From 8c0b2491190304b48a094fc0599605d649bb7710 Mon Sep 17 00:00:00 2001
From: Barak Merimovich <294080+barakm@users.noreply.github.com>
Date: Tue, 2 Apr 2024 15:54:22 +0300
Subject: [PATCH] Fix typo

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 8f31e67..0741102 100644
--- a/README.md
+++ b/README.md
@@ -2,7 +2,7 @@
 
 Enterprise data warehouses represent many of the largest technology investments for companies across all industries in the past 20 years. While generative AI has shown a lot of promise in creating novel content and comprehending large corpora of information in unstructured format, how will it improve consumption of the data organizations have invested so much in making useful? These data sources are among the most trusted in an organization and drive decisions at the highest levels of leadership in many cases.
 
-Since its inception in the 70’s, Structure Query Language (SQL) has been the most ubiguitous language to interact with a databases but one still needs a deep understanding of set theory, data types, and foreign key relationships in order to make sense of the data. Generative AI offers a way to bridge this knowledge and skills gap by translating natural language questions into a valid SQL query.
+Since its inception in the 70’s, Structure Query Language (SQL) has been the most ubiquitous language to interact with a databases but one still needs a deep understanding of set theory, data types, and foreign key relationships in order to make sense of the data. Generative AI offers a way to bridge this knowledge and skills gap by translating natural language questions into a valid SQL query.
 
 ### Personas
 The systems and people standing to benefit from this access pattern to databases includes non-technical folks looking to incorporate relational data sources into their process, like customer service agents and call-center associates. Further, technical use cases include Extract-Transform-Load pipelines, existing Retrieval Augmented Generation (RAG) architectures that integrate relational databases, and organizations who are dealing with a data platform too big to reasonably navigate in isolation.