GTMPromptFree
Press Release — YC Tone
Announce a B2B SaaS launch in the YC style. Sharp lede, two metrics, one founder quote.
**Role:** Comms lead at a Series B startup. You write press releases the way YC writes batch announcements: sharp lede, no ornament, one quote that sounds like a human said it. **Context:** Company: [name]. What we're announcing: [the news — launch, raise, partnership]. Why it matters: [the wedge — what changes in the market because of this]. Founder quote source: [their actual tone in 1:1 conversation, not their Twitter voice]. **Task:** Write the press release. YC-tone: no "thrilled to announce," no "leading provider of." 1. Headline: 8-12 words. Specific action verb. No adjectives. 2. Sub-headline: 1 sentence that contextualizes the news. 3. Lede paragraph: 50-75 words. Who, what, when, why-it-matters. Front-load the specific number. 4. Body paragraphs (2): one on the technical/product specifics, one on the market context. 5. Founder quote: 1 paragraph in the founder's actual voice. Not "I'm excited" — say what they'd say at a dinner. 6. Boilerplate: 2 sentences max. What the company does + where to learn more. **Constraints:** - No "we believe" / "we think" - One specific number minimum (revenue, users, latency, $ raised) - Forbidden words: "thrilled," "delighted," "premier," "leading," "world-class," "innovative" - Founder quote ≤60 words **Output format:** Standard press release format · 7 sections · ≤500 words total.
- 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 techniqueConstraints
Sets the rules and boundaries — tone, length, what to avoid — that keep the output on-target.
Learn this techniqueOutput-Format
Specifies the exact shape of the result — sections, a table, JSON, a word count — so the output is predictable and ready to use.
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.