Hire an AI risky business assumption test planner

Everything it can hand back

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

• The guesses your plan rests on, each with a number, ranked, with the riskiest named
• The cheapest kind of test for the top guess, who to try it on and what to leave out
• Pass, fail and in-between numbers set before the run
• A run plan and a rule for what to do on a pass, a fail or a middle result

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 plan and sense that part of it is a bet, but cannot say which part.

• step-01-leap-of-faith-assumption-finder.md. The few guesses your plan rests on, each with a predicted number, ranked with the riskiest first.
• step-02-smallest-test-picker.md. The cheapest kind of test for the top guess, who to try it on and what to leave out.
• step-03-mvp-experiment-planner.md. Pass, fail and in-between numbers set before the run, a run plan and a rule for what to do next.
• 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

• Finds the guesses. Rewrites comparisons as plain facts, splits the plan into a value guess and a growth guess, adds a number to each and ranks them.
• Picks the smallest test. Names the behaviour that counts as yes, picks the cheapest test form, chooses early adopters and cuts everything that does not feed the answer.
• Sets the numbers and the next move. Writes pass, fail and middle numbers first, plans the run one group at a time and writes what to do on each result.

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 riskiest-guess-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/riskiest-guess-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 plan (what you make, for whom, how they find it and what you expect back)
• Your biggest worry (optional)
• What you can spend and who you can reach this week (optional)

Tools and access

• Any good chat AI: Rewriting claims and ranking risk is text work.
• A spreadsheet: Keeps the ranked list and your numbers in one place.
• 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: Ranking guesses and writing a plan is text work.
• A landing page tool such as Carrd or Webflow: Builds a one-page offer for the test in an afternoon.

Functions and deliverables

• Risky business assumption test planner: Share your plan and key uncertainties. Get measurable assumptions, a small test for the riskiest one and decision rules set before testing.
  • The guesses your plan rests on, each with a number, ranked, with the riskiest named
  • The cheapest kind of test for the top guess, who to try it on and what to leave out
  • Pass, fail and in-between numbers set before the run
  • A run plan and a rule for what to do on a pass, a fail or a middle result
• Startup assumption checker: Find the leap-of-faith assumptions in your plan. Paste it and get the few risky guesses, each with a number, ranked so you test the riskiest first.
  • Your comparisons rewritten as plain claims
  • A value guess and a growth guess
  • A ranked list of guesses, each with a number
  • The group to test on first
• 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
• MVP experiment planner: Plan an MVP experiment for your product idea. Find the riskiest guess, run the smallest test, and set a pivot or persevere rule first.
  • A ranked list of guesses
  • The riskiest guess and the smallest test for it
  • Pass, fail and middle numbers set in advance
  • A pivot or persevere rule
• 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 plan and sense that part of it is a bet, but cannot say which part.
• You are about to spend months building and want proof of the shakiest part first.
• Your last test left you with praise and no facts.

Limits to check before starting

• Your plan already has sales or usage data behind it: test the change directly with your own numbers, or use the Ad meaning test planner if the doubt is about an ad.
• You still need to learn what buyers worry about: use the Buyer problem list builder, or talk to five customers first.
• You need to find where your buyers gather online: use the Customer community finder.

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 pack. It holds HANDOFF.md and three skill files, in the order they run: Leap-of-faith assumption finder, Smallest test picker, then MVP experiment planner.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Paste your plan as it stands, comparisons and all. Add the numbers you have, such as price, reach and sign-up rate. Say what worries you most.
• Any number your plan does not give is marked GUESS. Check each GUESS before you rely on it.
• Agree the pass numbers before you run the test, then bring back the results. This workflow plans the test. It does not run it.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/riskiest-guess-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.