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
"Nudge to me now is much more about wiggle it and see what happens rather than expecting exact outcomes."
Jen BriselliLearning Is The Engine: Designing & Adapting in a World We Can’t Predict
April 16, 2025
"This is probably the biggest change we are going to see within our working careers."
Robert Fabricant Sahibzada Mayed Nidhi Singh RathoreIndustry junctures: Paths forwards for UXR and the critical decisions that get us there [Advancing Research Community Workshop Series]
October 2, 2024
"Our nervous system does not know the difference between a tiger and an angry email from a manager—it just senses danger."
Alla WeinbergDesign Teams Need Psychological Safety: Here’s How to Create It
September 8, 2022
"We need distributed, shared, and participatory technologies for common good outcomes."
Dan HillDesigning for the infrastructures of everyday life
June 4, 2024
"Operations is the de-risking activity that creates scalable processes for better outcomes - Theresa."
Bria Alexander Patrizia Bertini Peter Boersma Jon Fukuda Dave Malouf Theresa Slate Changying (Z) ZhengCharting the future of DesignOps: A community workshop
April 18, 2024
"Prioritization isn’t about scoring to pick projects, but about facilitating discussion and aligning the team’s understanding."
Chris GeisonWhat is Research Strategy?
March 11, 2021
"Nothing about us without us."
Sam ProulxAccessibility: An Opportunity to Innovate
November 16, 2022
"Co-creation is highly actionable for teams and genuinely engaging for customers."
Dagmara KukawkaTiny team, moonshot impact: Democratizing research across continents
March 10, 2026
"Continuous feedback requires collecting responses tied to the same user across multiple channels with behavioral targeting."
Aleksandra Korczynska Caroline Jarrett Justyna ParmeeSurvey Tools
March 12, 2026
