Free in the Backbrief Kit
Ask an AI about your idea and you get a paragraph. This gives you a number.
Paragraphs are easy to nod along to. /grade-idea is one free command in Claude Code that runs five advisors with different lenses over your business idea, scores six dimensions 1 to 10, and makes every score cite your own words back to you. The pass line is 8.5 and it is deliberately strict. A low score is the useful result: it shows you the hole while it is still cheap to fix.
Three famous ideas, graded honestly.
- The classic coffee shop2.2 / 10
- Quibi, graded on its 2018 pitch3.8 / 10
- A vending machine route3.5 / 10
Risk coverage was the lowest dimension in all three runs. The panel scored what the pitches left out, which is exactly what a paragraph of encouragement never does.
On Quibi: the advisors know what any reader in 2026 knows. Treat it as a teaching grade, not a time-machine verdict.
8.5 is a stress-test pass line, not a prediction. A pass means no confident weakness was left un-named.
How it works. Three steps, no prompting skill.
Install the free kit.
One instruction in Claude Code, or the plugin install if you prefer. The kit is free, and /grade-idea ships inside it.
Type /grade-idea and describe the idea.
Plain words, as much or as little as you have. A napkin sketch is a valid input; what is missing gets scored as missing, not filled in charitably.
Read the scorecard.
Five advisors with different lenses score six dimensions, and every score has to cite your own words back to you. No citation, no score. You get a number, the reasoning, and the weaknesses ranked.
The six dimensions. Same public rubric as the paid system.
/grade-idea uses the same six-dimension rubric that Backbrief Business OS uses to grade full business plans, published verbatim on the inside page. The difference is depth, not honesty: the free command is a single pass on a raw idea, and the paid loop takes a full plan through revision cycles with a capped, cited grading loop.
- Is the offer clear.
- Who pays, for what, stated so a stranger understands it in one sentence.
- Is the demand real.
- Actual evidence people want this: named buyers, comparable products, real signals. Not "everyone needs this."
- Do the numbers work.
- The unit economics close using your own numbers from the brief.
- Can you actually run it.
- With your hours, your budget, your skills, not a hypothetical team's.
- Are the risks named.
- The top ways it fails, each with a mitigation or your explicit, eyes-open acceptance.
- Why you.
- A concrete reason someone picks this over the obvious alternative, including doing nothing.
Scores run 1 to 10 with equal weights. An 8.5 average passes. That is an A-.
It is free, and it is in the kit.
The free Backbrief Kit installs in about two minutes and ships the whole build team alongside /grade-idea. If the idea eventually deserves a full plan, the graded loop lives in Backbrief Business OS. Start with the number.