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
"A metaphor is like a flashlight—it shines on some things and keeps others in the dark."
Robin BeersNavigating organizational systems: Rethinking researcher’s role in driving change
March 13, 2025
"Kim Collins had about three coffees a day with different people just to get to know them and build connections."
Laura SchaeferDesignOps: A Conduit for Inclusion
September 9, 2022
"User choice can include opting for a higher carbon or lower carbon version of the same content."
Ned Gartside Mike Gifford Zoe Lopez-Latorre Tzviya SiegmanNavigating accessibility and climate
April 17, 2024
"Agents are models using tools in the loop, calling normal software functions as part of their process."
Peter Van DijckDesigning AI-first products on top of a rapidly evolving technology
June 10, 2025
"Only one designer exists for every 43 developers in many large enterprises."
Surya VankaUnleashing Swarm Creativity to Solve Enterprise Challenges
June 10, 2021
"Insight practices are just getting more established and are asking questions of higher strategic value, bringing disciplines closer together."
Jemma AhmedConvergent Research Techniques in Customer Journey Mapping
March 31, 2020
"Attrition numbers that normally hover around 14 or 15% have spiked to 30%, while hiring is up to 35%."
DesignOps and The Great Talent War of 2021
August 19, 2021
"Power core is where senior executives really care about outcomes or functions that hold power."
Robin BeersBeyond Insights: Researchers as Organizational Change Catalysts
March 25, 2024
"Sometimes you just need to do something completely different than what you’re working on."
Maria SkaadenPanel Discussion: Methodologies and Work Environments
November 8, 2018
