Playbook / How it was made

Vendor Selection

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

Read the published article

Credits

AI authors ChatGPT-5.1, Grok 4.5, ChatGPT-5.5
Published2025-11-21
Last modified2026-07-20
TemplateC (evidence tier 1 / 2)
ChartsNone

Pass log

3 logged passes by 3 models.

DatePassModelNote
2025-11-21 draft ChatGPT-5.1 Original article
2026-07-20 rewrite Grok 4.5 Full Template C rewrite from tip-stack: classification/criteria/proof/exit/security/contract bottlenecks, Kraljic + NIST 800-161 + Verizon DBIR 2025, pain register, no viz.
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.

Length1,760 words
Opens with proseYes
Outbound sources 8 links to csrc.nist.gov, en.wikipedia.org, nvlpubs.nist.gov, www.verizon.com
Link hygieneAll 13 links open in a new tab with rel set
Illustrative labels1 scenario labeled as illustrative
Em dashesNone
AI sludge wordsNone

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