Hire an AI demand research and low-cost test plan

Everything it can hand back

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

• A list of what people complain about, how they cope today and when they say they would buy, with links
• A half-page buyer brief in their own words
• A verdict on the idea, with the one fact that could end it
• Two or three cheap tests, each with a method, a number to watch and a pass mark

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 an idea and have not built anything yet.

• Step 1: What people post. Complaints, workarounds and buying signals about the problem, each with a link, plus a demand score.
• Step 2: Buyer brief. The moment that sends people looking, the forces for and against, their own words, and the job in one line.
• Step 3: The kill check. A verdict on the idea, the one fact that could end it, and the cheapest test left.
• Step 4: Cheap tests. The claim as a share of people who will act, two or three tests, a number to watch and a pass mark.
• Hand-back summary. Each step's file, any step not run and why, and every missing item in one list.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a clear yes.
• 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 Eric Ries and Demis Hassabis would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Find the pain people post about. Turns your idea into search phrases, reads public posts and comments, and groups complaints, workarounds and buying signals with links.
• Write a buyer brief from the evidence. Picks the moment that sends people looking and the force that matters most, and keeps their own words.
• Try to kill the idea. Checks the brief against known ways ideas die and looks for live proof that people pay. Ends with dead and why, or alive and the test left.
• Design a cheap test with a pass mark. Writes the claim as a share of people who will act, then gives two or three small tests such as a page, a pre-order or a sign-up.
• Run the test (your step). You run the cheapest test for one to two weeks and write down the numbers against the pass mark.

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-real-demand-for-your-idea-then-run-one-cheap-test 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-real-demand-for-your-idea-then-run-one-cheap-test/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 idea in a sentence or two, and who you think it is for
• The words you would search for to find people with the problem
• Your budget and days for a test
• Anything you already know about rivals or workarounds (optional)
• Your brand file (optional)

Tools and access

• Claude: Every current Claude model reads up to 1 million tokens, so a big pile of reviews and tickets fits in one chat.
• Gemini: Also takes long inputs, and works inside Google Sheets if your survey answers live there.
• Claude, ChatGPT or Gemini: A plain chat is enough. You paste your idea and read the test plan.

Functions and deliverables

• Demand research and low-cost test plan: Research real buyer problems, challenge the idea's weakest assumption and plan a cheap test with a clear pass rule.
  • A list of what people complain about, how they cope today and when they say they would buy, with links
  • A half-page buyer brief in their own words
  • A verdict on the idea, with the one fact that could end it
  • Two or three cheap tests, each with a method, a number to watch and a pass mark
• Product demand researcher: Give it a product idea and choose the sites. With ScrapeCreators access, get linked complaints, objections and buying signals.
  • Pain points ranked by how often they appear
  • Buyer phrases quoted with source links
  • Objections to existing solutions
  • Buying signals and alternatives people use
  Source: ScrapeCreators.
• Buyer brief writer: Share your offer and real buyer words. Get a short copy brief showing their situation, doubts and the main concern to address.
  • A job line that says when they look, what they want, and what stops them
  • How aware the buyer is, and how much the market has already heard, with the evidence
  • The four forces in your buyers' own words, and the one your copy must work on
  • A bank of buyer phrases to borrow, and a list of gaps to ask customers about
  • Any of its own checks the brief still misses, each named
• Business idea killer: Test a business idea before you build it. Get a clear verdict: dead, with the reason, or survived, with the cheapest test left to run.
  • A verdict: dead or survived
  • The kill pattern named, if dead
  • The cheapest remaining test, if survived
  • A row for your kill list
  Source: sickn33.
• Product demand test planner: Turn a product idea and target audience into low-effort demand tests with clear success thresholds.
  • One XYZ hypothesis with a number you can check
  • Two or three test designs that fit your budget
  • A method, a metric and a pass mark for each test
  • Ways to make each test ask for real commitment
  Source: Pawel Huryn.
• 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.
• Eric Ries: Turn a product plan into testable guesses using Eric Ries’s public approach. Start with the riskiest assumption and measure what customers actually do.
  • Your problem worked on the way Eric Ries would: their questions, their method, their push-back
  • The answer or the work, in Eric Ries's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Demis Hassabis: Plan an AI research test using Demis Hassabis’s recorded approach. Choose the root problem, define a score and learn in a small test world.
  • Your problem worked on the way Demis Hassabis would: their questions, their method, their push-back
  • The answer or the work, in Demis Hassabis'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 an idea and have not built anything yet.
• Friends say it is great, but nobody has paid or signed up.
• You can only afford one small test before you decide to go on.

Limits to check before starting

• Your idea already has paying customers: use a market-sizing check, or ask those customers what they want next.
• You have no idea yet: talk to five people in your field about their daily problems first.
• You want a full business plan or a financial forecast: ask an accountant or use a plan template.

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".
• Write the idea as a question, such as "do people want a way to do X?".
• Run the cheapest test it picks for one to two weeks. Compare the numbers with the pass mark and stop if they fall short.

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-real-demand-for-your-idea-then-run-one-cheap-test 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.