Detector tell · 2 patterns · weight 2
Two words that mark copy written to impress
Two rows at weight 2, both from the vocabulary of marketing rather than of chat assistants.
Our detector calls this category “Buzzword”. The patterns below are
read out of functions/api/tools/detect.js when this page is
built. A match is a fact about a phrase, not about who wrote the text.
Where this phrase showed up
Did not appear in the licensed samples we checked — no human sample and no AI sample. The rule still matches text that contains its own pattern. The constructed example below is that check.
We are not going to invent an example to fill the gap. What we can show instead is a sentence we wrote ourselves, purely to check that the rule is live.
A constructed example — written by us, not evidence
This sentence was written for this check. It is not from the licensed samples, nobody wrote it as real prose, and it says nothing about how anyone writes. Its only job is to prove the rule still fires, and the generator fails the build if it stops.
“The team wants to leverage the new cutting-edge scheduler.”
-
/\bcutting-edge\b/gi→ “cutting-edge” -
/\bleverage the\b/gi→ “leverage the”
What it means when a person writes this way
This is the label most likely to fire on something a human wrote for money. Product pages, funding applications and conference abstracts are full of both words, and were long before any of this. Whether the licensed samples exercises them at all is printed above.
The patterns, as the engine holds them
2 of the 70 rows in our phrase table carry this label. They are printed here as they are written, because a paraphrase of a regular expression is a different regular expression.
/\bcutting-edge\b/gi weight 2 Matches “cutting-edge” , in any capitalisation .
/\bleverage the\b/gi weight 2 Matches “leverage the” , in any capitalisation .
What a hit does to your score
The phrase model is one of four in our ensemble, and its formula is
patternScore = min(98, max(5, 10 + 7 x total weight)). One
occurrence of the heaviest row in this category takes that model from 10 to
24 out of 100 —
and the pattern model carries 40% of the ensemble when the em-dash signal fires and 55% when it does not.
"leverage the" requires the article, so "leverage existing tooling" does not match. That is narrower than the label name suggests.
Check your own text
Our detector is free and shows you which sentences it flagged and why, including this category. Treat the score as a starting point, not proof.
Other things the detector looks for
- AI vocabulary — 16 patterns
- Formal connector — 4 patterns
- GPT-4 closer — 8 patterns
- GPT-4 sycophant opener — 7 patterns
- GPT-4 labeled output — 4 patterns
- Structural marker — 4 patterns
- All 22 categories