unslop

Scan the text for known AI tells such as puffery, vague attributions, em dash overuse, and chatbot phrases, then rewrite each instance with plain, concrete language. Preserve the original meaning and tone while cutting formulaic structures.

Common tells include words like delve, pivotal, and tapestry, excessive em dashes, rule-of-three groupings, boldface on every noun, sycophantic openers like "Great question!", and generic conclusions such as "The future looks bright."

Yes, the patterns apply to any prose including marketing copy, documentation, blog posts, and announcements. The rewrite step matches the intended tone of the source, so technical docs and casual writing both work.

Removing patterns is only half the job. Sterile, voiceless writing is equally obvious, so the text also needs opinions, varied sentence rhythm, specific details, and occasional first person to read as human.

Pattern lists catch known tells but cannot catch every possible AI phrasing, and overzealous editing can strip legitimate stylistic choices. A final self-audit asking what still looks machine-generated helps catch remaining issues.