SmartyPress AI Engine Documentation Article

Prompt Variables and Customization

Configure writing tone, style, sections, and create custom variables for AI prompts.

Prompt Variables And Customization is the focus of this documentation page. Configure writing tone, style, sections, and create custom variables for AI prompts. Follow the sections below to configure the feature and use it in your WordPress workflow.

Prompt Variables let you customize AI behavior globally. Define writing tone, style, section structure, and create your own custom variables.

Built-in Variables

Configure in SmartyPress AI → Settings → Available Variables tab:

Setting key Prompt token Default Description
writing_tone {WRITING_TONE} neutral Tone of voice (for example: neutral, formal, casual, friendly, professional)
writing_style {WRITING_STYLE} informative Writing style (for example: informative, descriptive, creative, narrative, persuasive)
number_of_sections {NUMBER_OF_SECTIONS} 3 Number of H2 sections in generated articles. {SECTIONS_COUNT} is an alias for the same value.
paragraphs_per_section {PARAGRAPHS_PER_SECTION} 3 Paragraphs per section
Available Variables tab in SmartyPress AI settings with reusable prompt values
Standard variables cannot be removed; custom ones are added in the row at the bottom.

Custom Variables

You can add your own key-value variables in the settings. Keys are normalized to lowercase snake_case and exposed in prompts as uppercase tokens — for example, a key audience becomes {AUDIENCE}. Standard variables cannot be removed.

Using Variables in Prompts

Variables work in Content Generation prompts, Bulk Generation prompts, plan prompt templates, and Magic Wand custom prompts:

Write a {WRITING_STYLE} article about {TOPIC} in a {WRITING_TONE} tone.
The article should have {NUMBER_OF_SECTIONS} sections with {PARAGRAPHS_PER_SECTION} paragraphs each.
Language: {LANGUAGE}

System Variables

These runtime variables are populated by the plugin during generation (not stored as editable defaults on the Available Variables tab):

Variable Source
{TOPIC} User-entered topic
{TITLE} Generated or current post title
{LANGUAGE} Selected generation language
{CONTEXT} Shared/bulk context, editor context, or related prompt context
{SECTIONS} Generated section headings
{CONTENT} Generated article content
{EXCERPT} Generated excerpt (when provided to the prompt processor)
{SECTIONS_COUNT} Alias of {NUMBER_OF_SECTIONS}
{TEXT} Selected text in Magic Wand / editor rewrite actions
{SELECTED_TEXT} Highlighted text for actions such as Suggest Synonyms

Magic Wand prompt chips commonly expose {TEXT}, {LANGUAGE}, and {CONTEXT}. Bulk Advanced prompts also list {TOPIC}, {TITLE}, {SECTIONS}, {CONTENT}, {WRITING_TONE}, {WRITING_STYLE}, {NUMBER_OF_SECTIONS}, {SECTIONS_COUNT}, and {PARAGRAPHS_PER_SECTION}.

Prompt Variables And Customization Workflow Checklist

The prompt variables and customization workflow should be treated as a repeatable process, not a one-time setting. Start by confirming that the SmartyPress AI Engine module related to this page is enabled, then check the default provider, model, language, and post type settings before you run the feature on production content. This keeps generated output predictable and makes it easier to compare results between OpenAI, DeepSeek, OpenRouter, Yandex GPT, and GigaChat.

Use this checklist whenever you document, test, or train another editor on Prompt Variables and Customization. It helps keep the setup aligned with WordPress permissions, Rank Math SEO fields, and the editorial workflow used by your site. If a result looks different from what you expected, repeat the same checklist with a smaller prompt and a lower temperature before changing global settings.

  1. Confirm that the required SmartyPress AI module is enabled in the Components screen.
  2. Open Settings and verify that the selected provider has a valid API key and a tested connection.
  3. Choose the model that fits the task: fast models for drafts, premium models for final marketing copy, and web-search models for research.
  4. Review the output language, temperature, max tokens, and prompt variables before generating content.
  5. Save the result as a draft first, then review headings, links, facts, and SEO fields before publishing.

Recommended Settings

For most prompt variables and customization tasks, start with a balanced model such as GPT-4o Mini, GPT-4o, DeepSeek Chat, or a carefully selected OpenRouter model. Keep temperature around 0.5 to 0.8 for documentation and tutorials, because these pages need clarity more than experimentation. Increase temperature only when you need more creative headlines, introductions, or alternative wording.

Use a clear default language and keep prompt variables consistent across articles. For documentation pages, a neutral or professional writing tone usually works best. If the generated result is too short, increase the number of sections or paragraphs per section rather than asking the model to “write more” after the fact. Structured settings create more stable output and make Prompt Variables and Customization easier to reproduce later.

Scroll to Top