ThinkWithPrompt by SynotticThinkWithPrompt

Build habits for using AI to sharpen my thinking, not replace it

Reviews how you use AI at work and builds practical habits so AI improves your reasoning instead of just speeding up answers.

Working with AIFew-ShotStandardProductivityWriteRewrite & EditFill-in Template

The prompt

Help me use AI to think better, not just to get answers faster. My role and the kind of thinking my job needs: [e.g. "product manager - prioritizing, judging trade-offs, persuading stakeholders"] How I use AI now: [TYPICAL TASKS and how I prompt - e.g. "I ask for a first draft and lightly edit it"] Where I worry I am relying on it too much: [e.g. "I no longer write first drafts myself", "I accept summaries without reading the source"] Skills I want to keep or build: [e.g. "analysis", "writing", "judgment"] Return: 1. Honest diagnosis - where my current use is outsourcing thinking rather than improving it, and the skills at risk. 2. Think-first habits - 5-7 concrete habits, each with when to use it and an example prompt. Include: writing my own view before asking AI; asking AI to question me rather than answer; asking for counterarguments and missing perspectives; making AI show its assumptions; comparing AI's answer with mine and explaining the difference; checking claims against sources. 3. When fast answers are fine - the routine tasks where speed is the right goal. 4. Weekly practice - a 15-minute routine to keep my own skills sharp. 5. Warning signs - signals that I am becoming over-reliant or overconfident in AI output. Keep it practical and specific to my role. No generic advice about AI being a tool.

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

Fill in the blanks and use this promptMore Working with AI prompts

What to fill in

  • e.g. "analysis", "writing", "judgment"

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