Pre-launch checkBefore your customers

Every checkout
meets its users.Meet them first.

Paste a link. AI testers, each with their own habits, device and inbox, use your product the way your customers will. You get back what broke, how to fix it, and a second test once you've fixed it. Websites and web apps today. iPhone, Android and Windows apps next.

What you can test

Anything a customer can use.Send them in first.

Checkouts, sign-ups, onboarding, dashboards, team pages. Testers use the real thing on the screen your customers hold, and circle the exact spot where it let them down, in their own words. Every card below is a real test on one of three practice apps we built with known problems, so we can measure what they catch.

Where testers go · today and next

TODAYWebsitesShops, landing pages, sign-ups. Anything with a link.
TODAYPhone browsersSmall screens, thumbs and taps, not a mouse.
TODAYWeb appsDashboards, settings, team pages, exports.
NEXTNew featuresEvery pull request, before it merges.
NEXTPhone appsiPhone and Android apps from the store.
NEXTDesktop appsMac and Windows apps your customers install.

Your customers

Your customers live everywhere.So do your testers.

Paste your site. Kranth reads it, works out who would use it, and casts testers to match: where they live, what they use, how much patience they have, and why they came. Below is the cast for Kettle, a practice tea shop, and what happened when they tried to buy something.

The errand they were given“Buy any tea as a guest and pay with the test card.”

When it breaks

It broke in production.Everyone found out at once.

Five ways a broken product comes back to bite you. The stories are made up. The bugs in them are real: our testers found every one in our practice apps before any customer did.

A story

Talk to a tester · soon

Ask them why they left.They remember every step.

When a tester gives up, you can ask them why. They answer from what they did and saw in the session. Below, our team questions Marcus, who left the checkout of our practice shop. Every answer is his own words from the recording.

Marcus · tester

Case file · Tester

Watch them work

Watch them work.Every cursor has a name.

Ten testers, one shop, played back. Each coloured cursor follows the path its tester really took through Kettle. The log on the right shows every click and every thought. Each tester's box below shows where they are and how much patience they have left. Pages turn red where people got stuck.

Replay · Kettle · 10 testers

How we test the testers

We broke three apps on purpose.Then we sent them in.

A shop, a habit app and a dashboard, each with 20 problems we planted and wrote down first. Five testers used each app six times. A separate AI judge checked every report against that list. Here is what they caught, and what they missed.

0of 60 planted problems found
8/15of the subtle ones
~1¢per tester, per session
~14%of reports were false alarms

They missed 22. Each miss is on the board above, and each one is something we are working on. For scale: one careful person on our team, testing by hand, found 10 of the same 60.

How it works

Testers, not test scripts.Here's how one is built.

Nobody writes steps for them. Each tester has a background, a device and habits of their own. They use your product alone and decide what to do next, the way a person would. These are the ten from the map above, at Kettle's checkout.

  1. 01You paste a link

    Add a test login or a test card if they need one, and an errand if you have one in mind. Or let them wander.

  2. 02The testers are built

    Each one gets a background drawn from 101 personality types, a phone or a laptop, an email inbox, and habits: how patient they are and what they press first.

  3. 03Each one uses it alone

    Each tester gets their own browser and their own session, with no script. They report what stops them, slows them or just looks wrong, with the step and the screenshot.

  4. 04You get one fix list

    We merge the reports and rank them by how many testers hit each one. Every item has the steps, the fix and a way to check it. Fix it, then send the testers back in.

The link · kettle.teaBuy any tea as a guest and pay with the test card.
Not your customers.

These are AI testers. They find what breaks and what confuses. Then go talk to the real people.

Not a test script.

Nobody tells them where to click. That is how they find the paths your tests never walk.

They don't just say yes.

In our practice shop, all ten hit the card bug and said so in their own words.

For your agent · soon

Call them from your agent.Every pull request meets them first.

Add Kranth to Claude Code, Cursor or any MCP client, or call the REST API. Your agent sends testers to the preview link, they use it, and the fix list comes back as a comment on the pull request. Push the fix and they check again. This part comes after the web app. Below is how it will look, using problems our testers really found on Kettle.


        

Live event stream

Pull request #212checkout: new payment form
you
commented/kranth test "buy any tea as a guest"
K
kranth-reviewer bot commented
10 testers · 9 finished · 3 to fix
  • Preview: pr-212.kettle.dev, 6 phones and 4 laptops
  • Watch the sessions
Fix first
    In their words

    Kranth checks again on your next push. Comment /kranth retest to run it now.

    claude mcp add kranth.cursor/mcp.json/kranth test on a pull requestPOST /v1/tests

    Where this goes

    Software that meets its usersbefore it ships.

    Today, ten testers go into one website and come back with a fix list. Next, they test every pull request, and phone and desktop apps too. The end game is a standing crowd shaped like your real customers, in every language and on every device, using your product every day. Your AI agent fixes what they hit before a real customer ever does.

    1. Fix first · /checkoutAccept the test card with spaces in it10 of 10 hit it
    2. Fix next · /checkoutPut each error next to its fieldfound why: 1 of 10
    3. Then · phonesStop the security code running off the card2 of 10 on phones

    For the one-person company

    Ship on Friday. Your testers used it on Thursday, and you already fixed what stopped them.

    For your AI agent

    It writes the change, reads the fix list on the pull request, fixes it and asks the testers again. You review a green pull request.

    For the team with customers everywhere

    Every market, language, device and kind of patience your customers have, without booking a lab or paying a panel.

    For your customers

    They never meet the bug. That is the whole point.

    Pricing

    Pay per tester, not per seat.Cheaper than a one-star review.

    One credit sends one tester through one task, on a phone or a laptop, and pays for their part of the fix list. Every plan gets the same testers and the same checks. Plans start at $39 a month, or top up from $10. Plan credits you don't use roll over to the next month.

    StarterTwo products, tested before every release.
    $39/ month

    250 tester credits a month

    • 2 products
    • Testers built for your customers
    • Phones and laptops
    • Fix list with steps to repeat
    • Retest after you fix
    • Email support
    Join the waitlistExtra credits $0.163 each
    Where most teams land
    ProTeams that ship every week.
    $99/ month

    800 tester credits a month

    • 3 products
    • Everything in Starter
    • Pull request comments and agent access (soon)
    • Talk to a tester after the run (soon)
    • Priority support, replies within 24 hours
    Join the waitlistExtra credits $0.124 each
    ScaleMany products, testers on every deploy.
    $399/ month

    4,000 tester credits a month

    • 5 products
    • Everything in Pro
    • 10 seats included
    • Shared Slack channel, replies within 4 hours
    Join the waitlistExtra credits $0.0998 each
    No plan? Top up from $10 for 50 tester credits. $0.20 each, never expire.
    Join the waitlist
    Enterprise

    Testers that work behind your login, on your own devices and in your own regions. We never train on your data, and the contract says so. Talk to us to set it up.

    [email protected]

    Meet your testers.

    Paste a link and tell them what to do. They use it on their phones and laptops, and you get back what broke, how to fix it, and a retest.