directly to crawl, no credentials required.
Phase 02

Crawl

Starting from the post-login page, the agent performs a breadth-first crawl of your application, staying strictly within the same origin — it never wanders to external sites. For every page visited it records the title, headings, all links, visible buttons, input fields, and form count, building a complete interactive map of your UI surface.

A built-in destructive-action filter prevents the crawler from following logout, delete, cancel-subscription, or similar links — keeping your session alive and your data intact.
Phase 03

Discover Flows

The complete crawl map — page titles, headings, button labels, input field names — is fed to AI, which synthesises up to 6 realistic Gherkin test flows. Scenarios cover navigation sequences, form submissions, search interactions, filtering, and pagination, all referencing real labels from your live application. A deterministic heuristic fallback ensures flows are always generated.

Each flow is a standalone Gherkin Feature with one Scenario that starts from a concrete URL and references actual button and field labels discovered during the crawl.
Phase 04

Execute

Every synthesised flow is executed in a real browser through the same PipelineRunner that powers QAEverest's UI Automation module. The browser session starts pre-authenticated — the login state saved during Phase 1 is injected — so every scenario begins exactly where a real user would. Per-flow results include pass/fail status, the failed step, error detail, and a screenshot on failure.

The agent launches Chromium, falling back to Firefox if unavailable. Flows run headlessly in the background — no browser window appears on your machine.
Phase 05

Triage Bugs

Each failed flow is analysed by AI, which produces a structured bug candidate: a concise title, a severity rating (Critical, High, Medium, or Low), the expected behaviour, and the actual behaviour. The Gherkin flow itself serves as the built-in reproduction steps. Bug cards appear in the results view instantly, ready to file.

Heuristic fallback classifies bugs even without AI connectivity — timeouts and navigation errors are rated High, other failures Medium — so no failure goes unrecorded.
What You Get

Every failure becomes a structured bug report

The agent doesn't just flag failures — it writes the bug for you. Each failed flow becomes a complete bug candidate with a title, severity, expected vs actual behaviour, and the Gherkin flow as reproduction steps — ready to file in one click.

CriticalApp crash, login failure, navigation timeout, or 500 error. Fix before any release.
HighMajor feature broken or core workflow blocked. Significant impact on real users.
MediumUnexpected behaviour with a workaround available. Schedule for the current sprint.
LowEdge-case or minor observation with no workflow impact. Log in backlog.
CriticalStep failed: Navigate to checkout page
ExpectedCart page loads with selected items and order total visible
ActualNavigation timeout — page did not respond within 30 seconds
FlowEnd-to-end checkout — add item and proceed to payment
Steps to reproduce
Feature: Checkout flow Scenario: Add item and proceed Given I am on the product listing When I click "Add to cart" And I click "Proceed to checkout" Then I should see the cart summary
File to Jira
File to ClickUp
Compatibility

Works for public and protected applications

No login? No problem. Credentials? The agent finds the form and fills it.

Public applications

If the target URL has no password field, the agent detects this automatically and proceeds directly to crawl — no credentials configuration needed.

  • E-commerce product catalogues
  • Public dashboards and portals
  • Documentation and support sites
  • Marketing and landing pages

Protected applications

Provide your application username and password. The agent locates the login form, fills it, verifies success, and saves the session state so every executed flow starts pre-authenticated.

  • SaaS application dashboards
  • Admin and management panels
  • Internal tools and intranets
  • Customer and partner portals
Safe by design during crawlThe crawler never follows links whose text or URL contains logout, delete, cancel subscription, deactivate, reset, or similar destructive hints — your session stays alive and your data stays untouched throughout the run.

Your credentials never touch our database

At run launch, your username and password are passed to the agent over a secure stdin channel as JSON — they never appear on CLI arguments (which are visible in the process table), never written to disk, and never stored in the database. The run record retains only a masked username such as “Ad***” for display purposes.

Stdin-only transfer Never in the process table Never written to disk Never stored in the database
Bug Filing

One click from bug candidate to Jira or ClickUp

Every bug card has a File to Jira and a File to ClickUp button. The agent pre-fills the entire report — you only need to provide your project key or list ID.

File to Jira

Provide your Jira project key (e.g. QA). The agent creates an issue in your configured Jira instance using your API key from Settings.

SummaryAI-written bug title
SeverityCritical / High / Medium / Low
DescriptionExpected · Actual · Target URL · Flow
StepsGherkin flow as code block
Issue typeBug

File to ClickUp

Provide your ClickUp list ID. The agent creates a task using the token configured in Settings — personal or organisation-level.

NameAI-written bug title
SeverityCritical / High / Medium / Low
DescriptionExpected · Actual · Target URL · Flow
StepsGherkin flow as code block
Linked issueURL returned and stored with the run
Once filed, the bug card shows the issue key (e.g. QA-42) with a direct link to the tracker. Bugs already filed cannot be filed again from the same run.

See It In Action

Enter your application URL and preview the Login → Crawl → Discover Flows → Execute → Triage Bugs run.

Your bug candidates will appear here.

Explore Now!

Book a DemoBecome a Partner