An automated test follows instructions to check your website. When those instructions become outdated, 9l helps repair and check them. https://t.co/QHWXIIeLTo
When you’ve got 900 #Playwright tests and someone suggests another framework.
I just want my locators fixed 😭
That’s why we’re building #9lives: repair the locator, keep the assertions, re-run the spec.
What’s the smallest UI change that wrecked your suite?
A renamed button. A 20s comeback.
9lives repaired the test offline and re-ran the spec to verify it. AI steps & repair: Claude subscription. No rewrite. No API key.
Built without external funding. QualityMax aims to lead modern test automation.
https://t.co/DyBaOVuDMH
#testautomation #9lives #qualitymax
We pointed two AI users at a live booking site. Neither could complete a purchase.
They didn’t hit a database crash. They didn’t trigger a 500 error. They just got blocked, annoyed, and gave up.
This is the gap between a "green build" and a functioning product.
When you let AI coding tools write both your feature code and your test code, they don't build a safety net. They build a self-consistent hallucination. Your CI pipeline says `Clean` in three seconds, but your actual user flow is quietly bleeding cash.
To show what this looks like in the wild, we ran our Agentic Eyes personas - AI agents that walk a product like real, impatient users against a live checkout flow.
Here is what they reported:
1. "The coupon validation spinner never stops loading if the code is invalid. I can't tell if it's processing or broken."
2. "On mobile Safari, the 'Pay' button is pushed entirely off-screen by the cookie banner, with no way to scroll down."
Nobody argues with a bug in their own app.
If you are shipping AI-generated code without a deterministic, independent review layer, you are letting the generator grade its own homework.
Want to see what's actually blocking your users?
Drop your URL below, and we’ll run a bare, no-strings Agentic Eyes diagnostic on your public signup or booking flow. No credentials, no repo access, just raw evidence.
We’re delighted to announce that QualityMax is taking part in #WebSummit2026 this year and will be joining the startup programme. Can’t wait to meet you all there 🙌
We��re so excited to be joining the startup programme at #WebSummit2026 @WebSummit this November. We can’t wait to say hi to some new people! Meet you there 👋
#qualitymax #startup #buildinpublic https://t.co/kFulqZPmSr
We’re ending our partnership with Cursor following its acquisition by SpaceX. Under our proposal, Cursor’s direct access to our models would end on November 12.
We know that the people most affected by this decision are the developers who rely on OpenAI models in Cursor. We care about their experience in this transition and we’re ready to go above and beyond to support them.
https://t.co/OzuCTzUjfX