AI series · Part 1: GenAI and Knowledge Modeling
Taxonomy: Organize Knowledge So AI Searches Less and Finds More
A taxonomy is a tree of categories. Tagging documents with one lets an AI assistant skip irrelevant content before it searches, which means less noise and more accurate answers.
A taxonomy is a tree of categories where each child is a more specific type of its parent ("is a type of"). It works like the aisles in a supermarket: you go straight to the Dairy aisle for cheese instead of walking the whole store.
Where you already see taxonomies
- Amazon menus: Electronics → Mobiles → Smartphones → Android.
- Hospitals: ICD-10 disease codes are also a tree, from broad chapters down to specific conditions.
How we use it in an AI assistant
In our reference HR assistant, every policy document belongs to one branch of a small taxonomy:
Benefits → Leave, Insurance
Workplace → Remote Work
Finance → Travel
Workforce → Interns and ContractorsEvery chunk of text is tagged with its category. For the question "Can an intern take maternity leave?", the system searches only the Leave and Interns documents. The travel policy and the insurance policy are never even considered.
I tag every chunk with a taxonomy category and filter by it before searching. Fewer, more relevant documents means less noise and more accurate answers.
- The short version
Next in the GenAI series: Ontology: The Blueprint Behind Enterprise Knowledge
Start from the top: GenAI Quick Answers and Series Guide
We deploy these patterns across production engagements in fintech, healthcare, and eCommerce. Talk to a senior engineer about how they apply to your platform.