Hire an AI product risk experiment planner

Everything it can hand back

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

• Four risks scored out of 100, with the weakest named
• One small test, who to run it on and what to cut from it
• A fail line written before you run it
• A keep going or change course call, with the new guess and a review date

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 a product idea and a bad feeling about one part of it.

• Step 1: Four risks. Value, ease of use, feasibility and viability each scored by how strong the proof is, with the riskiest named.
• Step 2: Smallest test. The action that counts as a yes, who to try it on, what to cut, the ask and a fail line.
• Step 3: Keep or change. Your results set against the fail line, signs you are stuck, the kind of change and a new guess.
• Review date. A date to look at the new guess again, with the next test to run.
• 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 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 Steve Blank would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Score the four risks. Writes the problem and the customer in plain words, scores value, ease of use, feasibility and viability by how strong the proof is, and names the weakest.
• Shrink the test to the smallest one. Takes the test for the weakest risk, names the action that counts as a yes, picks five to twenty people, cuts everything the test does not need and sets the fail line.
• Run the test (your turn). Run it with real people and write down what each one did and said. Count the no answers too.
• Decide whether to keep going or change course. Sets your results beside the fail line, counts the signs you are stuck, names the kind of change that fits what people said and writes the next guess with a review date.

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 test-your-ideas-riskiest-risk-and-decide-what-next 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/test-your-ideas-riskiest-risk-and-decide-what-next/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 product idea and what you already know about it
• Customer words, reviews or messages (optional)
• Your brand facts (optional)
• After the test, a note of what each person did and said (step 3 waits for it)

Tools and access

• Any good chat AI: Rating evidence and writing a test is text work that any strong chat AI does with this skill.
• A prototype or mock page: Lets you run the cheap test it recommends with real people.
• Any good chat AI: Choosing a form and writing the cut list is text work.
• A one-page site builder such as Carrd: Makes a sign-up or pre-order page in an afternoon.
• A screen recorder: Records a short demo film without extra software.
• Any good chat AI: Weighing evidence and writing a call is text work.
• A shared document: Keeps the evidence, the call and the review date where the team can see them.

Functions and deliverables

• Product risk experiment planner: Share your idea, users and current evidence. Get key risks, a small test plan and a next-step review after real results.
  • Four risks scored out of 100, with the weakest named
  • One small test, who to run it on and what to cut from it
  • A fail line written before you run it
  • A keep going or change course call, with the new guess and a review date
• Product idea risk checker: Share your idea and evidence. Get four risk areas, evidence scores, and a cheap test for the riskiest gap.
  • Each of the four risks with the evidence, or marked unknown
  • A score out of 100 for how well the evidence covers the risks
  • A named owner for each risk
  • The cheapest test for the riskiest one, and the result that would change your plan
• Minimum experiment planner: Pick the cheapest test for your riskiest business guess. Get the test form, who to try it on, what to cut and a fail line.
  • The behaviour that would count as yes, and how many people must do it
  • A test form and a runner-up, each with its cost and what it cannot tell you
  • The early adopters to try it on and how to reach them this week
  • A keep list, a cut list and the ask for a real commitment
  • A fail line, and who to call afterwards to learn why
• Product pivot decision reviewer: Decide whether to keep going or change course. Get a one-line call with facts for and against, the kind of pivot that fits and a review date.
  • A keep-going or change-course call in one line, with facts for and against
  • A count of six stuck signs, each with its evidence
  • How many more test cycles you can afford
  • If changing course, the kind of change that fits, what you keep and a new guess to test
  • A date for the next review and who should be there
• 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
• Steve Blank: Test your startup assumptions with Steve Blank's customer development method. Get a guess list, a one-page model and your next customer interviews.
  • Your problem worked on the way Steve Blank would: their questions, their method, their push-back
  • The answer or the work, in Steve Blank'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 a product idea and a bad feeling about one part of it.
• You are about to build and want one cheap test first.
• You ran a test before but never agreed what a pass or a fail meant.

Limits to check before starting

• You already have real sales for this idea and know it works: just grow it, or use the Seven-question startup scorer to check the whole business.
• Your main question is about money or pricing: use the Bad-year break-even tester first, then come back to test the risk.
• You want to find out what customers say about a problem before you have an idea: use the Buyer problem list builder.

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 has HANDOFF.md and three skill files, in the order they run: Product idea risk checker, Smallest test picker and Pivot or persevere decider.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Paste your idea and anything real you have, such as sales, messages or customer words. Say what you have not proved yet.
• Run the test with five to twenty people. Write down what they did, including who said no.
• Come back with those notes. The last step judges them against the fail 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/test-your-ideas-riskiest-risk-and-decide-what-next 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.