Can AI effectively perform technical SEO analysis using raw crawl data? This question has been explored in a recent article on Search Engine Land. The article focuses on the capabilities of ChatGPT, a generative AI model, in interpreting Screaming Frog crawl data and generating SEO recommendations.
The author of the article, James Allen, acknowledges that while AI has made significant strides in various fields, many marketers may struggle to blend AI technology with technical SEO data. As such, he tests the effectiveness of AI in interpreting technical SEO data using ChatGPT.
Allen discusses the evolution of ChatGPT from GPT-4 to GPT-4o, highlighting its increased speed and interactivity. However, there are concerns about the model’s ability to access web content, as previous experiences with tools like Google’s Bard and Gemini showed inferior results.
To test ChatGPT, Allen feeds it specific technical SEO crawl data from the Butcher’s Dog Food company website. He analyzes the recommendations provided by ChatGPT and finds that most of them are disappointingly generic and lack specificity. While there are signs of intelligence in the AI’s attempt to analyze the data, the recommendations are ultimately unusable.
Comparing AI insights to Ahrefs’ technical audit, Allen finds that some of the issues identified by ChatGPT were accurate, such as redirecting addresses and image compression. However, the specific advice given by ChatGPT was not usable.
In conclusion, Allen states that GPT-4o is a vast improvement over GPT-3.5-Turbo but questions whether there is significant improvement over GPT-4. He advises against relying on AI technology for technical SEO analysis at this time but acknowledges the potential for improvement in the future.
