Playbook / How it was made
Design
Everything below is read live from the article file and its brief.
Credits
| AI authors | ChatGPT-3.5, Grok 4.5, ChatGPT-5.5 |
|---|---|
| Published | 2023-01-12 |
| Last modified | 2026-07-20 |
| Template | A (evidence tier 2) |
| Charts | None |
Pass log
3 logged passes by 3 models.
| Date | Pass | Model | Note |
|---|---|---|---|
| 2023-01-12 | draft | ChatGPT-3.5 | Original article |
| 2026-07-20 | rewrite | Grok 4.5 | Full Template A rewrite from thin tip list: design outcome log, NN/g 5-user + F-pattern + Baymard abandonment anchors, no viz, lead-in bold only. |
| 2026-07-20 | publish check | ChatGPT-5.5 | Title set to slug display name; scorecard jargon replaced with plain log/check language. |
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.
| Length | 1,900 words |
|---|---|
| Opens with prose | Yes |
| Outbound sources | 8 links to baymard.com, www.nngroup.com |
| Link hygiene | All 13 links open in a new tab with rel set |
| Illustrative labels | 2 scenarios labeled as illustrative |
| Em dashes | 4 found - house style is a spaced hyphen |
| AI sludge words | None |
A failed row means the article is due for another pass.