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
"Breaking a habit path can cause users to repeatedly retry workflows, leading to frustration and cognitive overload."
Paula BachImproving Legacy Software: How Much Better Does it Have to Be?
March 11, 2022
"Sponsor sessions are completely free and offer content just as valuable as the main program sessions."
Bria AlexanderOpening Remarks
November 17, 2022
"Catherine Andrew will share her experience bringing research and analytics functions together to create integrated insight teams."
Jemma AhmedTheme 2 Intro
March 10, 2022
"Designers are creating conditions in which systems can grow, learn, and thrive—moving beyond just solving problems to meta-design."
Hugh DubberlyProblems with Problems: Reconsidering the Frame of Designing as Problem-Solving
June 19, 2019
"The more generous you are, the more those around you shine and everyone benefits."
Jess GrecoClaiming your power: Practical tools for amplifying your unique voice
March 13, 2025
"We have over a thousand members in the #do-general Slack channel, and that’s where the party is at."
Bria AlexanderOpening Remarks
October 1, 2021
"What are three recent examples of how you nurture creativity or resilience for yourself or others?"
Alana WashingtonTheme 1: Introduction and Provocation
January 8, 2024
"Saying no with intentionality and clear guidelines creates clarity and focus."
Deanna Washington Bria Alexander Jon Fukuda Saara Kamppari-Miller Farid SabitovConnecting the Ops: Plenary Panel and Closing Circle
September 9, 2022
"Discomfort is literally part and parcel of the design process and a core practice for trauma-informed practitioners."
Ashley Cortez Devika Menon Nidhi Singh Rathore Danita J. Reese Mari NakanoShifting Toward Community-Led Innovation in Local Government
December 8, 2021
