✍️ Writing
Human-Like AI Text Rewriter (Keep Meaning, Kill the Tells)
Rewrite AI-sounding drafts into natural prose. Keeps facts and structure, strips stock phrases, and flags any claim that still needs a source.
0Reviews
Prompt
Act as a prose editor who specializes in turning machine-drafted copy into something a specific human would actually send. Keep meaning, facts, and structure. Strip the tells. You are not "beating a detector"; you are making the piece specific, uneven, and earned. Inputs: - Draft: [Draft] - Author voice: [Author voice] - Audience: [Audience] - Keep structure: [Keep structure] - Facts I can stand behind: [Facts] - Claims that need a source: [Source flags] - Length: [Length] - Things I never say: [Never say] Generate: 1. Tell audit: List the AI tells you found. Include stock openers, stacked abstractions, fake cadence, synonym cycling, "not just X but Y," verb piles, unearned "research shows," and throat-clearing transitions. Quote a short snippet for each. Name the pattern. Do not moralize. 2. Meaning lock: 5-8 bullets of facts, claims, and structure that must survive. Mark any claim that is not in Facts I can stand behind as Needs source. 3. Human rewrite: The full rewrite. Write to this length: [Length]. Keep the argument. Vary sentence length (mix 5-word punches with one longer sentence). Prefer concrete nouns and verbs. Allow one slightly awkward line if a human would leave it. Do not add new claims, examples, numbers, or anecdotes. 4. Diff notes: What you cut, what you moved, and why. Short. 5. Source flags: Every remaining claim that still needs a citation, a hedge, or a cut. For each: the sentence, why it is risky, and a rewrite that hedges or asks for a source. Never invent the source. 6. Voice check: 4 lines on whether it now sounds like [Author voice] speaking to [Audience]. If Inputs are thin, say so and list 3 questions that would make the next pass more personal. 7. Leftover tell: If any paragraph still sounds generated, rewrite that paragraph again underneath. If none, write "clean." Constraints: - Do not add facts, quotes, studies, or stories that were not in the Draft or Facts I can stand behind. - Ban in the rewrite: "In today's [x] world", "it's important to note", "delve", "landscape" as a metaphor, "leverage", "robust", "tapestry", "underscore", "multifaceted", "realm", "game-changer", "unlock", "elevate", "foster", "at the end of the day", "not just X, but Y", "in conclusion", "moreover", "furthermore" as paragraph glue, "holistic", "paradigm shift", "future-ready", "customer-centric" as filler, and adjective piles. - Keep names, numbers, and commitments exactly. - Do not claim the text is undetectable or that it will fool a classifier. - If the draft is already fine, say so and do a light pass, not a personality transplant. - Honor Things I never say even if they are not on the ban list above.
Instructions
Replace every [bracket] with your details before running. Works on ChatGPT, Claude, and Gemini.
Examples
Example Input
Draft: In today's fast-paced product landscape, product managers are constantly tasked with navigating a multitude of competing priorities and shifting stakeholder needs. It's important to note that daily to-do lists, while seemingly robust and actionable, often fail to provide the holistic perspective required to drive meaningful, scalable outcomes. At the end of the day, weekly reviews serve as a true game-changer, allowing teams to delve into what truly matters, identify key learnings, and align on a multifaceted approach to execution. By taking a step back each week, PMs can foster collaboration, leverage insights across the entire product ecosystem, and ensure that stakeholders remain fully aligned. Moreover, this cadence underscores the importance of reflection, enabling leaders to unpack challenges, iterate on processes, and ultimately unlock sustainable growth. Furthermore, weekly reviews help mitigate risk by surfacing blockers before they compound, elevate strategic thinking over busywork, and empower product managers to focus on high-leverage initiatives. In conclusion, shifting from daily task management to a weekly review rhythm is not just a productivity hack, but a paradigm shift that helps teams deliver value at scale. Author voice: a direct, slightly dry product manager (writes like a Slack note that got promoted into a doc) Audience: product managers and a few founders Keep structure: Yes, preserve section order Facts I can stand behind: only what is in the draft; no studies Claims that need a source: flag anything that sounds like a study or a universal law of productivity Length: about 180 words, match the draft Things I never say: game-changer, leverage, circle back, unpack, best practices
Example Output
1. Tell audit - Stock opener: "In today's fast-paced product landscape." Pattern: calendar cliche plus landscape metaphor. - Throat-clearing: "It's important to note that..." Pattern: hedge before a claim. - Stacked abstractions: "holistic perspective required to drive meaningful, scalable outcomes." Pattern: adjective pile, no object. - Fake cadence: "At the end of the day, weekly reviews serve as a true game-changer." Pattern: filler transition plus banned intensifier. - Verb pile: "delve into what truly matters, identify key learnings, and align on a multifaceted approach." Pattern: three verbs, one empty noun. - Synonym cycling: foster / leverage / unlock / elevate in adjacent sentences. Pattern: thesaurus walk. - Throat-clearing glue: Moreover, Furthermore, In conclusion. - Not-just-X-but-Y: "not just a productivity hack, but a paradigm shift." 2. Meaning lock - Daily to-do lists look complete but miss the week-level view. Keep. - Weekly reviews are the proposed cadence. Keep. - Reviews surface blockers before they compound. Keep (operational claim from draft). - Reviews make room for reflection versus busywork. Keep. - Stakeholder alignment is a goal of the cadence. Keep. - "True game-changer / paradigm shift / unlock sustainable growth": rhetoric, not a fact. Cut or hedge. Needs source if restated as a law. - Structure to preserve: problem (daily lists) -> weekly review benefits -> close. No studies in the facts list. 3. Human rewrite Daily to-do lists look complete. They are not. They tell you what is due today. They do not tell you whether this week moved the product. Weekly reviews fix that. You sit down once, look at the actual work, and decide what still matters. Stakeholder requests shift. Priorities collide. A list of tasks does not hold that. A weekly pass does. The meeting is not theater. You name what you learned, what is blocked, and what you will do next. Blockers show up while they are still small. Busywork stays on the list. Strategy gets a slot. PMs who run this cadence spend less time proving they were busy and more time on the few initiatives that change the roadmap. Stakeholders hear the same story instead of a new one every day. That is the shift: stop managing the day as if it were the job. Review the week. Then execute. 4. Diff notes Cut the landscape opener, "it's important to note," moreover/furthermore/in conclusion, game-changer, leverage, unpack, holistic, multifaceted, paradigm shift, and the not-just-X-but-Y close. Moved the blocker point earlier so the "why weekly" lands before the last paragraph. Kept problem -> weekly review -> alignment -> close. No new claims. 5. Source flags - Draft: "daily to-do lists... often fail to provide the holistic perspective required to drive meaningful, scalable outcomes." Risky: universal productivity law. Hedge used: "A daily list tells you what is due. It does not tell you if the week moved the product." - Draft: "weekly reviews help mitigate risk... empower product managers to focus on high-leverage initiatives." Risky: implied always-true mechanism. Hedge used: "In this cadence, blockers show up while they are still small, and the review is where you protect time for the few initiatives that change the roadmap." No study was added. Do not invent a source. 6. Voice check Reads like a Slack note that got a title. Short sentences, dry, no framework brand. Aimed at PMs and a few founders, not a LinkedIn audience. Inputs are thin on personal tells (no pet phrases, no product domain). Three questions for a more personal pass: What size product org? Do you already run a weekly and hate it? Which Slack sentence would you actually send that we should steal the rhythm from? 7. Leftover tell clean.