How I Built an AI-Powered SEO Content Machine with n8n Workflows

Analyzing Data from Google Search Console Workflows

Overview of Workflows

• The speaker introduces two workflows for analyzing data from Google Search Console to identify content gaps and create articles based on those gaps.

• Emphasis is placed on the "content opportunity" section, which highlights potential topics for new content based on keyword analysis.

Content Gap Analysis

• Each page analyzed provides specific insights, including top keywords by impressions and identified content gap opportunities.

• The speaker discusses creating new content targeting specific keywords, linking it with existing articles to improve ranking chances.

Workflow Features

• The workflow generates a dashboard that outlines what type of content should be created for each keyword, including article length and internal/external links.

• It scrapes data from search results to provide comprehensive outlines based on competitor analysis, questions extracted, and identified content gaps.

Setting Up the Workflow Logic

Triggering the Workflow

• The main workflow is initiated manually or via a scheduled trigger; it retrieves URLs from a Google Sheet containing all relevant website pages.

• Users can easily add more pages or websites by configuring the sheet with domain names and BigQuery table names.

Data Extraction Process

• The first step involves splitting out pages for testing; a limit can be set for demo purposes (e.g., five pages).

• A custom SQL query extracts low-hanging fruit long-tail keywords dynamically based on page performance rather than fixed thresholds.

Keyword Analysis and Article Creation

Analyzing Keywords

• Extracted keywords are analyzed using a large language model to determine if they represent valid new content ideas.

• Valid ideas are flagged for further processing in the next sub-workflow focused on filling content gaps.

Content Development Process

• The process includes analyzing tone and writing style before clustering keywords into groups to create targeted articles.

Content Generation Workflow Using APIs

Data Retrieval and Processing

• The process begins by retrieving data from the Zer results using an API from Data for SEO, which is then processed through a code node to enhance readability for subsequent LLM calls.

• This workflow aims to minimize token consumption by filtering out unnecessary information, making it more cost-effective.

Competitor Analysis

• After obtaining ranking data, URLs are passed to the Firecrawl API to gather content, which is aggregated for competitor analysis.

• Insights gained include competitor headings and content length, providing a structural guideline for creating new articles.

Content Brief Creation

• The previous LLM node generates a content brief that includes essential elements such as title, meta description, target word count, content type (e.g., guide), and outlines based on competitor data.

• An alternative approach could involve using an AI agent equipped with tools to fetch the current date; however, simplicity was prioritized in this case.

Comprehensive Data Utilization

• The process also identifies content gaps from ZER results and compiles extensive data necessary for generating article outlines and titles.

• Finally, there’s an option to store this data in platforms like Google Sheets or Airtable for further use while ensuring all key details are captured effectively.