Home now shows your automation level and a live "Happening now" box, so you can see Phyllix working. The plan card moved out of the way, and the automation buttons line up.<\/p>","2.3.3":"
One-button setup: press Start and Phyllix sets itself up, then asks you to check your profile. Articles now vary in shape. Fixes Home buttons that needed a second click, and links that said "not allowed".<\/p>","2.3.1":"
Important: fixes 2.3.0 from WordPress.org, which was missing two files and could stop with an error. Also adds optional automatic updates, and the home screen no longer shows twice.<\/p>","2.3.0":"
Local content now covers every area in your Business Profile; new plans for agencies; and your site can be reminded to run its queue on time even when nobody visits (switch off in Settings \u2192 Automation \u2192 Advanced).<\/p>","2.2.1":"
Important fix: internal links could be written inside a page's schema, breaking it or leaving it showing as code. Stops that, and repairs affected pages (Quick fixes \u2192 Repair all).<\/p>","2.2.0":"
Automation now works every day, spread across the week, instead of all at once: set articles per week and per day in Settings. The split between new articles and page improvements now protects both sides. Includes all of 2.1.x.<\/p>","2.1.2":"
Broken live pages are now listed where they get fixed \u2014 schema repairs in Quick fixes, leftover AI text in Improve pages \u2014 with a count on each tab. Includes all of 2.1.1 and 2.1.0.<\/p>","2.1.1":"
Free one-click repair for pages whose schema shows as code (Site health), and Improve no longer refuses those pages. Plus 2.1.0: Improve on Elementor, Divi, WPBakery, Avada, Beaver Builder and Bricks, save fixes, a clearer Automation section, a new look.<\/p>","2.1.0":"
Improve pages now works on Elementor, Divi, WPBakery, Avada, Beaver Builder and Bricks pages without touching the layout; several fixes that stop saves from damaging pages; a clearer Automation section in Settings; and a new look.<\/p>","2.0.10":"
Major release: adds fully optional, off-by-default automation (auto-approve, auto-write, auto-publish, and automated page\/CTA improvements), each its own toggle in Settings \u2192 Automation. If you do nothing, nothing changes \u2014 Phyllix keeps drafting and proposing exactly as before.<\/p>"},"ratings":[],"assets_icons":{"icon-128x128.png":{"filename":"icon-128x128.png","revision":3723449,"resolution":"128x128","location":"assets","locale":"","width":128,"height":128},"icon-256x256.png":{"filename":"icon-256x256.png","revision":3723449,"resolution":"256x256","location":"assets","locale":"","width":256,"height":256}},"assets_banners":{"banner-1544x500.png":{"filename":"banner-1544x500.png","revision":3723449,"resolution":"1544x500","location":"assets","locale":"","width":1544,"height":500},"banner-772x250.png":{"filename":"banner-772x250.png","revision":3723449,"resolution":"772x250","location":"assets","locale":"","width":772,"height":250}},"assets_blueprints":{},"all_blocks":[],"tagged_versions":["1.3.0","1.4.0","2.2.1","2.3.0","2.3.1","2.3.3","2.3.4"],"block_files":[],"assets_screenshots":{"screenshot-1.png":{"filename":"screenshot-1.png","revision":3723449,"resolution":"1","location":"assets","locale":"","width":1354,"height":902},"screenshot-2.png":{"filename":"screenshot-2.png","revision":3723449,"resolution":"2","location":"assets","locale":"","width":1346,"height":898},"screenshot-3.png":{"filename":"screenshot-3.png","revision":3723449,"resolution":"3","location":"assets","locale":"","width":981,"height":912},"screenshot-4.png":{"filename":"screenshot-4.png","revision":3723449,"resolution":"4","location":"assets","locale":"","width":1013,"height":920},"screenshot-5.png":{"filename":"screenshot-5.png","revision":3723449,"resolution":"5","location":"assets","locale":"","width":1013,"height":854},"screenshot-6.png":{"filename":"screenshot-6.png","revision":3723449,"resolution":"6","location":"assets","locale":"","width":1016,"height":922}},"screenshots":{"1":"The cockpit - what Phyllix is working on and what needs your decision","2":"Ideas, scored and waiting for your approval","3":"A draft article with its SEO and readability review","4":"Improve pages - the plan for a page, shown before anything is written","5":"Results - how your published articles are actually doing in Google","6":"Site health - technical problems found on your pages, with fixes"}},"plugin_section":[],"plugin_tags":[2353,5882,468,127115,186],"plugin_category":[55],"plugin_contributors":[280606],"plugin_business_model":[],"class_list":["post-363163","plugin","type-plugin","status-publish","hentry","plugin_tags-ai","plugin_tags-content-marketing","plugin_tags-keyword-research","plugin_tags-search-console","plugin_tags-seo","plugin_category-seo-and-marketing","plugin_contributors-mtairowodza","plugin_committers-mtairowodza"],"banners":{"banner":"https:\/\/ps.w.org\/visualithic-phyllix\/assets\/banner-772x250.png?rev=3723449","banner_2x":"https:\/\/ps.w.org\/visualithic-phyllix\/assets\/banner-1544x500.png?rev=3723449","banner_rtl":false,"banner_2x_rtl":false},"icons":{"svg":false,"icon":"https:\/\/ps.w.org\/visualithic-phyllix\/assets\/icon-128x128.png?rev=3723449","icon_2x":"https:\/\/ps.w.org\/visualithic-phyllix\/assets\/icon-256x256.png?rev=3723449","generated":false},"screenshots":[{"src":"https:\/\/ps.w.org\/visualithic-phyllix\/assets\/screenshot-1.png?rev=3723449","caption":"The cockpit - what Phyllix is working on and what needs your decision"},{"src":"https:\/\/ps.w.org\/visualithic-phyllix\/assets\/screenshot-2.png?rev=3723449","caption":"Ideas, scored and waiting for your approval"},{"src":"https:\/\/ps.w.org\/visualithic-phyllix\/assets\/screenshot-3.png?rev=3723449","caption":"A draft article with its SEO and readability review"},{"src":"https:\/\/ps.w.org\/visualithic-phyllix\/assets\/screenshot-4.png?rev=3723449","caption":"Improve pages - the plan for a page, shown before anything is written"},{"src":"https:\/\/ps.w.org\/visualithic-phyllix\/assets\/screenshot-5.png?rev=3723449","caption":"Results - how your published articles are actually doing in Google"},{"src":"https:\/\/ps.w.org\/visualithic-phyllix\/assets\/screenshot-6.png?rev=3723449","caption":"Site health - technical problems found on your pages, with fixes"}],"raw_content":"\n
Phyllix reads your website, works out what your business actually does, and then works on your search visibility the way a marketing manager would - by finding what you could realistically rank for, what your existing pages half-cover, and what is missing entirely.<\/p>\n\n
By default, it never publishes anything. Every article it writes is filed as a draft<\/strong> for you to read, edit and approve, and if you want that to stay true forever, it will. Every change it proposes to a page you already have is shown to you in full first, and the original is kept so it can be undone. An explicit Automation section in Settings lets an owner who wants more turn on exactly as much as they choose \u2014 anywhere from just sending findings to your Ideas queue automatically, up to approving, writing and publishing articles with no click at all. Every level is off by default, and turning any of it on is a deliberate choice you make.<\/p>\n\n What it does<\/strong><\/p>\n\n How it treats your content<\/strong><\/p>\n\n This is the part we care most about. A page you already have is a page that already works for someone, so:<\/p>\n\n Free plan<\/strong><\/p>\n\n The free plan includes 3 AI-written articles, once \u2014 a one-time allowance, not a monthly one. Reading your site, the business profile, the content map, the keyword map, the gap analysis, manually-tracked competitors, Google Search Console tracking, and fixing technical SEO problems are always included, for free, forever, with no limit. Once the 3 free articles are used, buy AI credits ($1.25 each, pay only for what you use, no subscription) or move up to a paid plan for an ongoing monthly allowance. Free also reads up to 25 pages of your own site, once, ever.<\/p>\n\n Phyllix cannot work without connecting to an external service.<\/strong> It does not run AI models on your server, and it does not ask you for API keys. Instead it sends work to the Phyllix service, which runs the AI on your behalf. You should understand exactly what that means before you use it.<\/p>\n\n Phyllix connects to When it connects:<\/strong><\/p>\n\n When the service calls your site:<\/strong> with a licence connected, the service calls your site every few minutes at What is sent:<\/strong><\/p>\n\n What is not sent:<\/strong> your database, your users, your customers' data, your orders, or the content of any page Phyllix has not been asked to work on. Pages you have marked Private or password-protected are skipped outright, whatever content type they are, and any email address found in a page's text is stripped before that text reaches an AI request.<\/p>\n\n Terms: https:\/\/visualithicsolutions.com\/terms\nPrivacy: https:\/\/visualithicsolutions.com\/privacy<\/p>\n\n The Phyllix service passes your request to one of two AI providers, depending on the task. Your content is sent to them by the Phyllix service, not directly by this plugin.<\/p>\n\n If you choose to connect Google Search Console, Phyllix calls\n https:\/\/oauth2.googleapis.com to exchange the credentials you supply for an\naccess token, and Terms: https:\/\/policies.google.com\/terms\nPrivacy: https:\/\/policies.google.com\/privacy<\/p>\n\n If you run a site health check, Phyllix calls Terms: https:\/\/policies.google.com\/terms\nPrivacy: https:\/\/policies.google.com\/privacy<\/p>\n\n When checking AI Visibility questions or discovering competitors, Phyllix's\nresearch sometimes comes back with a citation on Google privacy: https:\/\/policies.google.com\/privacy<\/p>\n\n When you run a site health check, Phyllix makes a HEAD request to the addresses\nyour pages link to, in order to find broken links and redirect chains. These are\nthe sites you have already linked to. No data about you or your site is sent -\nthe request only asks whether the address still responds.<\/p>\n\n The Diagnostics page in Settings makes one request to If your server's normal DNS lookup for the Phyllix service ever fails, Phyllix\nasks Cloudflare ( Cloudflare privacy: https:\/\/www.cloudflare.com\/application-privacy-policy\/\nGoogle privacy: https:\/\/policies.google.com\/privacy<\/p>\n\n\n By default, no \u2014 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 \u2014 anywhere from just sending findings to your Ideas queue automatically, up to approving, writing and publishing articles with no click at all \u2014 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.<\/p>\n\n 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 \u2014 visible on every relevant screen, so you can always see what automation did versus what you did yourself.<\/p>\n\n Nothing automation publishes is permanent. A published article is an ordinary WordPress post \u2014 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.<\/p>\n\n Pages linked in your site's navigation menu are never touched by any automated action, at any setting \u2014 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.<\/p><\/dd>\n 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.<\/p><\/dd>\n It is built specifically not to. Only the text inside your existing layout is edited \u2014 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.<\/p><\/dd>\n Yes. The original content is stored before any edit, and every applied change can be reverted from within Phyllix.<\/p><\/dd>\n 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.<\/p><\/dd>\n 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.<\/p>\n\n You never need to open the JSON file. Upload it and Phyllix reads the email address out of it for you.<\/p><\/dd>\n 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.<\/p><\/dd>\n See the \"External services\" section above, which lists this in full.<\/p><\/dd>\n 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.<\/p><\/dd>\n 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.<\/p><\/dd>\n That message is the stored result of the last time this step actually ran \u2014 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 \u2014 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.<\/p><\/dd>\n 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.<\/p><\/dd>\n\n<\/dl>\n\n\n Earlier versions, and the full detail of every release, are in changelog.txt in the plugin folder.<\/p>","raw_excerpt":"An AI marketing director for your site: finds ranking gaps, drafts articles for your approval, with optional full automation.","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/da.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin\/363163","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/da.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin"}],"about":[{"href":"https:\/\/da.wordpress.org\/plugins\/wp-json\/wp\/v2\/types\/plugin"}],"replies":[{"embeddable":true,"href":"https:\/\/da.wordpress.org\/plugins\/wp-json\/wp\/v2\/comments?post=363163"}],"author":[{"embeddable":true,"href":"https:\/\/da.wordpress.org\/plugins\/wp-json\/wporg\/v1\/users\/mtairowodza"}],"wp:attachment":[{"href":"https:\/\/da.wordpress.org\/plugins\/wp-json\/wp\/v2\/media?parent=363163"}],"wp:term":[{"taxonomy":"plugin_section","embeddable":true,"href":"https:\/\/da.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin_section?post=363163"},{"taxonomy":"plugin_tags","embeddable":true,"href":"https:\/\/da.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin_tags?post=363163"},{"taxonomy":"plugin_category","embeddable":true,"href":"https:\/\/da.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin_category?post=363163"},{"taxonomy":"plugin_contributors","embeddable":true,"href":"https:\/\/da.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin_contributors?post=363163"},{"taxonomy":"plugin_business_model","embeddable":true,"href":"https:\/\/da.wordpress.org\/plugins\/wp-json\/wp\/v2\/plugin_business_model?post=363163"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}\n
\n
External services<\/h3>\n\n
The Phyllix service (Visualithic Solutions)<\/h4>\n\n
https:\/\/visualithicsolutions.com<\/code>, operated by Visualithic Solutions, to license the plugin and to run every AI request.<\/p>\n\n\n
\/wp-json\/phyllix\/v1\/wake<\/code> to remind it to run Phyllix's queue, so work starts on time even when nobody visits (WP-Cron only runs on visits). Only a call signed with your own licence key is accepted; it runs the work Phyllix would run on its own 5-minute schedule, and no content is sent in either direction. Switch it off in Settings \u2192 Automation \u2192 Advanced (\"Keep my schedule on time\").<\/p>\n\n\n
home_url()<\/code>)<\/li>\nAI providers used by that service<\/h4>\n\n
\n
Google Search Console (optional)<\/h4>\n\n
https:\/\/searchconsole.googleapis.com<\/code> to read which searches\nyour site appears for. This is entirely optional and nothing is sent to Google\nbeyond the API request itself.<\/p>\n\nGoogle PageSpeed Insights (optional)<\/h4>\n\n
https:\/\/www.googleapis.com\/pagespeedonline<\/code> with the public address of the page being checked, to retrieve its performance scores.<\/p>\n\nGoogle grounding redirect (AI Visibility and competitor discovery only)<\/h4>\n\n
vertexaisearch.cloud.google.com<\/code>\n\u2014 a Google redirect link, not a real page. For those two features only, Phyllix\nmakes a HEAD request directly to that link to follow the redirect to the real\naddress, so it can show or record the actual source rather than a redirect\nlink. No data about you or your site is sent - the request only asks where\nthe link redirects to.<\/p>\n\nLinks on your own pages<\/h4>\n\n
Connectivity diagnostics<\/h4>\n\n
https:\/\/api.wordpress.org\/<\/code>\nas a control check - a destination every WordPress site already trusts. This\nconfirms your server can reach the internet at all, so a failure to reach the\nPhyllix service reads correctly as a problem with that one destination, not\nyour server's outbound access in general. No data about you or your site is\nsent - the request carries nothing beyond the request itself.<\/p>\n\nPublic DNS resolvers (fallback only)<\/h4>\n\n
1.1.1.1<\/code>) and, if that also fails, Google (8.8.8.8<\/code>) - both\npublic DNS-over-HTTPS resolvers - to look up the address instead, the same way\na browser's own DNS-over-HTTPS setting would. This only happens after your\nsite's normal outbound connection has already been proven to work. Only the\nhostname being looked up is sent, and nothing about your site or its content\nis included.<\/p>\n\n\n
\n
Does it publish anything by itself?<\/h3><\/dt>\n
Can I use my own OpenAI or Anthropic API key?<\/h3><\/dt>\n
Will it break the layout of my pages?<\/h3><\/dt>\n
Can I undo a change to a live page?<\/h3><\/dt>\n
What happens when I use up my article allowance?<\/h3><\/dt>\n
How do I get the Google file for Search Console?<\/h3><\/dt>\n
Does it work without Google Search Console?<\/h3><\/dt>\n
What data does it send?<\/h3><\/dt>\n
Could it read something it shouldn't - an invoice, a quote, a private page?<\/h3><\/dt>\n
What stops it putting something odd on my page?<\/h3><\/dt>\n
A step says \"This failed\" with an old-looking error \u2014 I fixed that already, why is it still there?<\/h3><\/dt>\n
Do I need Yoast or Rank Math?<\/h3><\/dt>\n
2.3.4<\/h4>\n\n
\n
2.3.3<\/h4>\n\n
\n
2.3.1<\/h4>\n\n
\n