This n8n workflow automates the transformation of press releases into polished articles. It converts the content of an email and its attachments (PDF or Word documents) into an AI-written article/blog post.

What does it do?
This workflow assists editors and journalists in managing incoming press releases from governments, companies, NGOs, or individuals. The result is a draft article that can easily be reviewed by the editor, who receives it in a reply email containing both the original input and the output, plus an AI-generated self-assessment. This self-assessment represents an additional feedback loop where the AI compares the input with the output to evaluate the quality and accuracy of its transformation.

How does it work?
Triggered by incoming emails in Google, it first filters attachments, retaining only Word and PDF files while removing other formats like JPGs. The workflow then follows one of three paths:

– If no attachments remain, it processes the inline email message directly.
– For PDF attachments, it uses an extractor to obtain the document content.
– For Word attachments, it extracts the text content by an HTTP request.

In each case, the extracted content is then passed to an AI agent that converts the press release into a well-structured article according to predefined prompts. A separate AI evaluation step provides a self-assessment by comparing the output with the original input to ensure quality and accuracy. Finally, the workflow generates a reply email to the sender containing three components: the original input, the AI-generated article, and the self-assessment. This streamlined process helps editors and journalists efficiently manage incoming press releases, delivering draft articles that require minimal additional editing.