> For the complete documentation index, see [llms.txt](https://docs.intelligems.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.intelligems.io/general-features/atlas-ai/atlas-qa/faqs.md). # FAQs ## Atlas QA FAQs ### General
What does Atlas QA do? Atlas QA is Intelligems' quality assurance (QA) agent. It reviews your test's configuration and your live storefront before launch, catches misconfigurations and best-practice gaps, and returns a report with the problem, the impact, and the fix — backed by screenshots.
What accounts and plans is it available on? All Intelligems accounts, on every Shopify plan, for both tests and personalizations.
What test types does it support? Price, content, offer, shipping, checkout, theme, template, and split URL. Atlas QA is test-type aware — it runs only the checks that apply to your test type and skips the rest. For the full list of what runs, see [What Atlas QA Checks](/general-features/atlas-ai/atlas-qa/what-atlas-qa-checks.md).
### Running a check
When does it run? On demand, any time, from the **QA & Preview** tab of a test or personalization. It doesn't run automatically, and it won't start your test for you. You don't have to wait until you're ready to launch — running a check partway through setup is a good way to catch a broken selector or a targeting mistake early.
Does it stop me from launching? No. If you launch with unresolved errors, you'll be asked to confirm that you've QA'd the test yourself and accept the risk of launching with those errors open. The decision is always yours. We'd recommend fixing errors first — those are the ones that reach shoppers — but you know your store better than the agent does.
Do I still need the manual QA checklists? Yes. Atlas QA takes the first pass at quality assurance — it doesn't replace your own review. Use Atlas QA first, then work through the checklist for your test type.
### Reading your report
What's the difference between an error and a recommendation? An **error** means the test can't produce valid results as configured — fix it before you launch. A **recommendation** is a non-blocking issue or a best-practice gap. Atlas QA surfaces the risk and tells you where to look, but you decide whether it applies to your store. Recommendations don't block a launch.
What does "needs manual review" mean? It doesn't mean a check failed. It means Atlas QA couldn't confirm the check on its own and is handing it to you. Three different things land findings here: * **Atlas QA couldn't reach your storefront.** Browsing can fail when a preview URL didn't load. Click **Re-run** — this often clears on a second attempt. * **The check was skipped because something it depends on was flagged.** Fix the issue it points to, then re-run. * **The check genuinely needs a person.** Some things can't be confirmed without a real order or a manual look. Do the check yourself, then click **Mark as reviewed**. Click **How to review** on any finding to see which of these applies.
Why was one of my checks skipped? When one root issue would cause several checks to fail, Atlas QA skips the checks downstream of it rather than reporting one problem as five. A skipped check carries a **Skipped** badge and a note naming the issue to fix first — for example, *"Skipped — fix Content modifications issue first, then re-run to verify this check."* Fix the issue it points to and re-run. The skipped check will verify itself.
What does "Mark as reviewed" do? It clears a finding from your report once you've handled it or decided it doesn't apply. Use it after you've manually confirmed something Atlas QA couldn't verify on its own. Marking a finding as reviewed doesn't change your test — it only updates the report.
Does it catch everything? No. It's a pre-launch first pass, not a guarantee. Some setups still warrant a manual check or a real test order — post-purchase upsells and websites with bot protections. Every report carries a reminder that AI-assisted QA may not catch every issue.
What if it flags something that isn't actually a problem? Go ahead and launch. Then [let us know](https://portal.usepylon.com/intelligems/forms/intelligems-support-request) — false positives are the findings we most want to hear about, and every report helps us tighten Atlas QA.
### Sharing and notifications
Can I share the report with my developer? Yes. Click **Share link** on any report to generate a link straight to the findings, fix steps, and screenshots. {% hint style="info" %} **Viewer needs an Intelligems login.** The link opens the report for anyone who can already sign in to this Intelligems account. To share with an outside developer or agency, add them as a user first. {% endhint %}
Will I get notified when the report is ready? Yes. You'll get an email when the check finishes, so you don't have to sit and watch. There are two versions depending on the outcome: no issues found, or issues found with a link straight to the report. Only the user who pressed **Start QA check** gets the email.
### Limits
Does it watch my test after it launches? Not today. Atlas QA guards the launch. Continue doing periodic sweeps of your site while a test is running — see Best Practices During a Test.
Can it fix issues for me? No. Atlas QA tells you what's wrong and how to fix it, but the change is yours to make. Some fix steps include a **Go** button that jumps you straight to the right screen in the app.
--- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.intelligems.io/general-features/atlas-ai/atlas-qa/faqs.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.