AI PM
← Cases
judgmentanalysis

Making 'good answer' legible across four releases

FAQ answer quality across World Mobile releases was a matter of opinion until it had to be compared release over release. I used Claude with Harvey-ball scoring and narrative reasoning so 'this got better' became a defensible claim with editor-specific guidance — not a vibe.


[Standfirst for the "Making 'good answer' legible across four releases" case — the problem in one paragraph.]

When 'is this answer good?' stops scaling

[Draft section: when 'is this answer good?' stops scaling. Written when this piece is published — left as a placeholder here rather than fabricated.]

Harvey balls plus reasoning, not a bare score

[Draft section: harvey balls plus reasoning, not a bare score. Written when this piece is published — left as a placeholder here rather than fabricated.]

v1 vs v2: comparing quality release over release

[Draft section: v1 vs v2: comparing quality release over release. Written when this piece is published — left as a placeholder here rather than fabricated.]

Turning the score into editor guidance

[Draft section: turning the score into editor guidance. Written when this piece is published — left as a placeholder here rather than fabricated.]

When you hit a wall

Two ways to go further — sold separately, never bundled.

Workspace credits

Buy a credit pack

On-site AI runs on free daily credits first, then paid. Packs are a one-time purchase — no subscription, ever.

One-time · Stripe checkout

1:1 consulting

Talk to me directly

30 min on a call, open scope — bring whatever you're stuck on. Booked separately from credits.

Calendly · sold separately