ChatGPTCreativeWritingAI score · PendingAI-assisted edit · no obvious prompt-injection riskn8n.io

Generate SEO-Optimized WordPress Content with Perplexity Research

Input research topic → Perplexity research + AI writing → Output formatted WordPress draft with Telegram notification

Some experienceStepsWorkflowPromptTip
Who
Content creators, marketers, and WordPress site owners who need to publish SEO blog posts at scale
You get
Submit a research query and automatically receive a WordPress draft with title, slug, meta description, HTML body, and featured image, plus a Telegram completion notification
You need
n8n · wordpress · perplexity · telegram

Constraints

Import the template into n8n, configure four credential types (WordPress, OpenAI, Perplexity AI, Telegram), submit a research topic via the form trigger, and let the workflow run research, writing, formatting, publishing, and notification automatically. Replace hardcoded WordPress site URL and image URL before use.

What they did

Template author Joseph LePage created an n8n workflow template chaining a form trigger, Perplexity AI research, OpenAI content generation, WordPress publishing, and Telegram notification into an automated blog production pipeline. Published in the n8n.io template library as ID 3291.

How it went

The template has 73,985 views on n8n.io (author_report). No runtime success rate, generation quality assessment, or ROI data is provided by the source.

Worth knowing

1. Prompts hardcode a Canadian AI consulting company persona (SocialFind, recruitment/HR keywords) and must be rewritten for your business; 2. WordPress site and image URLs are example hardcodes—publishing without replacement targets the wrong site or uses irrelevant images; 3. Perplexity node uses httpHeaderAuth credential type; confirm API Key format is Bearer Token; 4. Author ID is fixed to 2; match to your WordPress site's actual user; 5. This site has not tested this workflow, reproduction=not_tested

n8n workflow template

Structure checked · Not run-tested

Use “Import from File” in n8n, or copy the JSON and paste it into the editor. Connect your own accounts, then try test data. The template is inactive by default.

Setup and test checklist

Credentials to connect

  • Wordpress node: connect wordpressApi credentials.
  • OpenAI Chat Model node: connect OpenAI API credentials.
  • Create HTML node: connect OpenAI API credentials.
  • Upload Image to Wordpress node: connect wordpressApi credentials.
  • Set Image on Wordpress Post node: connect wordpressApi credentials.
  • Perplexity Research node: connect HTTP Header Auth credentials.
  • Send Success Message to Telegram node: connect Telegram API credentials.
  • gpt-4o-mini node: connect OpenAI API credentials.

Configuration to replace

  • Source template is n8n public workflow #3291 (~25 nodes). Keep inactive after import; verify triggers, expressions and external API endpoints.
  • Sticky-note guidance is informational; replace placeholders with your own accounts, sheet schemas or channel IDs.

Test input and expected output

  • Manually run the main path once in a test workspace and confirm credentialed nodes authenticate without errors.
  • Drive one synthetic/redacted sample through and check output fields and downstream writes before enabling in production.

Template changes

  • Author credential bindings, webhookId and execution data are removed; the workflow is inactive. Nodes, connections and original prompts are preserved. Not run-tested in n8n.
  • No business-logic edits; verify keys, quotas and privacy compliance before use.

Template retrieved: 2026-10-25

Steps

  1. Submit research topic via form trigger

    Enable the 'On form submission' node in n8n, visit the form URL, and enter your research topic in the 'Research Query' field (required textarea).

  2. Perplexity AI conducts research

    The workflow automatically calls the Perplexity AI API (model: sonar-pro) to search and return detailed summaries with source citations. Configure httpHeaderAuth credentials with your Perplexity API Key.

    Execution prompt · Source text。Perplexity Research node system message

    Act as a professional news researcher who is capable of finding detailed summaries about a news topic from highly reputable sources.

    Execution prompt · Source text。Perplexity Research node user message

    Research the following topic and return everything you can find about: '{{ $json['Research Query'] }}'.
  3. Clean up citation links

    A Set node replaces Perplexity citation markers [1]-[10] with full source URLs, producing annotated research text for the writing node.

  4. AI copywriter generates blog body

    The Copywriter AI Agent node (connected to gpt-4o-mini) drafts a 1500-2000 word SEO blog post based on the research and query. The prompt presets a Canadian AI consulting company persona—modify for your business.

    Execution prompt · Source text。Copywriter AI Agent node text parameter (promptType=define)

    =You are part of a marketing team that creates high-quality blog posts for the AI consulting and workflow automation industry based in Canada. Your goal is to produce engaging, SEO-optimized content that positions the company as an authority in the AI consulting industry and attracts inbound leads.
    
    Every 2 days, your team posts a blog on the most trending topics in AI consulting and n8n workflows. As the copywriter, you are provided with the following information:
    
    - Query: The main topic for this week's blog post, representing the most trending news in the recruitment space.
    
    - Other keywords: A list of high-search-volume keywords related to AI consulting and n8n workflows. Incorporate these naturally into the blog post where relevant, without forcing them or changing the post's meaning.
    
    - Research findings: Detailed information from reputable sources related to the blog topic. Your post must be based on this research.
    
    Given this information, write a comprehensive blog post that:
    
    - Includes the query in the blog title, H2 header, and early in the introduction.
    - Incorporates all details from the research findings, including source URLs for potential hyperlinks.
    - Is detailed and informative, showcasing the companies expertise in AI consulting and n8n workflows to automate business processes.
    - Uses a professional yet engaging tone, highlighting the exciting developments and challenges in the recruitment industry.
    - Flows naturally and logically, making it easy for readers to follow.
    - Is between 1500 to 2000 words long.
    - Is written at a level accessible to HR professionals and business leaders.
    
    Additional requirements:
    - Include practical takeaways or actionable advice for recruiters and HR professionals.
    - Highlight how the topic relates to the companies services or expertise.
    - Include a call-to-action (CTA) that encourages readers to explore the comapnies services or contact for more information.
    
    Create the entire blog post draft in your first output. Don't stop or cut it short.
    
    Your output must be the blog post and nothing else.
    
    Here are the details of this blog post project:
    
    Query:
    {{ $('On form submission').item.json['Research Query'] }}
    
    Detailed Research:
    {{ $('Cleanup Links').item.json.research }}
  5. Generate WordPress-compatible HTML

    The Create HTML node (OpenAI, gpt-4o-mini) converts the blog body into WordPress-compatible HTML with reading time, key takeaways, table of contents, body content, and FAQ, applying specified styles (blue links #00c2ff, heading borders, etc.).

    Execution prompt · Source text。Create HTML node messages.values[0].content

    =Only output the HTML content without preamble or further explanation. Generate WordPress-compatible HTML for a blog post based on the provided content.
    
    ### CONTENT PROCESSING:
    - Process all content from {{ $json.output }}
    - Preserve all original facts, information, and URLs
    - Format according to the specifications below
    
    ### REQUIRED STRUCTURE (IN THIS ORDER):
    1. Title (H2)
    2. Estimated reading time
    3. Key takeaways (3-5 bullet points)
    4. Table of contents (linked to all headings)
    5. Main content (with proper heading hierarchy)
    6. FAQ section
    
    ### STYLING REQUIREMENTS:
    - Style Override: Include a style section with !important declarations
    - Links: All hyperlinks, TOC items, and FAQ questions must be #00c2ff (blue)
    - Headings: All headings need a bottom border in #00c2ff with padding
    - Spacing: Add <br><br> between each major section
    
    ### ENGAGEMENT FORMATTING:
    - Use bold, italics, bullet points, quotes, and highlighting for emphasis
    - Create proper paragraph structure with appropriate line breaks
    - NO emojis allowed
    - Use whitespace strategically for readability
    
    ### HYPERLINK HANDLING (CRITICAL):
    - When URLs appear next to keyphrases (e.g., "AI tools (https://example.com)")
    - Convert to: <a href="https://example.com" style="color: #00c2ff !important;">AI tools</a>
    - The KEYPHRASE must be linked, never the URL itself
    
    ### WORDPRESS COMPATIBILITY:
    - Use WordPress block classes (wp-block-heading, wp-block-paragraph, etc.)
    - Add heading IDs starting with "h-" for better TOC linking
    - Ensure all styles use !important to override theme styles
    
    DO NOT include any explanations, code tags, or comments. Output ONLY the raw HTML.
  6. Generate title, slug, and meta description

    The Create Title, Slug, Meta node (AI Agent with gpt-4o-mini and Structured Output Parser) generates SEO-friendly title, URL slug, and meta description from the blog content, outputting JSON. The prompt's keyword direction (recruitment/HR) must be adapted to your industry.

    Execution prompt · Source text。Create Title, Slug, Meta node text parameter

    =**Create a slug, blog post title, and meta description for the following blog post:**
    
    {{ $json.output }}
    
    **Slug Guidelines:**
    - Keep it concise (4-5 words maximum).
    - Include the primary keyword related to recruitment or HR.
    - Use hyphens to separate words.
    - Avoid unnecessary words, articles, or prepositions.
    - Ensure it reflects the main topic of the blog post.
    - Make it readable and relevant for both users and search engines.
    
    **Title Guidelines:**
    - Avoid AI words like "Transform" or "Revolutionize" and similar overused terms.
    - Avoid using a colon (:) in the title.
    - Never structure it as a primary/secondary title separated by a colon.
    - Include the primary keyword related to recruitment or HR (e.g., 'AI in recruitment' or 'talent acquisition trends').
    - Clearly inform users what they can expect from reading the blog post.
    - Be concise and engaging, ideally 50-60 characters long.
    - Incorporate power words that appeal to HR professionals and recruiters.
    
    **Meta Description Guidelines:**
    - Avoid AI words like "Transform" or "Revolutionize" and similar overused terms.
    - Be concise: Limit to 150-160 characters to ensure full visibility in search results.
    - Include keywords: Naturally incorporate primary recruitment-related keywords to enhance relevance and visibility.
    - Provide value: Clearly convey the benefits or insights readers will gain from the article.
    - Be engaging: Use action-oriented language or a thought-provoking question to encourage clicks.
    - Align with content: Accurately reflect the blog post's content to meet user expectations and reduce bounce rates.
    - Highlight expertise: Subtly emphasize SocialFind's authority in the recruitment field.
    
    Your output must be a single valid JSON object with these 3 fields:
    -slug: The slug
    -title: The blog post title
    -meta: The meta description  
    
    Each should be presented without any additional text, explanation, quotation marks, or formatting.
  7. Merge blog details

    The Merge node combines three branches (HTML content, title/slug/meta JSON, raw data), and the Aggregate node consolidates them into a unified data structure for the WordPress node.

  8. Clean HTML markers

    A Set node strips ```html and ``` code block markers from the OpenAI response, extracting pure HTML content.

  9. Publish to WordPress

    The Wordpress node creates a draft post (status=draft, authorId=2, commentStatus=closed) using the merged title, slug, meta, and HTML content. Configure wordpressApi credentials and update the hardcoded site URL (currently commonclone.com).

  10. Set featured image

    The workflow sets an image URL via Set Image URL, downloads it with GET Image, uploads to WordPress media library via HTTP Request, and associates it as the featured image. Replace the hardcoded example image URL with your own source or dynamic logic.

  11. Send completion notification via Telegram

    The Telegram node sends a success message with creation timestamp to the configured chat. Set TELEGRAM_CHAT_ID in environment variables and configure telegramApi credentials.

    Execution prompt · Source text。Send Success Message to Telegram node text parameter

    =Success! Your blog post was created at {{ $now }}

Prompt you can copy

Setup guidance · Editorial suggestion。Setup assistant to help import template and verify configuration

This block is the prompt. Ads are never placed here.

You are an n8n workflow setup assistant. The user wants to replicate the 'Generate SEO-Optimized WordPress Content with Perplexity Research' template. Assist in this order: 1) Confirm the user has an n8n instance and four credential types (WordPress API, OpenAI, Perplexity AI, Telegram); 2) Guide importing workflow.json; 3) Check node-by-node for hardcoded values that must be replaced (WordPress site domain, image URL, author ID, company persona prompts); 4) Suggest testing with a sample query first. Do not execute any API calls or publishing actions directly.

Replace hardcoded domain, image URL, and company persona prompts before running

Source

🔍🛠️Generate SEO-optimized WordPress content with AI powered perplexity research · joe · n8n.io · 2025-03-23

Comments & feedback

Tried this method? Share results, problems or improvements. Comments appear after moderation. Please avoid sensitive information.

Loading…

    Related