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
"When you hit the bottom, that’s where creativity flourishes and it’s time to iterate, evolve, and redesign."
Maria GiudiceBecoming a Changemaker by Leading with Design
March 29, 2023
"Before, silos ruled. Now, teams share information and make cross-supply chain decisions focused on customers and associates."
Anat Fintzi Rachel MinnicksDelivering at Scale: Making Traction with Resistant Partners
June 9, 2022
"Leave some space for creativity in your design system so designers can innovate without breaking consistency."
Jaime CreixemsBest Practices when Creating and Maintaining a Design System
June 7, 2023
"If you try to describe a person as 'the grumbler' across all their life, you miss the context and purpose."
Indi YoungThinking styles: Mend hidden cracks in your market
January 8, 2025
"Sponsor sessions are not sales pitches, they’re people like you, really knowledgeable, sharing great things."
Louis RosenfeldWelcome / Housekeeping
June 6, 2023
"I felt like a fake when I didn’t know the details of the Earned Income Tax Credit program, but later I dug in hard and changed that."
Crystal PhilcoxThe Many Faces of Operations
November 6, 2017
"The pandemic is reminding me of the positive and powerful force digital can play when we really need it most."
Leah BuleyClosing Plenary: The Crisis of Digital
March 31, 2020
"One of the challenges for designers is to orient around forces rather than only people."
Sheryl CababaLiving in the Clouds: Adopting a Systems Thinking Mindset
June 6, 2023
"Hope is the only thing that lets the conversation continue and reach forward."
Erika FlowersAI-Readiness: Preparing NASA for a Data-Driven, Agile Future
June 10, 2025
