1 Introducing AI-powered search

 

This chapter covers

  • What is AI-powered search?
  • Understanding user intent
  • How AI-powered search works
  • Content and behavioral intelligence
  • Architecting an AI-powered search engine

The search box has become the default user interface for interacting with data in most modern applications. If you think of every major app or website you use daily, one of the first things you likely do on each visit is enter a query to find the content or actions most relevant to you.

When you’re not explicitly searching, you may instead be consuming streams of content customized to your tastes and interests. Whether these be video recommendations, items for purchase, prioritized emails, news articles, or other content, you’re likely still looking at filtered or ranked results and given the option to either page through or explicitly filter the content with your own query.

For most people, the phrase “search engine” brings up thoughts of a website like Google, Bing, or Baidu that enables queries based on a crawl of the entire public internet. However, the reality is that search is now available in nearly all our digital interactions every day across the numerous websites and applications we use.

1.1 What is AI-powered search?

1.2 Understanding user intent

1.2.1 What is a search engine?

1.2.2 What do recommendation engines offer?

1.2.3 The personalization spectrum between search and recommendations

1.2.4 Semantic search and knowledge graphs

1.2.5 Understanding the dimensions of user intent

1.3 How does AI-powered search work?

1.3.1 The core search foundation

1.3.2 Reflected intelligence through feedback loops

1.3.3 Signals boosting, collaborative filtering, and learning to rank

1.3.4 Content and domain intelligence

1.3.5 Generative AI and retrieval augmented generation

1.3.6 Curated vs. black-box AI

Summary