Early access. Every feature on this site carries its status. Where we are today

Product & engineering

Ship every week without breaking what makes money.

In the pilot, agents try your key journeys on each release, as a shopper on a phone, a keyboard and screen-reader user, and an AI shopping agent. We're building the hand-off that sends blockers to your coding agent and runs the check again.

The loop

Release, check, fix, re-check, confirm.

  1. 01

    You release

    A deploy, or a Shopify theme publish.

  2. 02

    Agents try key journeys

    Three kinds of customer, stopping before payment.

  3. 03

    Blockers found, or none found on this run

    With a screenshot and the change to make. Never “works”.

  4. 04

    Your agent fixes it

    Through MCP to Claude Code or your own agent.

  5. 05

    Re-check, then real visitors confirm

    The journey runs again; live traffic settles it.

  • Release check: key journeys tried on every release, stopping before payment Pilot
  • Your coding agent gets the fixes Building
  • Set it up from Claude Code Building
  • The check runs itself after a fix Building
  • Every change checked against your other pages: worked, didn't, or can't tell yet Building

What we promise, and what we don't

A blocker found is a fact. “None found on this run” is all we say otherwise.

A test run can show that something blocked a customer. It can't prove a site has no problems, so we never say a site or a checkout “works”, or that it's “accessible”.

Try your key journeys on the next release.