--- title: “Can You Review This Draft I Generated?”: The 60-Second... description: A practical prompt template addresses the growing problem of 'AI slop' — low-quality, unverified AI-generated drafts dumped on coworkers for review. The core... canonical: https://daily.dev/posts/can-you-review-this-draft-i-generated-the-60-second-adversarial-audit-prompt-for-ai-slop-2hcioy4dc twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: “Can You Review This Draft I Generated?”: The 60-Second Adversarial Audit Prompt for AI Slop | daily.dev og:description: A practical prompt template addresses the growing problem of 'AI slop' — low-quality, unverified AI-generated drafts dumped on coworkers for review. The core... og:url: https://daily.dev/posts/can-you-review-this-draft-i-generated-the-60-second-adversarial-audit-prompt-for-ai-slop-2hcioy4dc og:image: https://api.daily.dev/og/posts/2hCIOy4dC.png og:image:alt: “Can You Review This Draft I Generated?”: The 60-Second Adversarial Audit Prompt for AI Slop og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # “Can You Review This Draft I Generated?”: The 60-Second Adversarial Audit Prompt for AI Slop **[Medium](https://daily.dev/sources/medium_js)** · 6 min read · 0 upvotes · 0 comments ## Summary A practical prompt template addresses the growing problem of 'AI slop' — low-quality, unverified AI-generated drafts dumped on coworkers for review. The core insight: default chatbot behavior (RLHF-tuned agreeableness) makes AI a poor critic, so the author provides a copy-paste 'Adversarial Quality Gate' prompt that instructs the model to act as a skeptical auditor, flagging hallucinated facts, empty buzzwords, logical contradictions, and operational gaps. A worked example shows the prompt catching fabricated market statistics and a strategic contradiction in under a minute, plus a diplomatic message template to send back to the original author instead of doing the cleanup work yourself. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How do I get ChatGPT or Claude to give harsh, critical feedback instead of generic praise on a document I paste in? Explicitly instruct the model to act as an uncompromising, skeptical quality inspector rather than asking it to 'review' the document, since models are RLHF-tuned to be agreeable and default to diplomatic praise. Frame the prompt around specific inspection criteria—fabricated facts, empty buzzwords, logical contradictions, and operational gaps—and forbid opening pleasantries or compliments to force direct, critical output. _daily.dev surfaces prompting techniques like this for developers building sharper AI review workflows._ ### What percentage of workers feel overwhelmed by cleaning up AI-generated content from coworkers? 67% of white-collar workers report feeling overwhelmed and drained by having to clean up, verify, and untangle low-quality AI-generated material dumped on them by coworkers and external partners, according to a survey by Adaptavist reported by ITPro. This phenomenon has been termed 'AI slop' and reflects a growing cost-shifting dynamic where quick AI drafting creates disproportionate review burden for others. _track how AI workflow friction like this evolves by following practical AI-usage discussions on daily.dev._ ## Similar posts on daily.dev - [Is This Slop? Detecting AI-Generated Content Without a Model](https://daily.dev/posts/is-this-slop-detecting-ai-generated-content-without-a-model-bn7hlke8u) · Towards Data Science · 1 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#chatgpt](https://daily.dev/tags/chatgpt), [#claude](https://daily.dev/tags/claude), [#prompt-engineering](https://daily.dev/tags/prompt-engineering) [View this post on daily.dev](https://daily.dev/posts/can-you-review-this-draft-i-generated-the-60-second-adversarial-audit-prompt-for-ai-slop-2hcioy4dc) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"“Can You Review This Draft I Generated?”: The 60-Second Adversarial Audit Prompt for AI Slop","url":"https://daily.dev/posts/can-you-review-this-draft-i-generated-the-60-second-adversarial-audit-prompt-for-ai-slop-2hcioy4dc","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/can-you-review-this-draft-i-generated-the-60-second-adversarial-audit-prompt-for-ai-slop-2hcioy4dc"},"datePublished":"2026-08-31T05:32:45.800Z","dateModified":"2026-08-31T05:33:45.560Z","description":"A practical prompt template addresses the growing problem of 'AI slop' — low-quality, unverified AI-generated drafts dumped on coworkers for review. The core...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/311b20c9a1c40cf4fd414091b8e454c6?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/311b20c9a1c40cf4fd414091b8e454c6?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Medium","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Medium","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/medium","url":"https://daily.dev/sources/medium_js"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/can-you-review-this-draft-i-generated-the-60-second-adversarial-audit-prompt-for-ai-slop-2hcioy4dc","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,chatgpt,claude,prompt-engineering","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Medium","item":"https://daily.dev/sources/medium_js"},{"@type":"ListItem","position":3,"name":"“Can You Review This Draft I Generated?”: The 60-Second Adversarial Audit Prompt for AI Slop"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/can-you-review-this-draft-i-generated-the-60-second-adversarial-audit-prompt-for-ai-slop-2hcioy4dc#faq","mainEntity":[{"@type":"Question","name":"How do I get ChatGPT or Claude to give harsh, critical feedback instead of generic praise on a document I paste in?","acceptedAnswer":{"@type":"Answer","text":"Explicitly instruct the model to act as an uncompromising, skeptical quality inspector rather than asking it to 'review' the document, since models are RLHF-tuned to be agreeable and default to diplomatic praise. Frame the prompt around specific inspection criteria—fabricated facts, empty buzzwords, logical contradictions, and operational gaps—and forbid opening pleasantries or compliments to force direct, critical output. daily.dev surfaces prompting techniques like this for developers building sharper AI review workflows."}},{"@type":"Question","name":"What percentage of workers feel overwhelmed by cleaning up AI-generated content from coworkers?","acceptedAnswer":{"@type":"Answer","text":"67% of white-collar workers report feeling overwhelmed and drained by having to clean up, verify, and untangle low-quality AI-generated material dumped on them by coworkers and external partners, according to a survey by Adaptavist reported by ITPro. This phenomenon has been termed 'AI slop' and reflects a growing cost-shifting dynamic where quick AI drafting creates disproportionate review burden for others. track how AI workflow friction like this evolves by following practical AI-usage discussions on daily.dev."}}]} ```