8 ready-made prompts
AI Auditing
Verify what AI produced: fabricated sources, plagiarism risk, AI writing tells, misread tables and skewed numbers.
Before publishing a text, the question is not "is it good" but "can it be falsified". This category reads AI output the way a prosecutor would: it separates every claim, verifies each source individually, and flags the AI smell and the plagiarism risk in the text.
Prompt to Catch Fake Citations: When the AI Invents Sources
Tests every source on four axes (does it exist, does it support the claim, is the metadata consistent, is it accessible) and surfaces the suspect ones first.
Intermediate ChatGPTClaudeAI Plagiarism Check: Rank Your Text by Risk Before Submission
Scans definition sentences, opening paragraphs and conclusions separately, then gives a source type and a rewrite direction for each risky sentence.
Advanced ChatGPTClaudePrompt to Make AI Text Sound Human (Remove the Tells)
Finds the clearest AI tells — rule-of-three balance, empty adjectives, cliché openers, connective overload — and rewrites around them without losing meaning.
Intermediate ChatGPTClaudePrompt to Remove Translationese From AI Output
Splits long sentences, turns passive into active, clears pronoun clutter and rebuilds the rhythm. For marketing and SEO copy.
Intermediate ChatGPTClaudeAI Misreading Your Table? Prompt for Source-Traced Numbers
Requires row and column coordinates, unit and period for every number, and marks anything unreadable as "uncertain". Essential for financial analysis.
Advanced ChatGPTClaudePrompt Injection Check: Find Hidden Instructions in Files and Pages
Detects instructions buried in documents — white text, hidden layers, HTML comments — and clears them before summarising.
Advanced ChatGPTClaudeAI-Written CV: The Tells Recruiters Spot in 8 Seconds
Flags vague claims, inflated verbs and copy-paste sections, then replaces each line with a measurable result.
Beginner ChatGPTClaudePrompt for Thesis Similarity Check
Similarity reports rarely flag copied ideas — they flag stock academic phrasing. This prompt names those patterns, scores each paragraph and tells you exactly what to change rather than "rewrite this".
AdvancedFrequently asked
About AI Auditing
Can I trust "AI detectors"?
Not on their own, and that is a real risk: they produce false positives, especially for non-native writers. In academic and publishing settings, keep a draft history proving you actually wrote the text before you submit. These prompts are written to find concrete evidence in the text — stock phrasing, over-balanced structure, unsourced certainty — rather than to replace a detector.
What is the fastest way to catch a fabricated source?
Open every DOI and URL one by one; roughly 10-20% either do not exist or resolve to a different paper. Asking the model to "verify these sources" does not work — the same model defends the same fabrication. Verification always happens in a browser, on the source itself. The prompt only gives you the order to check them in.
Why does AI increase plagiarism risk?
The model regenerates the most common sentence patterns in its training data, and those patterns are often near-verbatim copies of existing texts. Definition sentences, opening paragraphs and summary sections are the riskiest. The prompt flags those sections separately so you know which sentences need rewriting.
Other categories