Hire an AI marketing survey design reviewer

Everything it can hand back

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

• A decision check: can these questions and this group answer your decision
• A bias review: leading, double and unclear questions, with a fix for each
• A revised survey with each change marked
• A pretest plan with a short guide to read to testers
• A plan for reading the results, with what the replies cannot show
• A hand-back summary that lists every fact it could not check

How it does the job well

• Never send, post or schedule the survey. Write the revised version for the person to send.
• Never invent a response rate, a sample size or a benchmark. If a number is needed and was not given, write MISSING: and say what is needed.
• If the survey collects personal data, say which, and check that a consent line is present. Do not give legal advice. Say that consent and privacy rules depend on where the respondents live and a qualified person should confirm.
• 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: You wrote a customer survey and are about to send it to your email list.

• Decision check. Whether the questions and group can answer your decision, and who the replies cannot speak for.
• Bias review. Each leading, double or unclear question, what is wrong with it and a better wording.
• Revised survey. Your questions and answer choices with every change marked.
• Pretest plan. Who to test with, what to ask them and what to change afterward.
• Analysis plan. How each question will be counted, which groups to compare and the limits of the replies.
• Hand-back summary. Files saved, MISSING lines, checks that could not run and one next step.

How the work is checked

• Every question has a purpose that links to the decision, or is marked as cut.
• No question leads, asks two things at once or uses a word the audience may not know.
• The recruiting method and its limits are written beside the analysis plan.
• A consent line is present if personal data is collected, or MISSING: consent wording is shown.
• 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 Rand Fishkin and Alex Hormozi would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Market size and survey planner. Checks that the questions, the group you ask and the sample can answer your decision. Works out how many replies you need in each group if you give group sizes. Hands the decision check and sample limits to the next step.
• Interview and research planner. Plans the pretest from your survey draft and the decision check and groups from step 1: a few people from your audience say what each question means. Writes the tester guide. It leaves sample design with step 1.
• Wording review. This workflow's own check. It reviews each question for leading, double or unclear wording and for answer choices that overlap or miss a real option. It rewrites the weak ones and logs each change.

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 check-a-marketing-survey-before-sending-it 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/check-a-marketing-survey-before-sending-it/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 draft survey, with every question and answer choice
• The decision the answers will help you make, and by when
• Who you plan to ask, and roughly how many people are in that group
• How you will find respondents, such as an email list or a social post
• Your consent or privacy wording (optional)
• Results from an earlier survey (optional)

Helpful context (optional)

• Group sizes for each audience you care about.
• A named person who signs off the survey.

Tools and access

• Claude, ChatGPT or Gemini with file support: They read your draft as pasted text or a file. Sample-size sums need no special tool. If your AI cannot run code, it works them in the chat and marks them as estimates to check.

Functions and deliverables

• Marketing survey design reviewer: Check whether a survey can answer your decision, improve biased questions and plan how to review the answers.
  • A decision check: can these questions and this group answer your decision
  • A bias review: leading, double and unclear questions, with a fix for each
  • A revised survey with each change marked
  • A pretest plan with a short guide to read to testers
  • A plan for reading the results, with what the replies cannot show
  • A hand-back summary that lists every fact it could not check
• Market size and survey planner: Share market and survey inputs. Get two size estimates, segment-level sample targets and scored customer segments.
  • Top-down and bottom-up market size
  • A divergence check
  • Sample sizes per segment
  • Segment scores with keep or drop
  • Assumptions list
  Source: Alireza Rezvani.
• Interview and research planner: Share a decision, research question and who you can reach. Get a study plan and interview guide, not findings before research.
  • A sharper version of your research questions
  • A recruiting plan with numbers
  • An interview guide
  • Steps for turning notes into findings
  • A list of product decisions the findings should inform
  Source: RampStack.
• Survey question and bias checker: Share survey questions, sampling details and results. Get wording and sample concerns, a review score and fixes for the next survey.
  • A trust score out of 100 with four scored parts and a reason for each
  • Each wording problem quoted, and the memory effects per question
  • Each answer sorted into use as is, use as direction or do not use
  • A rewritten survey for next time, with who to send it to
• 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
• Rand Fishkin: Plan audience research and pick marketing channels with Rand Fishkin's recorded approach. Find where your buyers pay attention and tie it to a goal.
  • Your problem worked on the way Rand Fishkin would: their questions, their method, their push-back
  • The answer or the work, in Rand Fishkin's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Alex Hormozi: Improve an offer, price or lead plan using Alex Hormozi’s recorded frameworks. Check buyer needs, costs and honest promises before adding more leads.
  • Your problem worked on the way Alex Hormozi would: their questions, their method, their push-back
  • The answer or the work, in Alex Hormozi'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

• You wrote a customer survey and are about to send it to your email list.
• You want to know if the answers will help you decide on a price, a product or a message.
• A teammate wrote the questions and you suspect some push people toward one answer.
• You plan to post a survey link on social media and need to know what the replies can and cannot show.

Limits to check before starting

• You already have the answers. Use the Survey results checker and briefing planner workflow.
• You want to size a market, not check a survey. Use the Market size and survey planner on its own.
• You need to plan interviews, not a survey. Use the Interview and research planner.
• You need legal advice on consent or privacy law. Ask a qualified person. This only checks that your consent wording is there.

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 is a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude, ChatGPT or Gemini and say "Follow HANDOFF.md".
• Paste your draft survey. Say the decision, who you will ask and how you will find them.
• Read the decision check first. If the survey cannot answer your decision, fix that before the wording.
• Run the pretest with a few people from your audience. Bring what they said back and ask for a final version.
• Send only after you have made the changes you agree with and added your consent line.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/check-a-marketing-survey-before-sending-it 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.