Playbook / How it was made

Board Games

Everything below is read live from the article file and its brief.

Read the published article

Credits

AI authors ChatGPT-5.1, Claude Sonnet 5, ChatGPT-5.5, Grok 4.7
Published2025-11-21
Last modified2026-09-24
TemplateG (evidence tier 3)
ChartsNone

Pass log

7 logged passes by 4 models.

DatePassModelNote
2025-11-21 draft ChatGPT-5.1 -
2026-07-04 rewrite Claude Sonnet 5 Rewrite with named games, scoring mechanics, weight-matching table, and 5 real 80/20 examples
2026-07-04 edit ChatGPT-5.5 Retarget board game article for teaching rules, game choice, and hosting intent
2026-09-22 rewrite Grok 4.7 Casual take: BoardGameGeek rating skew, then the teach. Dropped the checklist.
2026-09-23 rewrite Grok 4.7 Reframed game night around the fit between game, group, teach, and session; added positive reasons to play and the story-tomorrow practice without dismissing collecting.
2026-09-23 voice Grok 4.7 Removed defensive not-exactly-80/20 lines so the lens opens an opportunity. Kept a limit only where a real figure needed one.
2026-09-24 rewrite Grok 4.7 Kept the fit-and-hospitality essay and restored the group-choice table, a Ticket to Ride teach, and scoring examples.

Research brief

The brief was written before the outline. It is the research the article stands on. Open the full brief.

Mechanical checks

These are run on the published HTML when you load this page. They are the checks a machine can do. The judgement gates - the deletion test, audience fit, whether the concentration claim is real - are in the publish checklist and are not automated.

Length1,491 words
Opens with proseYes
Outbound sources 1 link to blog.recommend.games
Link hygieneAll 4 links open in a new tab with rel set
Illustrative labels0 scenarios labeled as illustrative
Em dashesNone
AI sludge wordsNone

A failed row means the article is due for another pass.