AI Prompting Formula
The prompt structure that produces consistent, high-quality output from any modern AI.
By James Schramko · Updated April 2026.
Background
I saw an Anthropic prompt engineer present this formula in a session on prompting Claude. It is the structure they recommend when you want consistent, high-quality output from any modern LLM. The order matters. The components matter. I have used it across content, sales, and operator decisions and the difference in output quality is real.
This replaces the earlier RICESFQ playbook. The components are the same in spirit, the structure is sharper, and the Q step (questions) stays as a James addition because it earns its place.
Why It Matters
The model performs best when the prompt is built top-down: who it is, how to sound, what materials to use, what rules apply, what good looks like, what was said before, what you want right now, how to think, how to format, and how to start the reply.
Skip a layer and the output drifts. Reorder the layers and the output drifts. The order is the discipline.
The Formula
Use these in this order, top to bottom, in your prompt.
1. Task context
Tell the model who it is and what it is doing in general. Role plus broad domain.
Example: "You are a content editor working with small business owners on plain-English copy."
2. Tone context
Voice, register, audience. Sets the personality of the reply.
Example: "Direct, confessional, no hype. Short sentences. Treat the reader as an experienced operator."
3. Background data, documents, and images
The reference material the model should use as source. Paste it here, before the rules and the request.
Example: "[paste source brief, transcript, or document]."
4. Detailed task description and rules
The specific constraints. What to do, what not to do. Rules go here, not at the end.
Example: "Simplify the paragraph without changing meaning. Keep all numbers, names, and claims exactly as written. Do not add new ideas. No em dashes."
5. Examples
Show, do not only tell. One or two strong examples beat a paragraph of description.
Example: "[paste a paragraph in the target style that has worked before]."
6. Conversation history
Prior turns or carry-over context. If the prompt depends on what was discussed earlier, paste it here. If not, write "none" so the model knows.
7. Immediate task description or request
The specific ask, restated after all the context. This is what you want the model to do right now.
Example: "Rewrite the paragraph above in the target style."
8. Thinking step by step
Tell the model to reason before answering. Catches obvious errors and improves quality on anything that needs analysis.
Example: "Before you rewrite, think through which sentences carry the meaning and which carry filler."
9. Output formatting
How to deliver the answer. Length, structure, what to include and exclude.
Example: "Return only the rewritten paragraph. No commentary. No headings."
10. Prefilled response (optional)
This is an API-level technique. You pre-seed the start of the assistant's reply so it commits to a specific opening. Useful when you want to lock the format. Less applicable in a consumer chat interface where the model replies from scratch.
Example (in API): start the assistant turn with "Here is the rewritten paragraph:" so the model continues from there instead of preambling.
11. Questions (James addition, not Anthropic)
Invite the model to ask before it produces the final output. Catches ambiguity and missing context.
Example: "If anything in the brief is missing or unclear, ask before producing the rewrite."
How to Use the Formula
- Use it top to bottom. Order is the discipline.
- One task per prompt. If you have two unrelated jobs, write two prompts.
- Reference material goes early (step 3), not at the end.
- Rules go before the request (step 4 before step 7), not after.
- The thinking step (step 8) is cheap and almost always improves output. Use it on anything that involves reasoning.
- The Q step (step 11) is most useful when the brief is ambiguous or you are testing whether the model has enough to work with.
For everyday quick prompts, you do not need all 11 components. Use a short subset, in the same order. The discipline is the order, not the completeness.
Best Practices
- Use verified, high-quality source material.
- Never upload private or client data to a public AI platform.
- Save successful prompts for reuse and versioning.
- Always verify facts before publishing or distributing AI-assisted content.
- Treat outputs as drafts. Human oversight is required.
Worked Example
```
Task context: you are a content editor working with a small-business owner.
Tone context: plain English, short sentences, grade 6 readability.
Background data: [paste source text].
Detailed task description and rules:
- Simplify the paragraph without changing meaning.
- Keep all numbers, names, and claims exactly as written.
- Do not add new ideas.
- No em dashes.
Examples: [paste a paragraph in the target style].
Conversation history: none.
Immediate task: rewrite the paragraph above in the target style.
Thinking step: before you rewrite, think through which sentences carry the meaning and which carry filler.
Output formatting: return only the rewritten paragraph. No commentary. No headings.
Prefilled response: Here is the rewritten paragraph:
Questions: if anything in the brief is missing or unclear, ask before producing the rewrite.
```
The prefilled response line in the example above only applies in API or agent builds. In a chat interface, omit it.
Platform Flexibility
The formula works on Claude (where it was developed), and on any other competent LLM. The order and the components are the same regardless of platform. Some platforms expose the prefilled response slot directly (API). Others do not (most chat interfaces).
Responsible AI Use
Treat outputs as drafts that require human oversight. Maintain privacy, verify data accuracy, and keep training materials and client data inside your own workspace.
By using this formula in order, you get precise, consistent results from any AI tool while keeping data and workflow integrity intact.