This course is popular
3 people enrolled last week.
The no BS class on how search+RAG actually works
Humans increasingly search via chat, not search bars. Go beyond naive RAG to guide agents and understand intent
We teach you how:
Leverage agentic reasoning to go beyond RAG - Traditional RAG can't reason. An agent learns about retrieval systems and tailors its searches for more accurate results. Go beyond naive RAG with agentic search
Craft effective retrieval - Focus an agent's reasoning on the user's task, not "search", with task-targeted search tools. Tools built for agents; not for humans.
Go beyond LLM as a judge - Integrate human and clickstream feedback to guide the agent's judgment towards what users want
Improve traditional search too - Take lessons learned through agentic search back to traditional "search bar" search, simplifying query and content understanding
Come learn alongside search industry expert Doug Turnbull as we unpack how agents will change the search industry.
We teach actual, practical solutions based on what works for real search teams. From query understanding with LLMs to late interaction
What you’ll learn
Rethink search to put tireless agents at work for human users
Build search backends agents can reason about
Why agents love simplicity over complexity
Focusing tools on domain tasks, not "search"
Sidestep complex NLP to better understand queries
Iterate on query understanding through agentic approaches
Organize and structure content to be retrievable by an agent
How to integrate agentic approaches into a traditional search stack
Best practices to manage the agentic loop to save tokens, money, and prevent context rot
Technical approaches to extracting agentic insights (ie code generation)
An agent will by default use its judgments to iterate on relevance on its own. But shouldn't it use humans?
Integrating external feedback (user clicks, etc) into agentic relevance
Beyond LLM as a Judge to exploring how to iterate and improve retrieval for agents and humans
Learn directly from Doug
Doug Turnbull
Snuggie and Search Enthusiast
Who this course is for
Search technologists that want to learn how to ensure RAG and agentic search win
Startups eager to get a fast start with a modern approach to search, sidestepping old, outdated practices
Data scientists that want to consider how agentic / LLM / RAG based search can be oriented towards user feedback and business outcomes
Prerequisites
Lexical Search basics (do you know what BM25 is)
We will build on top of existing, core search knowledge
Basic search evaluation (judgments + metrics)
We will use common search datasets that use metrics like NDCG, etc to measure search
Vector search basics (do you know what an embedding is?)
Vector search will be one tool in our toolkit we'll apply to the agentic tools that we build
What's included
Live sessions
Learn directly from Doug Turnbull in a real-time, interactive format.
Lifetime access
Go back to course content and recordings whenever you need to.
Community of peers
Stay accountable and share insights with like-minded professionals.
Certificate of completion
Share your new skills with your employer or on LinkedIn.
Maven Guarantee
Your purchase is backed by the Maven Guarantee.
Course syllabus
Week 1
May
18
Lesson 1 - Information Retrieval as an agentic process
May
20
Lesson 2 - LLM Query Understanding
May
22
Office Hours
Week 2
May
25
Lesson 3 - An agentic harness - that searches
May
27
Lesson 4 - Beyond LLM as a judge
May
29
Office Hours
Free resource
Cheat at Search Essentials: Vectors and Embeddings
Learn how embeddings implement 'semantic search'
What is a 'vector embedding' and why do they capture meaning? And how can that be used to build a search system?
Tackle the practical realities vector retrieval
Why do we need a vector database? And why are they different from traditional search engines? Should they be different?
How are vector + lexical techniques combined?
Offer a concrete and concise explanation of how you will help students understand and apply this lesson.
Schedule
Live sessions
2-4 hrs / week
Three hours of courses. Optional guest talks from industry experts every week. Office hours to deep dive into your problems with your instructor
Mon, May 18
5:00 PM—6:30 PM (UTC)
Wed, May 20
5:00 PM—6:30 PM (UTC)
Fri, May 22
5:00 PM—6:00 PM (UTC)
Projects
1-2 hrs / week
Optional labs to expand your knowledge and deliver into your team's codebase
Frequently asked questions
$1,300
USD