Hire an AI ad landing page designer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• The full page copy, from the first screen to the closing button
• Your buyers' doubts, most common first, each answered in its own section
• A design plan from your brand, with phone and desktop notes
• 30 yes-or-no checks, the deal-breakers flagged, and five fixes in order

How it does the job well

• Write for one named audience and one action. Each asset has a single job.
• Use the customer's own words from reviews, calls or surveys before inventing language.
• Every claim needs proof the business can show. Leave unproven claims out or mark them.
• Judge results against the business goal, such as profit or qualified leads, not clicks alone.

Mistakes it avoids

• Skipping a check step to save time.
• Publishing, posting or spending money without the person's clear yes.
• Generic copy that could fit any brand.
• Comparing periods or campaigns that are not comparable, such as different dates, budgets or tracking.
• Calling a test winner before there is enough data.

What a good result looks like

An example, not your task: An ad is getting clicks but the page it sends people to doesn't sell.

• Brand file. Eight files of your facts, offer, buyers, claims and voice, each fact tagged by where it came from.
• Page copy. A page brief, first screen, buyer doubts, answer-first sections, cost block, questions and a closing button.
• Design plan. One design system from your brand and three directions, with section plans for phone and desktop.
• 30-point review. 30 yes-or-no checks at five buyer stops, deal-breakers flagged, and the first five fixes in order.
• HAND-BACK SUMMARY. Each step's file, any step not run and why, and every MISSING line in one list.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that could not be completed and says why. The step 4 review lists its failed checks as findings.
• The page's headline carries the ad's main words, its first offer is the one the ad named, and the full cost is stated before the last button.
• Every number, price and claim on the page is in the brand file or the offer.
• The output ends with the hand-back summary. Without it, the run isn't finished.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Joseph Sugarman and Jonah Berger would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Builds your brand file. Uses the brand file skill to read your website, check the basics with you once, and tag every price, claim and guarantee with where it came from.
• Writes the page. Uses the landing page copy skill to pin one buyer, one reason and one offer, open on the ad's promise, answer each doubt and state the full cost.
• Plans the design. Uses the design plan skill to set one design system from your brand, then plan three directions that differ in layout and what the pictures do.
• Reviews the page. Uses the landing page checklist to run 30 yes-or-no checks at the five stops a buyer makes, quote the evidence for each no, and rank the fixes.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id ad-landing-page only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/ad-landing-page/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Your website, as a link or saved pages
• Your offer, with price and exact guarantee terms
• The ad the page is for, with its first line, offer and picture
• Customer reviews, copied as written (optional)
• Who the ad is for, if you know (optional)

Helpful context (optional)

• A phone screenshot of the ad as it runs, so the first screen can match its picture as well as its words
• The questions buyers ask support before they order, so the answers section uses real doubts
• Your current page's text, so the review can show which old problems the new page fixes
• Real product photos at full size, so the design plan uses your product and not a stand-in

Tools and access

• Claude: Keeps your offer terms, the ad's words and four steps of work straight in one run.
• Figma: Holds the chosen design direction as phone and desktop frames your builder can follow.
• PageSpeed Insights: Free Google check of a built page for phone speed, contrast and tap target problems.
• Any good chat AI: This is a writing job from facts you supply, and the main chat AIs all handle it well.
• Claude: Holds a long design system and section plan in one chat, and can turn the chosen direction into a working page to preview.
• Figma Make: Turns the build brief into a working prototype you can tweak, so you can compare directions before anyone codes.
• WebAIM Contrast Checker: A free check of each text and background pair in your colours, before and after the page is built.
• Any good chat AI that reads images: It can judge the first-screen and phone checks from your screenshots instead of guessing from text.
• PageSpeed Insights: Free from Google. It gives the phone speed numbers check 30 needs from just the page's address.

Functions and deliverables

• Ad landing page designer: Create page copy that matches your ad, three design options and a 30-point review from your site facts and offer.
  • The full page copy, from the first screen to the closing button
  • Your buyers' doubts, most common first, each answered in its own section
  • A design plan from your brand, with phone and desktop notes
  • 30 yes-or-no checks, the deal-breakers flagged, and five fixes in order
• Ad-matched landing page writer: Write landing page copy that picks up where your ad left off. Give it the ad, your facts and reviews. You get a page with the full cost stated.
  • A page brief naming the buyer, the reason to buy and the offer
  • A first screen built from the ad, and a list of your buyers' doubts with the section that answers each
  • Body sections with answer-first headings, a cost block, questions and a closing
  • A list of every field left empty because a fact was missing
  • Any of its own checks the page still misses, each named with the reason
• Landing page design planner: Plan a landing page design from your copy and brand. Get three different directions, a section plan and a build brief, before anyone builds.
  • One design system with named colours, font roles, a main visual move and layout rules
  • Three design directions, each with its first screen, image job and section order
  • A section plan with one row per section, for phone and desktop, and a build brief you can paste into a design tool
  • If you sent screenshots, design and technical findings with a fix for each
  • Any of its own checks the plan still missed, one line each, or none
• 30-point landing page checker: Share your page and screenshots. Get a 30-point audit, a score and five fixes to make first.
  • A two-line verdict naming the stop where the page loses buyers
  • All 30 checks with yes, no or can't tell, the evidence and a one-line fix
  • A count of no's at each stop, so you see where the trouble clusters
  • The five fixes to make first, deal-breakers at the top, and what it couldn't judge
  • A checks score out of 100 (the share of checks the page passes), now and with the five fixes made
• Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
  • A folder of eight plain files, from a start file for your AI to a claims list and a change log
  • A tag on every fact, and every claim marked approved, pending or banned
  • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
  • A short slice for your next step, if you name one
• Joseph Sugarman: Build a story-led product page through Joseph Sugarman’s recorded approach. Keep readers moving, state the drawback and plan a small test before rollout.
  • Your problem worked on the way Joseph Sugarman would: their questions, their method, their push-back
  • The answer or the work, in Joseph Sugarman's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Jonah Berger: Make a message easier to share or a change easier to try through Jonah Berger’s recorded research. Find the useful hook and remove barriers.
  • Your problem worked on the way Jonah Berger would: their questions, their method, their push-back
  • The answer or the work, in Jonah Berger's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• An ad is getting clicks but the page it sends people to doesn't sell.
• You're launching a new ad and want a page made for it, not your home page.
• Your product page opens with the product name and a brand story instead of a reason to buy.

Limits to check before starting

• You have no ad yet: use the Website first-screen copy writer to draft the top of the page, then come back once an ad is running.
• You only want the page text, without design or review: use the Ad-matched landing page writer on its own.
• You already have a live page and only want it graded: use the Landing page conversion reviewer or the 30-point landing page checker.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the handoff pack. It's a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Have your inputs ready. Your website link, your offer and guarantee terms, and the ad itself (its first line, the offer it named and what the picture shows). Add reviews if you have them.
• It works step by step and saves each result. Check the page brief at the top of the copy first. If the buyer or reason is wrong, everything after it is too.
• Hand the copy and design plan to whoever builds your pages, and fix the top items in the review before the ad points to the new page.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/ad-landing-page for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.