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
"As a design ops manager, I try to alleviate decision fatigue for design managers so they can focus on the decisions that need their input."
Michelle ChinThe DesignOps Starter Kit
September 29, 2021
"Breaking up design research training into short exercises over time helps get people out of the building and engaged."
Louis Rosenfeld Jose Coronado Rachel Posman Guneet Singh Crystal YanThe Bigger Picture: A Panel Discussion
October 23, 2019
"You can’t have effective teams without happy designers and better designers; they’re interdependent."
Kristin Skinner Kamdyn MooreGroup Activity: A Deep Dive Into Value and Outcomes
October 23, 2019
"Radically adaptive experiences are conceived and compiled in real time, responding to context and intent."
Josh Clark Veronika KindredSentient Scenes and Radically Adaptive Experiences
June 11, 2025
"Choosing among all these research tools can be really overwhelming and intimidating."
JP Allen Holly HoldenNavigating the UX Tools Landscape
October 1, 2021
"The ultimate measure of our research is its impact—did we build the right thing and did it have the expected effect?"
Dr. Jamika D. Burge Robert Fabricant Peter Merholz Noam Segal Teresa TorresA Genuine Conversation about the Future of UX Research
March 20, 2024
"One out of every 12 men have some form of color blindness — that was overlooked until we changed our flag icons and got tears of thanks."
Dan WillisEnterprise Storytelling Sessions
June 8, 2016
"We took all the leadership admins to a call center for a week to make them feel what customers go through."
Panel Discussion: Communicating the Value of DesignOps
November 7, 2018
"Software is eating the world, but AI is taking it to a whole new level."
Husani OakleyTheme Three Intro
June 6, 2023
