An AI blog pipeline with a human editor: how this post was made
This post was drafted by a machine. A person read it, changed things, and merged it before you saw it. Since we spend this series describing how other organisations should apply AI to marketing work, it seemed reasonable to open up the pipeline that produces the series itself. This is part of our Practical AI in Marketing series, and it is the only post in it about us. The backlog is a JSON file…
This post was produced by an AI system, with a human editing and reviewing process. The story begins with a JSON file containing the topic, series, title, and related notes. Topics are stored in a JSON file within the same repository as the blog site, providing ample context for the AI to generate content. The human editor has the final say in merging the post or not, ensuring that it meets the standards and guidelines.
The pipeline is limited to the capacity of one human editor to review content each week. This post adheres to specific guidelines, such as word count, language, and the inclusion of client names. The AI promotes the use of prompts for guidance rather than controls, and the editor checks for any disallowed content during the review process.
The post is labeled as partially AI-generated, showcasing a more transparent approach compared to generic AI-assisted labels. The humanising process aims to eliminate salesy language and stock phrases, improving the overall quality of the content. It's worth noting that AI writing detectors, although useful, do not guarantee a quality signal and may lead to dishonest content if optimized for.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
