Summary
Large Language Models (LLMs) are to language as spreadsheets are to numbers: tools for modeling, exploration, and development. Among their many capabilities, LLMs can alleviate chores related to the design and implementation of information architectures. But doing so requires venturing beyond chat-based interfaces. In this brief demonstration, we'll see how to use OpenAI's API and a few open source command line tools to re-categorize content in a 1,000+ page website. The techniques demonstrated can be extended to other common content organization tasks.
Key Insights
-
•
Manual retagging of 1,200 blog posts would take about 10 hours, but leveraging GPT-4 reduced active human time to about 2 hours.
-
•
Using GPT-4 via command line and shell scripts enables automated tagging outside typical chat interfaces.
-
•
An organically grown taxonomy over 20 years contained unclear acronyms and inconsistent tag forms that GPT initially struggled with.
-
•
Cleaning and standardizing the taxonomy before prompting GPT is critical for effective AI assistance.
-
•
A review step of AI-suggested tags in CSV format allows human correction to avoid hallucinations entering production.
-
•
GPT-4 can propose new and useful tags outside the original taxonomy, enriching content classification.
-
•
The four-step GRU framework (Gather, Review, Update, Wrap up) balances automation with human oversight.
-
•
Storing blog content as markdown files simplifies integrating AI workflows via scripting and file manipulation.
-
•
The approach is adaptable and scalable to other CMS platforms by replacing scripting with API calls.
-
•
Taxonomies should use clear, unambiguous terms to improve both human and AI understanding.
Notable Quotes
"Some of the older content has discoverability problems, which is typical with blogs."
"Doing this tagging manually would have taken me around 10 hours of mind-numbing work."
"I’m actually using GPT-4, but not via the chat interface—I'm calling it from the Mac’s command line."
"I had to clean the taxonomy up because GPT wouldn’t know what to do with acronyms like TAOI."
"I save the proposed tags to a CSV file so I can preview and edit them before applying the changes."
"A middle review step prevents hallucinations from making it into the production site."
"GPT-4 functioned as an assistant not just in retagging but also in improving the taxonomy itself."
"The entire process took about three hours from start to finish, about a fifth of the manual time."
"Use clear and obvious terms in taxonomies—unusual acronyms won’t make sense to GPT or others."
"You need to review proposed changes before committing them to production, otherwise errors sneak in."
Or choose a question:
More Videos
"If nobody uses this because they don’t trust it, it doesn’t matter how accurate the model is."
Brian T. O’Neill Maria Cipollone Luis Colin Manuel Dahm Mike OrenDoes Designing and Researching Data Products Powered by ML/AI and Analytics Call for New UX Methods?
February 18, 2022
"Large language models can help organize content faster and at much larger scale than people can."
Jorge ArangoScale Smart: AI-Powered Content Organization Strategies
September 24, 2024
"Sponsor sessions are not sales pitches; they are super similar to the quality of the main conference session."
Bria AlexanderOpening Remarks
October 1, 2021
"Our curators have been working for months taking presentations from little ideas to something big that advances design ops as practice."
Louis Rosenfeld Bria AlexanderDay 1 Welcome
September 23, 2024
"How can we not forget about women?"
Mansi GuptaWomen-Centric Research: What, Why, How
March 29, 2023
"Sponsor sessions do not overlap at all with the main programming. It is 100% fully optional."
Bria AlexanderOpening Remarks
October 3, 2023
"If you are comfortable with it, put your cameras on. It makes me not feel like we’re talking to an answering machine."
Andy Polaine Lavrans LøvlieWhat is the role of service design in product-led organizations?
December 3, 2024
"Publishing again creates a new branch with changes and a pull request, making collaboration and version control seamless."
George Abraham Stefan IvanovDesign Systems To-Go: Indigo.Design Overview and Exploring the Developer Workflow (Part 3)
October 1, 2021
"Building coalitions and embedding research insights within the culture is essential for long-term impact."
Robin BeersBeyond Insights: Researchers as Organizational Change Catalysts
March 25, 2024
