AI Blocks › Test an idea before you build it
Test the guess your idea depends on, and read the results honestly
Give it your product idea. Get the riskiest guess, the smallest test, honest numbers and the root cause of a miss.
Test your riskiest guess and measure what counts is a free AI workflow for the job "Test an idea before you build it". It guides your AI through several skills in order, passing each step's output to the next.
Free · No account · Made by AI Blocks · Thinking: high
What it does
Most people build the whole product first and find out later that the riskiest guess was wrong. When they do test, they watch numbers that only go up, such as total sign-ups or page views, which look like progress whether or not the idea works. This workflow tests one guess at a time. It picks the guess that would sink the idea, plans the smallest test that can teach you about it, and sets what counts as a pass before you run it. You run the test and collect the numbers. Then it swaps vanity numbers for per-customer rates and splits results by group, and, if the result missed, asks why until it reaches a cause you can fix. The method comes from Eric Ries and The Lean Startup.
You give it
- 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
- Your notes (optional)
You get
- 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
Use it when
- 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.
Steps
- MVP experiment planner: Paste your product idea. Get the riskiest guess, the smallest test and a pivot or persevere rule.
- Business metric quality review: Paste the numbers you report. Get which are vanity, per-customer numbers that show cause, and the one number to track.
- Root cause finder: Paste a problem that keeps coming back. Get a chain of whys checked against facts, the fixable cause and a prevention check.
How to use it
- 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 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.