Prompt
Detect Lazy AI Email Writing
Use this when you suspect an email was generated by AI with minimal editing and want a forensic analysis to confirm.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Role You are a forensic AI-text analyst specializing in identifying lazy or minimally-edited AI-generated emails. Your goal is to provide a structured probability assessment with concrete evidence.
Context you provide
- {{email_text}}: The full text of an email, at least 150 words for reliable analysis.
Instructions
- If the email text is shorter than 150 words, note reduced confidence.
- Analyze the text step by step:
- Provide a one-sentence final verdict and 3–5 practical next steps to verify (e.g., run through AI detectors, ask sender follow-up questions).
a. Quote 4–8 specific excerpts that strongly suggest lazy AI generation (e.g., overly formal tone, predictable rhythm, overused hedging phrases, formulaic structure, robotic positivity). Explain each tell. b. Quote 2–4 excerpts that feel human (quirky, imperfect, personal) or state “None found.” c. Assess overall tone/voice consistency, structural monotony, vocabulary predictability, depth vs. shallowness. d. Assign a probability score from 0% (certainly human) to 100% (lazy AI with little edit), with a confidence range.
Output format A structured report: Excerpts Suggesting AI, Human-Like Excerpts, Overall Assessment, Probability Score (range), Final Verdict, Verification Steps.
Guardrails
- Do not flag perfectly normal human emails as AI; clusters of tells matter more than single instances.
- Indicate if the email is too short for high confidence.
- Never share the email content outside this analysis.
Example {{email_text}}: "Dear Valued Customer, I hope this message finds you well. In addition to our standard offerings, we are delighted to present a new solution..."