Writing5.0 · 134 ratings

Thought Leadership — Contrarian Take

Argue a contrarian position credibly. Steelman opposition, then dismantle.

Role-BasedChain-of-ThoughtConstraints

Prompt

**Role:** Thought-leadership writer who has had 20+ pieces go viral by arguing positions other people are afraid to argue. You know that contrarianism without rigor is just edgelording.

**Context:** Your contrarian thesis: [the position most people in your field disagree with]. The current consensus: [what most people say]. Why people might be wrong about consensus: [your evidence]. The strongest argument FOR consensus: [the steelman you'll need to address].

**Task:** Write the essay.

1. Opening (75-100 words): a specific scene or moment that contradicts consensus. Concrete, observed.
2. The consensus, steelmanned (200-250 words): present the OPPOSITE view as charitably as possible. Quote its strongest proponents. Acknowledge what they get right.
3. Your thesis (50-75 words): plain language. Disagree-able. The specific claim.
4. The evidence (300-400 words): 3 specific data points / case studies / observations that support your thesis. Each one is concrete. Each one is something the consensus doesn't have a great answer for.
5. The remaining doubt (100 words): be honest about what could prove you wrong. What evidence would change your mind?
6. The implication (100 words): if you're right, what changes? What action does someone take this week?

**Constraints:**
- The steelman is REAL — not a strawman dressed in steel
- Every claim has a citation, a number, or an observed example
- The "what would change my mind" section must name specific evidence
- No clickbait headlines — argue the position, don't sensationalize
- ≤1500 words

**Output format:** Essay · 6 sections · ≤1500 words · suitable for personal blog, Substack, or LinkedIn long-form.

How to use this prompt

  1. 1

    Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.

  2. 2

    Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.

  3. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

Role-Based

Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.

Learn this technique
Chain-of-Thought

Asks the model to reason step by step before answering — ideal for multi-step, logical, or analytical tasks.

Learn this technique
Constraints

Sets the rules and boundaries — tone, length, what to avoid — that keep the output on-target.

Learn this technique

Recommended models

claudegpt-4o

Build on this prompt

Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.

More in Writing