Edit posts and pages
Update copy, headlines, and sections, with the change shown as before-and-after before anything publishes. Drafts are drafts; publishing is a decision.
The website is where marketing's promises live, and updating it is where marketing's afternoons go. A price changes, a campaign launches, a landing page needs the new headline, and someone opens wp-admin, finds the page, edits, previews, publishes, and repeats it eleven more times.
The WordPress connector moves that work into the conversation. It links the AI you already use, like Claude, ChatGPT, or Copilot, to your WordPress sites through Mad Fish Elements, using the REST API your site already speaks. Your AI reads posts, pages, media, users, taxonomies, and comments, and ships the content changes you approve. The site the campaigns point at finally moves at campaign speed.
Connect your sites, and your AI reads them the way the REST API exposes them: every post and page with its full content and status, the media library, the categories and tags that organize things, the comments awaiting attention, and the users and settings that shape the site.
Reading at this level turns audits into questions. "Which pages still mention the old product name?" sweeps the site in a pass. "List posts that have not been updated in two years" builds the refresh backlog nobody had time to compile. "Which pages does the sale campaign land on, and what do they say right now?" checks the promise against the page. And because the same Gateway reads Google Ads and GA4, the campaign, the landing page, and the results appear in one conversation.
With Write access and your approval, your AI does the content work:
Update copy, headlines, and sections, with the change shown as before-and-after before anything publishes. Drafts are drafts; publishing is a decision.
New landing pages and posts drafted in your voice, saved as drafts for a human pass, structured like the pages that already work.
The old-tagline hunt, the broken-promise check, the price update across every page that carries it: one instruction, one change list, one approval.
Media, categories, tags, and comments handled in the same flow, and even plugin and settings reads for the site-health questions, with the riskier writes gated behind the permissions you set.
In practiceThe session marketers know too well: the campaign goes live at nine, and the site has to match. You ask, "Which pages mention the spring offer?" Six pages. You say, "Update all six to the summer offer copy I am pasting, as drafts." Six diffs appear, before and after. You approve five, edit one, approve it. "Publish all six." Done, and the audit trail shows what changed and who said so. Then the check that used to be hope: "Confirm every ad in the summer campaign points at pages that now say summer." The connector reads Google Ads on one side and the pages on the other. Match confirmed. Launch day took an hour fewer, and nothing shipped unread.
The site says what the ads promise, on the same morning, verified rather than assumed.
The find-and-fix chores that ate afternoons become an instruction and an approval.
Stale content surfaced on request, ranked by age and traffic when GA4 joins the question.
New content arrives as drafts in your voice; publishing stays a human decision with a paper trail.
"Which pages still mention the old pricing?"WordPress
The site-wide sweep as a checkable list.
"Update those pages to the new pricing copy, as drafts for my review."WordPress
Before-and-after diffs, published only on your approval.
"Draft a landing page for the fall campaign using the summer page as the pattern."WordPress
A structured draft in your voice, ready for the human pass.
"Do the ads in the fall campaign point at pages that exist and say the right thing?"WordPress · Google Ads
The promise-versus-page audit across both systems in one pass.
"List posts older than two years, with their traffic."WordPress · Google Analytics 4
The refresh backlog, prioritized by what people still read.
The queue between marketing and the website gets shorter: routine content changes happen in conversation with approvals, and the webmaster's time goes to the work that genuinely needs it.
For marketing teamsClient site updates are the definition of hands-on-keyboard work. Run content changes across client sites from one connection with per-client permission walls, keep every edit in the audit trail the client can see, and make launch-day parity a deliverable instead of a scramble.
For agenciesAsk in chat and share the dashboard without building exports or taking screenshots.
Pages and posts by last-updated, with traffic. Built for the refresh plan.
Ad destinations versus live page content. Built for launch mornings.
What changed, when, and who approved it. Built for the client and the compliance reviewer.
The charts stay simple here: table-first for audits, bar for freshness by section. And when your team wants these anytime, the Data Visualization add-on turns your reports into always-current dashboards they open from a link. Ask in chat; share the dashboard.
Site health reads in a few plain figures. Last-updated age by page: stale content is the quietest decay on any site. Pages by traffic, when GA4 joins the question, ranks what actually gets read. Campaign parity: how many live ads point at pages that say the right thing. This one should always be one hundred percent, and rarely is. Draft-to-publish flow: how much content sits waiting, and how long. And broken promises: old offers, dead prices, retired product names still live somewhere. Sweep monthly for freshness, check parity at every launch, and the site stays truthful. Each check is one question here. The afternoon they used to cost is the reason they never happened.
Day one: connect the site and take inventory. "List pages updated in the last 90 days, and the ten oldest." Day two: run a truth sweep. "Which pages still mention the old offer?" Read the list; fix nothing yet. Day three: make your first edit; pick one page; ask for the change as a draft. Read the before-and-after; publish on approval; day four: run the parity check. "Do the current campaign ads point at pages that say the right thing?" This is the check that saves launch days. Day five: schedule the habit. "Monthly, send the content freshness report." By Friday, the site has an operator rhythm: audits by question, edits by approval, launches verified instead of hoped. The webmaster queue gets shorter, and nothing shipped unread, because the diff came first every time.
Pair WordPress with Google Ads for the ad-to-page parity check every campaign deserves. Add GA4 to rank the refresh backlog by what people actually read, and Search Console to catch the pages Google is quietly demoting. Site, search, and spend, one conversation.
It will not redesign your site or touch your theme's code. It works through the REST API on content: posts, pages, media, taxonomies, comments. It will not publish without you; drafts and diffs come first, always. It will not bypass your site's own roles; it works with the credentials you connect, under Elements' per-person permissions on top. And it will not edit sites you did not connect.
Access is set per person, not per account, so Read seats see everything and change nothing while Write seats create and edit with your approval flow in front of every change. Delete access goes only to people you trust to clean up, and many teams start read-only, check answers against the platform, then widen access as the audit trail earns it.
You choose the level of human review and can change it at any time, while every action records what changed, when, and who approved it. Per-user access means Elements never stores your WordPress password, and your data is never harvested or resold.
Plans, account limits, and the multi-client Agency plan are on the pricing page .
It reads and writes what the REST API exposes. Standard posts and pages work cleanly; heavily builder-composed pages vary by how the builder stores content, and the before-and-after diff shows you exactly what an edit would touch before you approve it.
It can read them for site-health questions, and setting-level writes sit behind the strictest permissions. Content is the day-to-day surface; administration stays deliberate.
WordPress keeps revisions for posts and pages, and every connector change is in the audit trail. The safe path is built in anyway: drafts first, diffs shown, publish on approval.
No. Your AI acts only with the permissions you set, and changes follow the review level you choose. Read-only seats cannot change anything, because the approval flow is the product working as designed.
Your team can use Claude, ChatGPT, and Microsoft Copilot, while other AI tools can likely connect when they support MCP, the open standard for linking AI assistants to outside tools.
No. Your data stays yours, so nothing is harvested and nothing is resold.
The teams winning with AI are not handing their accounts to a black box; they keep the strategy and delegate the hands-on-keyboard work, while approvals and an audit trail make it safe to move fast. Connect the account you already have through the Gateway and ask the question you would normally build a report to answer.
Your first 14 days are free. Add your card to start, and cancel before the trial ends to pay nothing.