Hey, it's Cindy 🌱 You commented score, so here is the weighted six-factor scorecard from the reel.
btw the waitlist for AI System Club is now open! If you're keen on using AI to automate your content, video editing, job search, business or build AI agents, feel free to sign up (only if you want to hehe). Ps. the waitlist gets first dibs:)
the outcome
What you get
A 100-point evidence-based idea score across problem intensity, beachhead size, solution credibility, willingness to pay, differentiation, and timing, followed by a validation plan or a pivot.
Use the guide in order. Gather the real inputs, run the prompts against those inputs, inspect the evidence, then make one reviewable change at a time.
start here
Set it up step by step
Describe the idea, problem, solution, first customer, price, and why now. Attach interviews, search data, presales, competitor pricing, or other evidence.
Run the scorecard prompt. Claude must mark unsupported claims as assumptions and cap scores that lack evidence.
Inspect the score table and the three biggest failure modes. Challenge any high score without a source.
Run the cheapest validation test for the weakest high-weight factor.
Rescore after the test. Build only when the evidence changes, not because the wording got more persuasive.
copy these
The prompts
Run the weighted scorecard
📋 copy this
Act as a rigorous venture analyst. Evaluate this idea using only the evidence I provide and current primary sources you can cite. Score six factors from 0 to 10 and apply these weights: problem intensity 25%, willingness to pay versus delivered value 20%, reachable beachhead size 15%, solution credibility and four-week buildability 15%, differentiation and defensibility 15%, market timing 10%. For each factor show: score, weight, weighted points, evidence, assumptions, strongest counterargument, and the cheapest test that could move the score. Cap any factor at 5 when I provide no direct evidence. Calculate the total out of 100 and show the arithmetic. Then give me the three most likely failure modes, the single highest-leverage test to run this week, a kill criterion, and one pivot that keeps the useful insight while targeting a sharper pain. Do not imitate McKinsey or claim insider VC knowledge.
check the work
Quality gate before you trust it
1 Weights total 100% and the arithmetic is visible.
2 Unsupported factors are capped rather than rewarded for confident prose.
3 Market size uses a reachable first segment, not a global headline number.
4 The recommended test has a cost, timeframe, success threshold, and kill threshold.
5 The pivot preserves the strongest evidence while changing the weakest assumption.
6 Save the source links, as-of date, and final evidence beside the output so another person can reproduce the check.
Guardrail. A score is a decision aid, not proof of product-market fit and not a funding prediction. Models can manufacture confidence when evidence is thin. Validate with real behaviour, especially payment, retention, or repeated use.
keep it useful
Save the evidence with the workflow
Save the prompt with the source links and the date you verified them. When the tool, policy, price, interface, or documentation changes, update the guide before you reuse the workflow. Keep the inputs and outputs beside the project so the next run can be checked instead of reconstructed from memory.
the waitlist is now open
AI System Club is launching soon
Build AI systems with me through recorded lessons you can follow at your own pace. Join the waitlist for first access and the founding price.
btw this list gets first dibs the moment doors open :)