Prompting Craft
Get better first drafts from AI.
One sentence at the top of any prompt naming the audience changes the voice of an AI draft more than any other move. Two minutes on the single most-cited principle in the prompt-engineering literature, applied to your work.
No credit card required. Cancel anytime.
Why not buy an AI writing tool?
Jasper, Copy.ai, Writer, and a dozen other paid AI-writing tools sell themselves on producing better drafts than a generic ChatGPT prompt. They’re right. They often do, because they bake in audience and style controls behind the scenes. Their wrappers do the work this trail teaches you to do directly.
The wrapper costs $39 to $129 per month, per seat. The move it’s wrapping is one sentence: name the reader, name one fact about how they read.
For example: "It is for my manager Sarah, who reads on her phone and hates filler." Or "It is for our newsletter list, mostly designers, mostly skimming." Or "It is for me alone, journaling, no audience." The draft shifts to fit. Same outcome as a paid AI-writing wrapper. No second subscription on top of the AI you already pay for.
Questions
- Is my data private?
- Yes. Your prompts and AI responses are deletable, exportable, and only visible to you. We never expose individual prompts to admins, teammates, or Joring employees.
- What if the reader is me (e.g., journaling)?
- "It is for me alone, journaling, no audience, tone honest" is a perfectly good reader sentence. The model still uses it to shift voice (toward direct, lowercase, no-filler) instead of writing the careful neutral prose it defaults to.
- Do I need to add this to every prompt?
- Only when the output is something you’d actually send or publish. For exploratory questions ("explain X to me"), the reader is implicitly you and the model already does well. For drafts that go somewhere, naming the reader is the highest-leverage sentence in the prompt.
- Does this work in ChatGPT, Claude, and Gemini?
- Yes, equally well. All three modern LLMs respond strongly to audience context. It’s the most consistent prompt-engineering finding across providers.
- How is this different from telling AI to be "professional" or "friendly"?
- Adjectives like "professional" or "friendly" mean very different things to different audiences. And the model averages across all those meanings. Naming the actual reader collapses the ambiguity. "For Sarah, who hates filler" is more specific than "professional" and produces a better draft.
- What happens after the 14-day trial?
- Continue on Pro to keep real-time coaching, guided trails, and your exportable AI record. Or stay on Free with limited features. The trail progress you’ve already made doesn’t disappear.
Get drafts that sound written for someone, not averaged.
No credit card required. Cancel anytime.