Explores with intent
Give it a goal — “find checkout defects” — and it navigates your app pursuing that mission, not a fixed script.
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…
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.
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.
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.
At scale
One command, a whole swarm
A single orchestrator fans work out to dozens of agents, each exploring a different route in its own browser — in parallel, for hours.
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.
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.