Hire an AI product assumption test reviewer

Everything it can hand back

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

• The riskiest guess, the smallest test, the numbers that count as a pass and a rule for when to change direction or keep going
• Your reported numbers marked as vanity or real, with a per-customer or per-group rate in place of each
• A chain of whys checked against facts, the cause you can fix and a check that it won't happen again

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 want evidence before you build more of it.

• Step 1: MVP experiment planner. The riskiest guess, the smallest test, the pass line and a rule for changing direction or keeping going.
• Step 2: Vanity metric fixer. Your numbers marked as vanity or real, with a per-customer or per-group rate in place of each.
• Step 3: Root cause finder. A chain of whys checked against facts, the cause you can fix and a prevention check.
• 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

• Plan the smallest test. Lists the guesses your idea depends on and picks the riskiest. Designs the smallest test, sets the pass numbers and a rule for changing direction.
• Fix the numbers. Takes your test results and the plan from step 1. Marks the vanity numbers and swaps each for a rate per customer or group.
• Find the root cause. If the result missed, asks why of what you saw, then why of that answer, until it reaches a cause you can fix. Checks each answer against facts.

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 guess-test-metrics 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/guess-test-metrics/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 the guesses it depends on
• Your current plan (optional)
• The numbers from your test, such as visits, sign-ups and sales, for the later steps
• Notes from customers or the team on what happened (optional)
• Time to run the test and collect its numbers

Helpful context (optional)

• Raw numbers by customer group and week
• A list of what changed in the product between versions
• Quotes from customers who left

Tools and access

• Any good chat AI: Holds the plan, the results and the chain of whys across the pause.
• A spreadsheet: Lets you calculate per-customer rates from your raw numbers.
• 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.
• Any good chat AI: Reading a sheet and writing formulas is text work.
• A spreadsheet or analytics tool: Builds the per-group tables and charts from your export.
• Any good chat AI: Building and checking a chain from records is text work. Claude, ChatGPT and Gemini all do it with this skill.
• Your ticket or incident system: Holds the logs and tickets the chain needs as proof. Copy in the lines that matter.

Functions and deliverables

• Product assumption test reviewer: Share an idea and available evidence. Get a small-test plan, measures to track and a cause review after real results arrive.
  • The riskiest guess, the smallest test, the numbers that count as a pass and a rule for when to change direction or keep going
  • Your reported numbers marked as vanity or real, with a per-customer or per-group rate in place of each
  • A chain of whys checked against facts, the cause you can fix and a check that it won't happen again
• 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
• Business metric quality reviewer: Find the vanity metrics in your weekly report and swap them for per-customer rates you can act on, plus one main number to track.
  • A table showing which numbers are vanity
  • Replacement rates with formulas
  • Results split by group and release
  • One goal, one main number and a data check
• Root cause finder: Find the root cause of a problem that keeps coming back. Get a chain of whys checked against facts, a fix and a prevention check.
  • The problem written as something seen, not a guess
  • A chain of whys, each answer with its proof or marked unconfirmed
  • A second chain, in case there is another cause
  • The root cause your team can change
  • A fix that removes it, and a prevention check
• 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 want evidence before you build more of it.
• Your numbers are going up but you can't tell if the business is better off.
• A test or launch missed its target and you need to know why before you try again.

Limits to check before starting

• You have no customers or visitors to test on yet: use the Seven-question startup scorer first.
• You want to know if your business survives a bad year: use the Bad-year break-even tester.
• Your ad sales dropped and you need the reason: use the Ad sales drop analyst.

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 plus one skill file for each step.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Describe your idea. It runs step 1 and stops.
• Run the test with real customers and collect the numbers it asked for.
• Bring the numbers back and say "carry on from step 2". Add your notes on what happened.

Read it as data

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