Hire an AI page drop-off test planner

Everything it can hand back

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

• The step that loses the most buyers, the page that owns it, and fixes sized by effort
• The doubts your fixed page still leaves open, with the answer to add and where
• The test size, weeks needed and a verdict on whether you can test at all
• Rules for running the test, and a score out of 100 for test readiness

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

• 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: Your page gets visits but few sales, and you don't know which step loses the most people.

• Step table. Visits at each step, the drop-off between steps, and the leakiest step with the page that owns it.
• Fixes. Each finding from the phone review, sized by effort, with a note on whether to ship it or test it.
• Open doubts. Customer doubts the fixed page still leaves open, the missing answer or proof, and where to add it.
• Test size. The smallest lift worth finding, the weeks a fair test needs, and a verdict on whether you can test.
• Rules for running the test. Simple rules to follow while the test runs, plus a test readiness score out of 100.
• 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

• The step table adds up: each step's visits are no more than the step before.
• The leakiest step is the one with the biggest drop that the person could act on.
• Each fix says what was seen on the page.
• Each open doubt names a customer question behind it.
• 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 Neil Patel would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Finds the worst drop-off. Uses the funnel drop-off finder to build a step table, find the leakiest step, match it to its page and review that page on a phone.
• Finds the open doubts. Uses the unanswered question skill to check each customer doubt against the fixed page and say where each missing answer goes.
• Sizes the test. Uses the A/B test traffic checker to work out honest numbers, size the test, give a verdict and set rules for running it.

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 page-drop-off-fix 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/page-drop-off-fix/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 page, as a link, text or screenshots
• Visits or orders at each step, from your store or analytics (optional for step 1)
• Customer questions or reviews, copied as written
• Visits and orders for the last few weeks, as an export

Helpful context (optional)

• Visits and orders for the last four weeks, split by source
• Support tickets or pre-sale questions
• Phone screenshots of each step of the buying path

Tools and access

• Google Analytics: Gives visits and orders by step for the step table.
• Claude: Keeps the step table, the fixes and the test size straight across three steps.
• PageSpeed Insights: Free Google check of the page for phone speed problems.
• Any good chat AI that reads images: It can work from your phone screenshots and a pasted step table in one chat.
• Your analytics or GA4 funnel report: Gives the counts at each step, split by device and source, which the step table needs.
• Google Sheets: Holds the step table so you can check every rate and sizing sum yourself.
• Any good chat AI that reads images: It can check your phone screenshots for where each answer sits, not just the page text.
• Google Sheets: Holds the doubt table so you can sort it, add new reviews, and tick off fixes.
• Any good chat AI: The sums are simple, and the main chat AIs all show their working when asked.
• Google Sheets: Keeps each month's numbers in one place, so you can check every sum and compare with your own past.
• Evan Miller's sample size calculator: Free, and a quick second check on the visitors per version.

Functions and deliverables

• Page drop-off test planner: Share page content, step counts and customer questions. Get the largest measured drop, answer gaps and a traffic-based test estimate.
  • The step that loses the most buyers, the page that owns it, and fixes sized by effort
  • The doubts your fixed page still leaves open, with the answer to add and where
  • The test size, weeks needed and a verdict on whether you can test at all
  • Rules for running the test, and a score out of 100 for test readiness
• Sales funnel drop-off finder: Find the step where most visitors drop out before they buy. Get fixes sized from your own numbers and a page score out of 100.
  • A step table and the step where most buyers drop out, with the page that owns it
  • Findings for that page with evidence, each tied to the step it should move
  • Fixes sized from your own rates and labelled as a model, or ranked if you gave no numbers
  • Which fixes to ship now and which to test, what the page needs from you, and what already works
  • A page score out of 100 for the page behind the leakiest step, now and after the ship-now fixes
• Unanswered customer question finder: Find the customer questions your product page leaves unanswered. Paste reviews and phone screenshots. Get a doubt table, fixes and a score out of 100.
  • A table of doubts, each with a quote, its source count, where the page answers it and how visible that is
  • The fact or proof each answer needs, and a proposed answer and place
  • The top five fixes and a list of facts to collect before writing
  • A coverage score out of 100 (how many doubts the page answers where buyers can see them), now and with the new answers in
• A/B test traffic checker: Check if your site has enough visitors for an A/B test. Paste visits, orders and revenue to get the weeks needed and a readiness score out of 100.
  • A numbers table with conversion rate, average order value and revenue per visitor, each sum shown
  • A short read of what moved and what the traffic mix explains
  • The test sizing written out, with visitors and weeks needed
  • A verdict (can test, test a bolder change, or ship and watch) and three next actions
  • A test readiness score out of 100, showing how much of the needed sample your traffic reaches in four weeks
• 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
• Neil Patel: Plan search content using Neil Patel’s recorded approach. Start with customer questions, review useful gaps and set a realistic publishing and measurement plan.
  • Your problem worked on the way Neil Patel would: their questions, their method, their push-back
  • The answer or the work, in Neil Patel'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

• Your page gets visits but few sales, and you don't know which step loses the most people.
• You've changed your page before and couldn't tell whether it worked.
• You want to know if your traffic is big enough to run a fair A/B test.

Limits to check before starting

• Your page has no visitors yet: there is nothing to measure, so use the Landing page conversion reviewer to review the page by eye first.
• You want a fast pass or fail on the page itself: use the 30-point landing page checker.
• You need a new page written from scratch: use the Reasons-to-switch page writer.

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 page, the numbers at each step and your customers' questions.
• It works step by step and pauses twice. First while you fix the worst step, then while you add answers and export your traffic.
• Give each pause's result to the next step.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/page-drop-off-fix 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.