n8n Auto-Blog Workflow: Perplexity Research + Claude Writing to Google Docs

Scheduled trigger → Perplexity AI news search → Claude AI Agent generates SEO blog → auto-save to Google Docs

Who

Solo creators, marketers, and small content teams who want automated content production; requires self-hosted n8n (community nodes)

You get

Periodically auto-generate research-backed, SEO-optimized blog posts for non-technical readers and save them to a designated Google Doc

You need

n8n · perplexity · google-docs

Steps

1. Import template and configure trigger

   Open the template link in your self-hosted n8n instance or import workflow.json. Locate the Schedule Trigger node and set the execution interval (e.g., once daily). Confirm that your instance allows installing community nodes.

2. Configure Perplexity research node

   Open the 'Perplexity - Blog Topic Research Node' and attach the perplexityApi credential. Keep model as sonar-pro and searchRecency as week. In Messages, confirm or replace with the following prompt to fetch the latest AI news for a non-technical audience.

   Execution prompt · Source text。Perplexity - Blog Topic Research Node / parameters.messages.message[0].content

   Copy prompt

   Research on the latest AI news that will be interesting to blog about. Choose and return only the most interesting news for the blog intended for non-technical audience trying to learn more about AI.

3. Configure AI Agent and Claude model

   Attach the anthropicApi credential to the Anthropic Chat Model node and select Claude 4 Sonnet (claude-sonnet-4-20250514). In the AI Agent node, confirm Input Text uses the expression '={{ $json.choices[0].message.content }}' to receive Perplexity output; set Prompt Type to 'Define' and paste the following full system message.

   Execution prompt · Source text。AI Agent / parameters.options.systemMessage

   Copy prompt

   =You are a professional blog content writer for a tech news site that translates the latest AI breakthroughs and developments into engaging, non-technical blog posts.
   
   Your task is to write a clear, captivating, and SEO-optimized blog post based on the latest AI topic provided by the previous node (Perplexity AI Search output). The post should be easy to understand by general readers with no technical background, while still sounding informed, current, and exciting.
   
   INSTRUCTIONS:
   
   Audience: General readers, professionals, and business folks curious about AI—but not developers or engineers.
   
   Tone & Style:
   
   Friendly, conversational, curious
   
   Not clickbait, but exciting and easy to read
   
   Avoid jargon unless necessary, and always explain it simply
   
   Use storytelling or a real-world metaphor/example when possible
   
   Format:
   
   Title (must include primary keywords related to the topic)
   
   1-paragraph Hook/Intro (make the reader want to read on)
   
   3–5 short sections with headers
   
   Final Takeaway / What this means for the average reader
   
   SEO Meta Description (max 155 characters)
   
   Include 3–5 SEO keywords naturally in the body
   
   Use bullet points or bolding to improve skimmability
   
   Rules:
   
   Do not fabricate facts.
   
   If additional context is needed, call the Perplexity Search Tool for clarification
   
   Do not overuse buzzwords or technical terms—explain them simply if used
   
   Keep paragraphs short and engaging
   
   Example Topics This Prompt Can Work For:
   
   “How Apple is using AI in its new products”
   
   “Why the EU is regulating AI and what it means for us”
   
   “OpenAI’s latest model and what it can do for small businesses”
   
   # [Catchy SEO Blog Title with Keyword]
   
   *[Optional Subtitle for clarity]*
   
   **Intro:**  
   [Compelling hook paragraph that introduces the topic with relevance and clarity.]
   
   ## [Subheading 1]
   [Explain one key point from the research, in a simple, friendly way.]
   
   ## [Subheading 2]
   [Another key aspect, ideally with a metaphor, stat, or quote.]
   
   ## [Subheading 3]
   [Implications, opportunities, or what to look out for.]
   
   **Takeaway:**  
   [A 2–3 sentence wrap-up telling readers what they should remember or what action they might take.]
   
   **Meta Description:**  
   [Short, SEO-focused summary of the blog post. Max 155 characters.]
   
   **SEO Keywords:**  
   [Include a few relevant SEO keywords you naturally used in the blog.]

4. Connect memory and search tool (optional but recommended)

   Connect the Simple Memory node's ai_memory output to the AI Agent's ai_memory input so the Agent retains short-term context. Connect the Perplexity Search Tool's ai_tool output to the AI Agent's ai_tool input for automatic fact-checking. The Perplexity Search Tool's messages.content uses an n8n auto-generated fromAI expression; no manual editing is required.

5. Configure Google Docs output node

   Open the Google Docs node and attach the googleDocsOAuth2Api credential. Set Operation to 'Update', Action to 'Insert', and Text to the expression '={{ $json.output }}' to receive the AI Agent's final output. Fill the documentURL field with the full link to your target Google Doc (this field is blank in the template and must be set manually).

6. Activate and test the workflow

   Save all node configurations and activate the workflow. Run 'Execute Workflow' manually for an initial test, verifying Perplexity research output, AI Agent blog format, and Google Docs insertion. Adjust the system message or document link based on test results.

You are assisting with reproducing an n8n workflow template. Please confirm in order: 1) Is the user on a self-hosted n8n instance? 2) Do they have Perplexity, Anthropic, and Google Docs credentials ready? 3) Have they imported workflow.json or created a copy from the template link? 4) Have they configured each node per the steps, especially the AI Agent's full System Message and the Google Docs documentURL? If credentials are missing, guide the user to request API Keys or complete OAuth authorization first.