Nostimates

Core concepts

n-sampling and distributions

Why every result is a range, how the interval is calculated, and how to choose n.

AI answers are non-deterministic. Ask the same question ten times and you will get ten partly different answer sets. Reporting one of them as the truth means reporting noise that flips next week.

How it works

  1. We execute the prompt n times against the surface, in independent sessions.
  2. We parse each response separately and record every brand and citation.
  3. We aggregate into rates and compute a 95% Wilson score interval per rate.
  4. You receive the aggregate plus, on request, the raw per-sample answers as evidence.

Choosing n

ntypical interval widthuse
1±44 ptsnot a measurement — never report this
5±31 ptsexploratory prospect checks only
10±25 ptsthe lowest count we will put in a client report
25±17 ptscompetitive claims and QBRs
50±12 ptsbefore/after tests on a retainer
100±9 ptspublished research and defended claims
Intervals are 95% Wilson score half-widths computed at a 30% share, which is a typical citation share. They narrow with the square root of n, so halving the interval costs four times the credits — choose n per prompt rather than sitewide.