AI Blocks › Test an idea before you build it
Test your idea's riskiest risk, then decide what next
Give it your idea. Get its worst risk found, one small test to run, and a keep or change call.
Test your idea's riskiest risk and decide what next 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 ideas die from one weak spot, not from all four at once. People test the part they enjoy, such as the design, and skip the part that could end the idea, such as whether anyone will pay. Then they argue about what the results mean, because nobody wrote down what failure looked like. The steps fix this in order. First the idea is scored on value, ease of use, feasibility and viability, and the weakest one is named. Then its test is cut down to the smallest version, with an action that counts as a yes and a fail line set before you start. Then you run it. After the pause you bring back what each person did and said, and the last step sets those results against the fail line and says whether to keep going, change course or stop.
You give it
- 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
- Brand brain (optional)
- Customer words (optional)
You get
- 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
Use it when
- 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.
Steps
- Product idea risk checker: Paste your product idea and what you know. Get the four risks scored out of 100 and the cheapest first test.
- Minimum experiment planner: Paste your ranked guesses. Get the cheapest test for the top one, who to try it on and what to cut.
- Pivot or persevere decider: Paste your progress and customer notes. Get a keep-going or change-course call, the type of change and a review date.
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".
- 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.