Did some math, to calculate the success index. I realized that the LLM returns the ingredients (market size, growth, monetization, difficulty, competitor count, weaknesses).

So I have to normalize the signals from 0-1,
market = clamp( (log10(TAM_dollars) - 7) / 4 , 0, 1 )
growth = clamp( CAGR% / 30 , 0, 1 )
n = number of competitors
n = 0 → 0.40 (unvalidated market)
n = 1–3 → 0.90 (validated, room to enter)
n = 4–6 → 0.70
n = 7–9 → 0.50
n ≥ 10 → 0.30 (saturated)
feasible = (10 - difficulty) / 9
success% = round( 100 / (1 + e^(-6 * (S - 0.5))) )

Now working on implementation