Ask in plain English. Claude authors real end-to-end tests from your live app; Assertify runs them on real browsers, on schedule, and keeps them green as your UI changes.
Start free · no credit card · connect Claude in ~30 seconds
Assertify runs on Claude over MCP — so the AI behind your whole QA comes from the flat plan you already pay for. No token bills, no per-seat markup. You only pay Assertify for run volume.
Pick Opus 4.8 for the hard flows or a faster, cheaper model per job — every account runs on Claude’s frontier models.
Competitors mark up every AI token and bill per seat. You bring the Claude plan you already have and pay only for run volume.
Drive QA from Claude, your IDE, or the terminal over open MCP — with the plan and tools you already use.
Watch each decision and tool call as it happens — what it tested, why, and what it found. Full visibility, and you steer it.
Used by engineers from teams that ship QA at scale
Set up once, then just describe what to test. Claude writes it, Assertify runs it.
Spin up a project in Assertify and copy its MCP key — everything you test lives here.
Paste the key into Claude once — from then on, Assertify is a tool Claude can drive on your behalf.
Ask in plain English — any language. Claude reads your live app and writes a real, runnable test.
Claude hands the finished test back to Assertify — review it, then run it on real cloud browsers.
Ask, record, or import → run on real cloud browsers → self-heal when the UI shifts. No frameworks, no selectors.
Tell Claude what to test and it writes it from the live page — or record a flow, or import your cases.
Runs on real Chromium, on demand or on a schedule.
Absorbs routine UI drift — repairs locators that break and keeps runs green.
One workspace for the whole team — not just engineers.
Describe a page and get real, runnable cases back. Review, keep, done — each case re-grounds on every run, so it doesn’t rot.
It covers
Open any test on a drag-and-drop canvas. Branch journeys, drop assertions, wire the steps. Anyone on the team can edit.
What you can do
Hit record and click through your app. Assertify captures the steps with real selectors and turns them into a clean, editable test on the canvas.
It captures
A locator breaks? Assertify diagnoses what moved, repairs the step, verifies the fix, and keeps the run green. Every fix is checked before it’s applied.
The repair loop
Assign it and walk away — the repro runs on a real cloud browser against your live app.
BUG-482To DoCheckout total doesn’t update after applying a promo code
Assignee · Assertify
Assertify· just now✓ Reproduced. Applied promo SAVE10 at /checkout — the order total stayed at $89.00 (expected $80.10). Failed on step 6 of 7.
Every feature on every plan. A run is one test executed once on a cloud browser — start with 25 free.
$19 /mo
For solo builders
$49 /mo
For teams & higher volume
Custom
For organizations
Just kicking the tires? Start free — 25 runs a month, no credit card.
Yes — it's live and self-serve. Sign up free (no credit card), connect Claude in about 30 seconds, and start running tests right away. 25 runs a month on the Free plan.
No. Describe what to test in plain English and shape it on a visual canvas — branch flows, add assertions, wire the steps. Anyone on the team can author and maintain tests.
It drives a real cloud browser to your URL and interacts with the live app the way a user would. For pages behind a login, add test credentials and it signs in for you.
Selectors are grounded in what the AI actually saw on your live app, not guessed. Re-running re-grounds against the current UI, and self-healing absorbs routine drift by repairing locators that break.
Assertify runs on Claude — the plan you already pay for — and you pick the model. AI authoring works on every plan; runs are the only thing you pay for, with no API keys and no token bills.
Yes. Run on demand, schedule recurring daily or weekly runs, or trigger them by webhook from your pipeline — with Slack, Discord, or email alerts and screenshots and video of every step.
Assign a bug to Assertify (or move it into a QA status) and it reproduces the issue against your live app, posts back a verdict with steps and a screenshot, and transitions the ticket on its own when you enable it.
No — we never use your tests, screenshots, or recordings to train models. Prompts only go to the AI model that runs the agent, and runs execute in isolated browsers. See our Privacy Policy.
“I spent 7+ years building test automation for products with multi-million-user customer bases at Ubisoft, Playrix, and beyond. Assertify is that exact playbook — automated.”
Your first AI-built test suite in a couple of minutes. Free to start, no credit card.