Founder VoicePromptFree
Founder Voice — Long-Form Post
Sound like a founder with opinions. Tight thesis, two stories, one bet.
**Role:** Founder of a Series B SaaS who writes essays that 50,000 people read. You sound like a founder, not a brand — you have opinions, you've been wrong before, and you don't hedge. **Context:** Thesis you want to argue: [the specific claim — 1 sentence]. Why this thesis matters now: [the forcing function]. Two stories you'll tell: [#1 — from your own experience, #2 — from a customer or someone you observed]. **Task:** Write the essay. 1. Hook paragraph (75-100 words): start with a concrete moment, not an abstract claim. The reader should feel they're in a specific place at a specific time. 2. Thesis paragraph (50-75 words): the claim, in plain language. Not academic, not hedged. Make it disagree-able. 3. Story 1 (200-300 words): your own experience that supports the thesis. Specific timeline, specific people (by role if not name), specific quote if any. 4. Story 2 (200-300 words): the customer or observed example. Same specificity bar. 5. Synthesis (150-200 words): what the two stories share. Where they're different. The pattern. 6. One bet (50-75 words): based on this thesis, here's what you're betting on (in your company, in your time, in your money). Make it falsifiable. 7. Close (1-2 sentences): one sentence that calls back the hook image. Earn the ending. **Constraints:** - No three-letter acronyms without first defining - One hedge per essay max - No "I think" / "I believe" — say it directly - The bet must be specific enough that you could be proven wrong within 18 months **Output format:** Markdown essay · 7 paragraphs · ≤1500 words · suitable for Substack/Medium/personal blog.
- Built from
- Role
- Context
- Task
- Constraints
- Output format
How to use it
- Read it, then replace anything in [BRACKETS] with your details — the more concrete the context, the sharper the answer. The Studio lists the blanks for you and can add your project's background.
- Copy it (or download the .md) and paste it into the AI you already use — it knows your work, so that is where the prompt does the most.
- Not sure what it produces? Give it a test run in the Studio first, then refine 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 techniqueChain-of-Thought
Asks the model to reason step by step before answering — ideal for multi-step, logical, or analytical tasks.
Learn this techniqueConstraints
Sets the rules and boundaries — tone, length, what to avoid — that keep the output on-target.
Learn this techniqueWorks with
Any chat AI — ChatGPT, Claude, Gemini, Copilot, Grok, Mistral or a local model. The structure does the work, so you are not tied to one vendor or one model version.
New to structured prompts? Start with how to prompt AI, the RCTCO prompt framework this prompt is built on, and role prompting examples.