20-minute walkthrough with 2–3 personalized examples on your real pages.
Email, chat, or 24/7 phone support included on every paid plan.
Ask for more signups, a bigger basket, a page that speaks to enterprise buyers. Personyze AI works out who should see what, builds it in your own colours and fonts, and hands you a link to the finished campaign. You decide what goes live.
Works in the Personyze panel, inside WordPress, and from Claude or ChatGPT.
Join the list and take 10% off your first order.
Track uptime, yield and cost per unit across every line.
One account, one set of permissions. Ask in the panel, from your assistant, or inside the CMS you publish with — it is the same agent reading the same data and building the same campaigns.
The agent sits beside your campaigns. Describe a goal and it writes the targeting, picks a design from a gallery of 450+, places it and sets the timing — then hands you a link to the finished campaign.
What it builds →
Add Personyze as a custom connector and sign in with your own account. Ask how campaigns are performing, build one, pause an action — without leaving the conversation. Revoke access at any time.
How to connect →
MCP is the open standard assistants use to reach outside services. Personyze runs one, so there is nothing to install and no integration to build. You sign in as yourself, the assistant gets its own credential, and revoking it takes one click.
Read the docs →
Install the plugin and the agent appears in wp‑admin. No second tab and no separate login — you personalize the page from the same screen where you edit it.
WordPress personalization →
The same in‑CMS agent is rolling out to Shopify next, then across the other platforms Personyze integrates with. The storefront integration itself is already live and refreshed for the current API.
Shopify personalization →
For tools that cannot open a browser to sign in, use an API key instead. Same server, same permissions — and deleting a key disconnects anything using it.
About the MCP server →
The visual editor takes a single instruction aimed at the entire page. Every edit lands as a reviewable row you can undo one at a time.
“We rolled out across 40 properties without a single ticket to engineering.”
Two ways in: click any element and ask for a different look, or hand the whole page a goal. Either way it suggests first — you apply. Open the interactive editor demo.
Most campaigns are not built from nothing. They are last quarter’s campaign with a different audience, a different offer and a different page — mechanical work, and where the hours actually go.
You do not need the campaign’s name. Describe it the way you remember it and the agent finds it, then walks through what it targets and what it says, one item at a time, asking what should change.
/cruises
Ask what to improve this week and the agent looks across your pages, products and campaigns, then comes back with ranked, specific opportunities — each with the reason it is being suggested and a one-tap action to draft or fix it.
It reads the same numbers the panel reports: per-action results, site traffic by page, source, device and geography, and per-product stats.
Ask for a popup and the agent scans your live pages first — reading your colours, your heading font, your button style, even the tone of your copy — then builds the campaign to match. A visitor cannot tell it was generated.
Do not like a choice? Say “try a different colour” or “make it a bar instead” and it restyles on the spot. You are never editing CSS, and anything you set by hand survives a later rescan.
Say who should see it and the agent compiles that into actual targeting rules — then reads them back to you in plain language, because a rule that means something slightly different from what you asked looks identical from the outside.
You get the compiled rules back before anything runs, so a rule that means something slightly different from what you asked is caught while it is still a draft.
mobile
/pricing
Purchase
The wording is yours — these are examples of the kind of request, not commands with a fixed syntax. Pick the kind of site you run.
Build a bundle offer for visitors who viewed three or more products but never added to cart.
Which products get viewed a lot but rarely bought?
Free-shipping bar for returning mobile visitors who came from paid search.
More on e-commerce personalization and product recommendations.
Rewrite the pricing page for enterprise buyers in hospitality.
Show a demo-booking banner to visitors from companies in our CRM with more than 500 employees.
Which landing pages lose the most sessions from paid campaigns?
More on B2B personalization and personalization for SaaS.
Show a newsletter signup to readers on their third article this week.
Recommend related articles under each post for returning readers.
Which articles bring the most organic traffic that never subscribes?
More on personalization for publishers.
The reason to trust an agent with a live site is not that it never gets anything wrong. It is that everything it does is visible, reversible, and staged until you say otherwise.
Nothing changes on the strength of a prompt alone. The agent proposes, shows you what it would do in plain words, and waits.
New campaigns are shown only to visitors arriving from a staging IP. Real traffic keeps seeing what is live now, and you publish yourself.
You get the campaign with every setting in place — open it, look at it, decide. The build is the agent’s; the verdict is yours.
In the panel, in WordPress or through an assistant, the agent can only do what your own Personyze user is allowed to do.
Every package comes with a monthly allowance of AI actions, and the balance is shown before you run anything — under the prompt box, and live in the Visual Editor while a session is running. Nothing is spent without you seeing what is left first. Larger packages include more, and you can top up with AI credits if you run through it. See what each plan includes.
No. Everything it builds starts in staging, visible only to you, until you publish it. Changes that would affect real visitors — pausing an action, for instance — are confirmed in concrete terms first and are fully reversible.
It should not. The agent scans your live site before it builds, reading your colours, fonts, button style and the tone of your copy, then builds to match. Anything you set by hand survives a later rescan, and you restyle by asking rather than by editing CSS.
Build and restyle campaigns, compile targeting from plain words, pause and resume actions, create and populate audiences, look up visitor profiles, manage placeholders, read campaign and traffic performance, and answer product questions from the documentation. For anything the dedicated tools do not cover, it can call the Personyze REST API directly.
It reads your real account data and writes real configuration. Targeting becomes rules you can inspect in the panel; campaigns become actual campaigns. It also declines to quote a click-through rate on a sample too small to be meaningful rather than producing a confident number.
No. Add the Personyze MCP server URL as a custom connector and approve the connection on the Personyze screen that opens. The assistant receives its own credential, there is nothing to paste, and you can revoke access at any time.
WordPress today, through the Personyze plugin, which puts the agent directly in your WordPress admin. Shopify is next, with the remaining supported platforms following. See WordPress personalization and Shopify personalization.
There is no separate AI subscription. Each package includes a monthly allowance of AI actions, and the remaining balance is shown before you run anything. If the allowance runs out the AI stops and offers credits — it never runs up a bill you did not choose. See pricing.
Tell Personyze AI what you want to happen — a welcome offer, a recommendation row on the cart page, an A/B test on your pricing headline, a homepage rewritten for one audience, or just a read on what is worth fixing this week. It handles the targeting, the design and the staging.
More: all features · A/B testing · behavioral targeting · templates