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
"Design operations is really about how we’re scaling the work, thinking our practices, and serving cross-functional teams."
Alison Rand Sarah BrooksScaling Impact with Service Design
March 25, 2021
"The difference between the way people talk about how things are done and how they are actually done reveals unconscious assumptions."
Carl TurnerYou Can Do This: Understand and Solve Organizational Problems to Jumpstart a Dead Project
March 28, 2023
"People make decisions with limited information, especially about more distant parts of the system."
Sarah FlamionComplex Problem? Add Clarity by Combining Research and Systems Thinking
March 31, 2020
"If you do nothing, you cannot influence the future. Destination thinking shifts you from reactive to proactive future-oriented leadership."
Silke Bochat5 Antifragile Strategies for a DesignOps 2.0
September 23, 2024
"The hardest talk of all time is five minutes, not 30 or 45."
Uday Gajendar Lada Gorlenko Dave Malouf Louis Rosenfeld Dan Willis10 Years of Enterprise UX: Reflecting on the community and the practice
June 18, 2025
"When the dot com bubble burst, I had a great design job. Unfortunately, it was at another dot com."
Dan WillisEnterprise Storytelling Sessions
June 8, 2017
"Having a monthly newsletter gave people one place to go instead of having to check Slack or emails all the time."
Kara KaneCommunities of Practice for Civic Design
April 7, 2022
"For the first time, I was able to advocate for funding directly for the research function at high executive levels."
Nalini KotamrajuResearch After UX
March 25, 2024
"Lauren Cantor works with companies to create new business strategies by tackling human-centered design."
Bria AlexanderOpening Remarks
October 1, 2021
