What this tool looks for
Text drafted with AI chat tools tends to lean on the same handful of words and phrases. None of them is wrong on its own, but when several appear together, readers increasingly notice. The finder highlights three kinds:
- Overused words like delve, tapestry, seamless, robust, pivotal and testament.
- Stock phrases like in today's fast-paced world, it's important to note, navigate the complexities and I hope this helps.
- Stiff transitions like moreover and furthermore, plus em dashes, both optional.
The count per 1,000 words gives you a quick sense of how heavy the pattern is. A couple of hits in a long piece is normal; several per paragraph is worth a rewrite.
This isn't an AI detector
People used all of these words long before AI chat tools existed, so a highlighted phrase doesn't mean a person didn't write the text, and a clean result doesn't prove they did. AI detectors, such as those used by schools, judge the writing as a whole. Treat this as a style checker that points out tired phrasing, not a verdict.
How to fix flagged phrases
- Cut throat-clearing. "It's important to note that prices rose" says the same as "Prices rose".
- Use the plain word. Use instead of leverage, look at instead of delve into, smooth or nothing instead of seamless.
- Replace generic claims with specifics. A number, a name or an example does more than "a robust solution".
- Vary punctuation. If em dashes pile up, swap some for commas or periods with the em dash remover.