Skip to content
Meet Explorbot

Autonomous exploratory testing

An AI agent that investigates your product like your most relentless QA engineer — and turns every discovery into a test you can keep. This is vibe-testing.

See it in action

Watch Explorbot work, unscripted

A real session: the agent plans, drives the browser and writes tests on the fly — no human in the loop.

explorbot · autonomous session
Live
Explorbot is exploring…
Recorded live — Explorbot researches the app, plans four tests, then executes them step by step.

Explores with intent

Give it a goal — “find checkout defects” — and it navigates your app pursuing that mission, not a fixed script.

Finds the unexpected

Negative quantities, blank states, broken back buttons — and it even tries SQL and JS injection in your inputs.

Writes the test for you

Every flow it completes is saved automatically as a clean Playwright or CodeceptJS test you can keep.

Never clocks out

Runs on its own for hours on CI — 30 to 50 meaningful tests an hour, at roughly $1 of tokens.

Works with your suite

It won't replace your regression tests — it covers what they can't

Your Playwright and CodeceptJS suites re-run the same fixed steps every build. Explorbot re-explores the very same pages new ways — clicking new UI elements and paths your scripts never touch.

Regression suite

Same steps · every build

/login /cart /checkout /account same path, every run
in parallel

Explorbot

New ways & new UI · every run

/login /cart /checkout + new UI + edge states + new feature

Re-explore what you already test

Scripted tests repeat the exact same steps every build. Run Explorbot beside them and it re-explores the same pages new ways each time — clicking new UI elements and paths your script never touches — to surface regressions hiding just off the scripted route.

  • Runs in parallel with Playwright, Cypress or CodeceptJS
  • Revisits known pages, never the same way twice
  • Finds new UI elements and regressions scripts miss

Cover features before tests exist

A brand-new feature with zero automated coverage? Point Explorbot at it. From the live UI plus the specs and domain knowledge you give it, it works out the basic test cases and runs them straight away.

  • Reads the page, your specs and domain rules
  • Derives and runs the essential test cases
  • Gives new work real coverage from day one
How a session works

From blank page to passing test

A team of specialised agents hands off down the line — research, plan, execute, verify, keep.

Maps the UI into sections Indexes every element No docs or source needed Drafts test scenarios Normal, curious, edge State changes first Drives the browser Pilot breaks dead loops Adapts as apps change Verifies before passing Clusters by root cause Captures evidence Saves Playwright tests Report + screencasts Learns for next run 01 · RESEARCHER Research 02 · PLANNER Plan 03 · TESTER Execute 04 · ANALYST Verify 05 · HISTORIAN Keep
Under the hood

A crew of specialised agents

Cheap, fast workers do the clicking and reading; smart managers make the calls — so a full session costs cents, not dollars.

Researcher

Maps each page into sections, locators and an element index.

Planner

Drafts scenarios and cycles testing styles — normal, curious, edge.

Tester

Drives the browser one real step at a time to run each scenario.

Pilot

Supervises the Tester and breaks it out of dead loops.

Captain

Orchestrates the session and takes your commands in real time.

Navigator

Executes browser actions with resilient locator fallbacks.

Analyst

Writes the run report, clustering defects by root cause.

Historian

Banks passing flows as tests and learns from every run.

Plus the API crew, accessibility checks and self-healing reruns — all open source.

The takeaway

What every run leaves behind

Tomorrow's regression coverage comes from today's exploration — captured, not lost.

Runnable tests

Playwright or CodeceptJS specs for every flow it completes.

Test plans

Markdown scenarios in a format ready to sync to your TMS.

Reports & screencasts

A human-readable run summary with step-by-step video evidence.

Learned experience

Knowledge it reuses to test your app smarter on the next run.

On autopilot

Ship-ready QA, every day

Schedule Explorbot nightly to sweep your routes, analyse the run, report to your team — and ping you only when failures break the usual rate.

Runs nightly on CI No human in the loop About $1 per hour /posts, /admin, /settings Maps every route 30–50 tests / hour Clusters by root cause Compares to baseline Computes failure rate Summary to your team HTML report + evidence Syncs to Testomat.io Quiet on green runs Alerts on failure spikes Slack or email DAILY · CRON Schedule EXPLORE Cover routes ANALYZE Analyze REPORT Report ALERT Notify
Additionally

Two more bots beyond the UI

Explorbot drives the browser. ApiBot and DocBot bring the same autonomy to your APIs and your documentation.

API testing

ApiBot

ApiBot autonomously tests your API endpoints — hunting for security breaches, edge cases, and the request combinations a scripted suite would never try.

  • Probes endpoints for security breaches
  • Hammers edge cases and bad inputs
  • Chains API call combinations on its own
$ explorbot api explore /users
Living documentation

DocBot

DocBot walks through your app and builds documentation straight from the live UI, so it is never outdated. It is not a spec — it captures how things actually look and behave right now, even when no spec exists or the UI has grown past it. It documents the real, current state of your app.

  • Built from the live UI, not a spec
  • Never outdated — reflects today’s app
  • Documents reality, even beyond the spec
$ explorbot docs collect /dashboard
Quality, on autopilot

Put a swarm of test agents on your product today

Start free, connect your repo, and watch Testomat.ai plan, automate and explore your way to a calmer release.

Start free See all features