Hire an AI product fit survey and test planner

Everything it can hand back

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

• A short survey with one fixed key question and open follow-ups
• How to count the 40 percent test and what it means
• A plan to study the group who would be very disappointed, and one change to try
• Your growth ideas scored for impact, confidence and ease, sorted by average
• One test for each of the top ideas, with a measure and a stop date, and a run order

How it does the job well

• Start from the user problem and the evidence for it, then the solution.
• Write decisions down with the reason and the options you rejected.
• Keep scope small enough to ship and learn. Name what is out of scope.
• Define how success will be measured before building.

Mistakes it avoids

• Treating opinions or one loud request as proven demand.
• Specs that skip edge cases, error states or dependencies.
• Roadmaps with dates but no owners or confidence levels.

What a good result looks like

An example, not your task: You have users and want to know if the product is a must-have before you spend on growth.

• Must-have survey plan. Who to ask, the survey with its fixed key question, how to count the 40 percent test, and how to study fans.
• Growth idea ranking. Each growth idea scored 1 to 10 for impact, confidence and ease, averaged and sorted.
• First three tests. One test for each top idea, with a measure, a stop date and a run 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

• The key question has fixed answers, so the share is easy to count. The 40 percent line is described as a signal, not proof.
• Each score has a reason, and the average is shown.
• Each test has a measure and a stop date.
• Step 2 used your real survey answers, and no survey result or user number is invented.
• 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 Sean Ellis would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Picks who to ask. Picks active users who have had the core experience, and plans interviews first if there are too few.
• Writes the survey. Writes one fixed question on how they would feel without the product, plus open questions on the main benefit and who it is for.
• Plans how to count. Shows how to count the share who say very disappointed against the 40 percent line, and how to study that group.
• Waits for the answers. You send the survey and collect the answers. Nothing more runs until you bring them back.
• Scores the ideas. Takes your survey findings and scores each growth idea from 1 to 10 for impact, confidence and ease, then averages and sorts.
• Plans the tests. Writes one test for each top idea with a measure and a stop date, and puts the quickest first.

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 product-miss-growth-tests 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/product-miss-growth-tests/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

• What your product does and the core experience a user should have had
• How many active users you have and how to reach them
• A buyer profile or customer reviews (optional)
• A week or two to send the survey and wait for the answers
• Your list of growth ideas, from everyone who has them
• Your goal number and what you tried before (optional)

Tools and access

• Any good chat AI: Writing the survey and counting answers is text work that any strong chat AI does with this skill.
• A free form tool: Collects the answers in a table you can paste back.
• Any good chat AI: Scoring and sorting ideas against notes is text work that any strong chat AI does with this skill.
• A spreadsheet: Keeps the scores, averages and test results in one table you can re-sort.

Functions and deliverables

• Product fit survey and test planner: Share product and user context. Get a short survey, a review of actual answers and ranked growth ideas to test.
  • A short survey with one fixed key question and open follow-ups
  • How to count the 40 percent test and what it means
  • A plan to study the group who would be very disappointed, and one change to try
  • Your growth ideas scored for impact, confidence and ease, sorted by average
  • One test for each of the top ideas, with a measure and a stop date, and a run order
• Product demand survey planner: Plan a must-have survey for your product. Get a short survey, the 40 percent test and a plan to study the users who would be very upset.
  • A short survey with one fixed key question and open follow-ups
  • How to count the 40 percent test and what it means
  • A plan to study the group who would be very disappointed
  • One change to try and a plan to run the survey again
• Growth idea ranker: Share growth ideas and what you know so far. Get reasoned scores, a ranked list and small tests for the strongest ideas.
  • Each idea scored for impact, confidence and ease, with a reason for each score
  • The list sorted by average score
  • One test per top idea with a measure and a stop date
  • A run order, quickest first, and a re-score step
• Paid idea test planner: Share an idea, buyer, price and profit goal. Get buyer-count maths, a two-day outreach plan and decision rules set before testing.
  • The buyer count your goal needs
  • Ten people to ask and how to reach each
  • The exact ask and a two-day schedule
  • Go, change and one-more-round rules
• Product context file writer: Share product facts, audience and positioning. Get a reviewed context file that other marketing skills can reference.
  • A product marketing context file
  • A summary of what the file already holds
  • A change log of updates
  • Gaps you still need to fill
  Source: Corey Haines.
• Sean Ellis: Plan product-value research or growth experiments using Sean Ellis’s recorded approach. Find what users would miss, choose a useful measure and test one change.
  • Your problem worked on the way Sean Ellis would: their questions, their method, their push-back
  • The answer or the work, in Sean Ellis'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 have users and want to know if the product is a must-have before you spend on growth.
• Growth has stalled and the team has twenty ideas, but no way to choose.
• You are about to raise money or hire for growth and want evidence the product holds up.

Limits to check before starting

• You have fewer than about 30 active users: talk to them one by one first, or use the Customer purchase interview script writer.
• Your product has not launched and has no users: use the Minimum experiment planner to test the idea with real people first.
• You already know your fans and only want to compare competitors: use the Competitor funnel mystery shopper.

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".
• Describe your product and users. It writes the survey and the plan, then stops.
• Send the survey to active users and wait for the answers. This usually takes a week or two.
• Bring back the results and your list of growth ideas and say "carry on".

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/product-miss-growth-tests 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.