September 2026
Intermediate
224 pages
3h 53m
English
Content preview from The New Rules of AI Search
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
Resources
Jargon Buster
Here are 20 jargon‐buster terms in plain list form.
- Generative engine optimization (GEO)
A discipline focused on making your brand more visible and useful inside AI assistants and chat‐based search, not just classic Google results.
- Large language model (LLM)
An AI system trained on huge amounts of text that can answer questions, write content, and hold conversations in natural language.
- AI search
Any search experience where answers are generated or summarized by AI, including tools like ChatGPT, Gemini, Perplexity, and Copilot.
- AI Overview
Google's AI‐generated summary that appears in some search results, separate from a full conversational chat experience.
- Training data
The historical content (web pages, books, code, etc.) an LLM was trained on before deployment, which shapes what it already “knows.”
- Knowledge cutoff
The date after which events and updates are not fully included in a model's core training data.
- RAG (retrieval‐augmented generation)
When an LLM looks up fresh information (e.g., via web search) and then writes an answer that blends that with its existing training data.
- Reasoning/mixture of experts (MoE)
A response mode where the model breaks a complex request into parts and consults specialist data sources or tools before answering.
- Agentic web
An emerging version of the web where AI agents browse, click, compare, and act on behalf of users, rather than just showing them links.
- llms.txt
A proposed machine‐readable file (similar to robots.txt) ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.