Visualithic Phyllix

By default, no — articles are filed as drafts, and changes to existing pages are shown to you as a proposal and only applied when you click to apply them. An explicit Automation section in Settings lets you turn on more — anywhere from just sending findings to your Ideas queue automatically, up to approving, writing and publishing articles with no click at all — but every level is off by default, and turning it on is a deliberate choice you make, not something the plugin does on its own out of the box. A draft still passes the exact same content checks every draft passes before it can be filed at all, whether a human or automation triggered it. Every idea, draft and published article keeps a full record of when it was proposed, when and by whom it was approved, when and by whom it was written, and when and by whom it was published — visible on every relevant screen, so you can always see what automation did versus what you did yourself. Nothing automation publishes is permanent. A published article is an ordinary WordPress post — you can edit it, unpublish it, or delete it at any time through Phyllix's own editor or WordPress's own post editor, exactly as you would with anything you wrote yourself. Any edit Phyllix makes to a page you already had keeps the original content, so it can be reverted with one click. Pages linked in your site's navigation menu are never touched by any automated action, at any setting — quick fixes, calls to action, page rewrites, none of it. Those always wait for your own explicit review, with nothing in Settings that overrides it.

No. Phyllix provides the AI as part of the plan, which is why there are no keys to manage and no separate AI bill to reconcile.

It is built specifically not to. Only the text inside your existing layout is edited — blocks, builder sections, columns and widgets are put back exactly as they were, so full-width sections and layout settings survive. This works the same on the block editor, the classic editor, Elementor, Divi, WPBakery, Avada, Beaver Builder and Bricks. If a rewrite would lose a block, a shortcode, an image, a form or an embed, it is refused rather than applied. Pages built with Oxygen, Breakdance, Brizy, Thrive or SiteOrigin are not rewritten at all.

Yes. The original content is stored before any edit, and every applied change can be reverted from within Phyllix.

It pauses and tells you, right where you clicked. Nothing is charged automatically and nothing is written that you have not asked for. On a paid plan the allowance resets on the 1st of each month; on the Free plan the 3 articles are a one-time allowance that never resets. Either way, you can buy AI credits ($1.25 each, no subscription, pay only for what you use) to keep going immediately, or move up a plan for ongoing headroom.

Step-by-step instructions in plain English are shown inside the plugin, right above the upload box in Settings. It takes about five minutes, it is free, and you only do it once. In short: create a free Google Cloud project, enable the Search Console API, create a service account and download its JSON key, upload that file here, then add the email address Phyllix shows you as a user on your site in Search Console. You never need to open the JSON file. Upload it and Phyllix reads the email address out of it for you.

Yes. Search Console makes the keyword and results work far more accurate, because it replaces guesswork with what Google actually shows for your site, but Phyllix works without it.

See the "External services" section above, which lists this in full.

No. What Phyllix reads is an allow-list you control in Settings -> Content to read - it starts with just your ordinary Pages and Posts, and nothing else is added unless you tick it, so a separate "Invoices" or "Quotes" post type stays out by default. On top of that, anything you have marked Private or password-protected is skipped outright, whatever its type - and any email address inside a page's text is stripped in code before that text ever reaches an AI request, everywhere in the plugin, not only on the first read.

Every change Phyllix makes to a page is checked before it is saved. If the result contains anything that should not be visible to a visitor - structured data showing as words, HTML tags reading as text, markdown symbols, an unfilled placeholder, mangled characters, or the assistant talking to you - the change is refused and you are told exactly what was found. Nothing Phyllix introduces of that kind can reach a published page.

That message is the stored result of the last time this step actually ran — not a live check. It stays on screen exactly as written, however old, until this specific step runs again. If whatever caused it has since been fixed (a setting corrected, a connection restored, a plugin updated), the message will not know that on its own. Click "Clear error & try again" right there on the step — this clears the stored error and gives it a genuine fresh attempt, which either succeeds (the message disappears) or fails again with an up-to-date reason.

No, but Phyllix works with both. Where one is installed, the search settings it writes - focus keyphrase, synonyms, SEO title and meta description - go straight into that plugin's own fields. With neither installed, Phyllix keeps its own copy so the work is not lost if you add one later.