ThinkWithPrompt by SynotticThinkWithPrompt

Check my message for anything that could be misunderstood

Stress-tests a draft before you send it: ambiguous phrases, tone risks, and the questions readers will come back with.

Email & Workplace CommunicationFew-ShotStandardCommunicationAnalyzeFill-in Template

The prompt

Review my message before I send it and find anything that could be misunderstood or prompt follow-up questions. My message: [PASTE] Readers: [WHO - roles, seniority, how familiar they are with the topic, native language if relevant] What I want them to understand or do: [GOAL] Sensitivities: [e.g. "reorg rumors", "recent missed deadline", "new manager"] Check for: 1. Ambiguity - words or sentences with two reasonable readings (e.g. "next Friday", "we", "soon", "the issue", "should"). 2. Missing context - things I know that the reader doesn't. 3. Tone risks - phrases that could read as blunt, passive-aggressive, alarming, or dismissive, especially in writing without facial cues. 4. Hidden implications - what a nervous or skeptical reader might infer (e.g. job security, blame, a change being final). 5. Likely questions - the 3 to 6 questions readers will ask after reading, in order of likelihood. Return a table: | Phrase or issue | How it could be read | Risk (High/Med/Low) | Suggested fix | Then: - Answers to the likely questions that I could add to the message, or prepare for, using only the information I've given; mark gaps [ADD]. - A revised version with the high-risk fixes applied. Keep my meaning and voice; flag rather than change anything that alters my intent.

Highlighted [brackets] are blanks to replace with your own details.

Fill in the blanks and use this promptMore Email & Workplace Communication prompts

What to fill in

  • PASTE
  • GOAL
  • e.g. "reorg rumors", "recent missed deadline", "new manager"
  • ADD

How this prompt is built

This prompt follows the Few-Shot structure (Few-shot prompting). A few-shot prompt includes one or more worked examples of the input and the output you want, so the model can copy the pattern instead of guessing it.

Related prompts

Find more prompts like this