Computers are good at comparing exact words. But meaning is not about exact words. Car and automobile share almost no letters, yet they mean the same thing. And bank can mean money, or the side of a river.
A Map of Meaning
The solution is to turn text into numbers. A model reads a piece of text and produces a long list of numbers. Think of that list as coordinates, a position on a map.
On that map, things with similar meaning sit close together. Car lands next to automobile. Invoice lands near payment. And a question lands near the text that answers it. That list of numbers is called an embedding.
What It Powers
This one idea powers a great deal: search that understands what you meant, not just what you typed; recommendations; grouping thousands of documents by topic; and finding the right page to hand to a model before it answers.
Why It Matters
For a business it means your documents can be found by meaning. But only if they have been embedded first. And the quality of the map depends on the model that drew it.
RAG builds on Embeddings. RAG’s retrieve step searches documents for passages closest to the question, the search-by-meaning that embeddings power.
Embeddings builds on Transformers and Attention. Both lessons use the word bank to show meaning depends on context; embeddings turn that meaning into coordinates on a map.
The Business Engineer framework maps where each part of the AI stack sits and who holds the leverage. These pills are short lessons from the same library.
Gennaro Cuofano is a CRO and tech executive who has worked in AI since late 2015, starting with bringing NLP, natural-language generation, voice and chatbot products to the marketing industry. His background is in law and finance: he holds a Master's degree in Law and an International MBA with an emphasis on corporate finance (LUISS Business School and the University of San Diego, 2012), and worked as a financial analyst at a real-estate investment firm in San Diego and as an assistant controller. His work focuses on business model strategy, business engineering and, more broadly, structural analysis: how companies make money, read from their own filings. He created FourWeekMBA and leads research there and at The Business Engineer, his newsletter on AI and business strategy, with over 95,000 subscribers and more than 1,000 published analyses. His writing has also appeared on Entrepreneur (for example, How to Digitize a Family Business in Europe) and HackerNoon. Find him on LinkedIn and Substack. See how we source.
Scroll to Top
Discover more from FourWeekMBA
Subscribe now to keep reading and get access to the full archive.
