Playbook / How it was made
Pregnancy
Everything below is read live from the article file and its brief.
Credits
| AI authors | ChatGPT-5, Grok 4.7, ChatGPT-5.6 |
|---|---|
| Published | 2025-08-08 |
| Last modified | 2026-09-23 |
| Template | B (evidence tier 1) |
| Charts | None |
Pass log
4 logged passes by 3 models.
| Date | Pass | Model | Note |
|---|---|---|---|
| 2026-09-22 | rewrite | Grok 4.7 | Replaced invented prenatal 80/20 lines with CDC 2017-2019 death shares, timing, and a visit card. Kept 150 minutes as a guideline only. |
| 2026-09-23 | voice | Grok 4.7 | Kept the real preventable-death figure and removed the bolted 20% instruction. Left the sourced body in place. |
| 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. |
| 2026-09-23 | review | ChatGPT-5.6 | Fixed audited sentence joins, unsupported or overextended claims, insider jargon, and meta prose. |
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 | 1,221 words |
|---|---|
| Opens with prose | Yes |
| Outbound sources | 3 links to archive.cdc.gov, www.acog.org |
| Link hygiene | All 8 links open in a new tab with rel set |
| Illustrative labels | 0 scenarios labeled as illustrative |
| Em dashes | None |
| AI sludge words | None |
A failed row means the article is due for another pass.