Stanford University

Amazon

Zilliz

Blue Cross Blue Shield

The University of North Carolina at Chapel Hill

Yujian Tang

Founder @ Cracking Gen AI, 20k+ Learners on LinkedIn, Guest Lecturer @ Stanford

Build an Agentic RAG App (Hands-On)

Databricks

Amazon Web Services

30k+ Learners on LinkedIn, Guest Lecturer @ Stanford

Learn what tools an LLM needs to do RAG on its own

What makes a RAG App Agentic?

Use Databricks Free Edition to build and run your own Agentic RAG app

How to Build an Agentic RAG app on Databricks

Master Advanced Techniques for Building and Optimizing Agentic RAG Systems and Multi-Agent Workflows — Designed for Builders

Founder | Ex-Google | Prof UCLA & UMN

Google

Walmart

University of Minnesota

Stanford Continuing Studies

UCLA

Hamza Farooq

Founder | Ex-Google |
Adjunct UCLA & UMN, SCU | Venture Partner

Staff AI/ML Engineer (DX) @ Together AI 

Coursera

Together AI

University of Toronto

Weaviate AI Database

DeepLearning.AI

Zain Hasan

Staff AI/ML Engineer (DX) @ Together AI | AI Educator & Researcher | Founder

2026-05

2026-03

<h1>Master the full agent stack from first principles to production with RAG, voice, multi-agent systems, &amp; inference</h1>6 live sessions · 6 office hours · 1 demo day · 20+ hours<h3>What You’ll Build</h3>⚡ Agent Harness Design: Build a observable perceive–think–act loop in Python with structured tracing, evolving from simple LLM calls to full agent systems with tools, reflection, and planning⚡ Agentic RAG Systems: Create advanced RAG pipelines with routing, multi-hop reasoning, Knowledge Graph, and semantic caching to improve accuracy and efficiency⚡ Real-Time Voice Agents: Engineer a streaming STT → LLM → TTS pipeline with turn-taking, interruptions, and sub-second latency across modern voice platforms⚡ Multi-Agent Orchestration: Design coordinated agent systems using MCP and A2A with patterns like hierarchical, debate, and orchestrator-worker workflows⚡ Guardrails &amp; Evaluation: Build reliable systems with safety guardrails and trajectory-based evaluation using LLM-as-judge and validated benchmark tasks⚡ Production Deployment: Ship multi-agent systems with Google ADK, MCP, A2A, Llama Guard, and GCP monitoring<h3>💻 Prerequisites: Python</h3>👉 This bootcamp is for engineers who ship real agent systems

Build Production-Ready Agentic RAG, Voice & Multi-Agent Systems 

Build and Debug Production Agent Harness

Deploy and Optimize LLM Inference

Ship Agentic RAG with Graphs and Semantic Cache

Build Voice Agents That Feel Alive

Operate Multi-Agent Systems with Real Coordination

Evaluate, Guardrail, and Operate with Confidence

Machine Learning Engineer exploring different techniques to scale LLM solutions

Researcher, who would like to delve in to various aspects of open-source LLMs

Software Engineer, looking to learn how to integrate AI into their products

Rethink search to put tireless agents at work for human users

http://softwaredoug.com

Doug Turnbull

Snuggie and Search Enthusiast

June 2026

Oct 2026

Keyword search + an agent - is that all we need now? The agentic world challenges traditional ways of building search. Traditionally we've built thick, complex search APIs - query understanding, rerankers, learning to rank, vector databases. Yet an agent can compete in deep research benchmarks with the dumbest of search tools.This course pushes you to rethink search. We teach:<ul><li>Replacing search with agents - A search agent learns about retrieval systems, tailoring searches, achieving competitive results</li><li>Guiding agents, not algorithms - Search developers won't train algorithms. They'll build harnesses</li><li>Steering with an LLM judge - Integrate human and clickstream feedback to guide the agent's judgment towards what users want</li><li>Autoresearching to smarter search - Use + build a coding agent that optimizes retrieval code like an ML model.</li></ul>Come learn alongside search industry expert <a target="_blank" rel="noopener noreferrer nofollow" href="http://softwaredoug.com">Doug Turnbull</a> as we unpack how agents will rewrite the search industry.

The future of search is agentic. Are you ready?

What makes a great search tool to an agent?

Use LLMs to help agents structure, organize, and find content

Agentic results without the cost

Orienting agentic search towards the human, not the machi

We will build on top of existing, core search knowledge

Lexical Search basics (do you know what BM25 is)

We will use common search datasets that use metrics like NDCG, etc to measure search

Basic search evaluation (judgments + metrics)

Vector search will be one tool in our toolkit we'll apply to the agentic tools that we build

Vector search basics (do you know what an embedding is?)

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

Create your own production-ready AI application in 6 weeks

Teaching AI and Data to 100k+ students 

DataTalksClub

Manning Publications

OLX Group

Alexey Grigorev 

15 years of experience. Teaching AI and Data to 100k+ students

Cohort 3

Cohort 4

This course takes you from core concepts to production-grade AI systems through hands-on, project-focused modules.<ol><li>LLMs &amp; RAG Learn Large Language Models and Retrieval-Augmented Generation. Build conversational agents using the OpenAI SDK and create data-processing pipelines. Outcome: A RAG pipeline with real data.</li><li>Agentic Flows + MCP Add agentic behavior with function calling, using libraries like PydanticAI, and Agents SDK. Expose tools via MCP. Outcome: A capable, tool-using agents.</li><li>Testing &amp; Evaluation Improve through testing and offline evaluation. Use LLMs as judges to compare approaches. Learn tools like Evidently and LangWatch. Outcome: A thoroughly tested and evaluated assistant.</li><li>Monitoring &amp; Guardrails Use Grafana, Pydantic Logfire and OpenTelemetry for observability and safety. Outcome: Real-time monitoring.</li><li>Use Cases Create two agents: a website generator and a code reviewer. Learn about other use cases.</li><li>Capstone Build an end-to-end AI application with your data. Outcome: A portfolio-ready project.</li></ol>Hackathon: Collaborate on real-world problems.By the end, you will: build, evaluate and monitor a smart assistant; create deep research and coding agents; have a polished portfolio project

Build your own Agentic AI Assistant

🛠️ Build a Fully Functional AI Assistant from Scratch

🤖 Add Agentic Behavior to Your AI Systems

🔧 Use Testing and Evaluation to Improve Prompts and Results

📈 Monitor Your Application 

🔧 Build 8+ Projects 

🎓 Ship a Capstone AI Project — Start to Finish

Coding

We will rely on these tools when building the assistant

Python, Git, Docker, command line

We will use OpenAI for building the AI agent

OpenAI key or alternative

Data Scientists and ML Engineers proficient at coding who want to integrate AI into their projects

Software Engineers curious about LLMs who want to build AI applications

AI Enthusiasts who are stuck at the tutorial phase and want to create something end-to-end

This is a project-based course. In 6 weeks, learn a repeatable framework, build a multi-agent app, and leave as an Agentic Architect.

O'Reilly instructor|Pearson SME|ex-Cisco

Cisco

Claro Brasil

Pearson

O'Reilly

Carmelo Iaria

Agentic Architect, O'Reilly instructor, 30 years of global experience, ex-Cisco

Cohort 5

Cohort 6

—This course is what you need to stay relevant — and protect your career.—Why this course mattersIn 2026, engineering value is shifting from task execution to orchestration and systems thinking. Anthropic’s research shows that being a software engineer increasingly means orchestrating agents that write code, evaluating their output, and ensuring the system solves the right problems—not just writing more code yourself. The gap between early adopters and everyone else is widening fast.You will leave with a production-ready capstone architecture, reusable templates, and a repeatable method you can apply immediately to your projects.—The course was named a Maven TOP100 course!—What alumni sayBuilders from AT&amp;T, HP, Morgan Stanley, T-Mobile, Cognizant, Experian have applied the method I teach to build amazing multi-agent applications.<ul><li>Matt (Founder, SAVANT-AI): "Five stars for course logic, course structure, and course value."</li><li>Alexa (Lead UX Designer, Caseware): "I can already see how to bring it into my work."</li><li>Satyan (Group PM, AT&amp;T): "The concepts taught here make the difference between building a product that works and one that doesn't."</li></ul>—5 Need-based Scholarship seats available - <a target="_blank" rel="noopener noreferrer nofollow" href="https://forms.gle/REvzHtVMAnL1uXv66">Apply</a>—

Software development is moving from writing code to orchestrating agents. 

Define a solid foundation with clear research and project scope

Architect your complete multi-agent solution — from roles to workflows

Design and build a production-ready Agentic AI Application

Define and configure your multi-agent crew — from backend logic to integrations

Add enterprise-level quality: integrate human feedback, observability, and QA

Deploy, validate, and present your final Capstone solution with confidence

Own delivery outcomes in tech/product/design/consulting. Read-level Python is helpful; pair with a technical teammate if needed.

Experience & Background

Comfort with Git/GitHub, API basics, and AWS (or similar). If rusty, budget extra setup time in Weeks 1-2.

APIs & Cloud Platforms

Agentic IDE (Cursor, Claude Code, GitHub Copilot), OpenAI API credits (~$20+), GitHub account, AWS access (recommended)

Required Tools & Access

Technical Builders (software, AI/ML, data, platform) moving from demos to reliable delivery.

Product and Business Owners (PMs, founders, consultants) responsible for outcomes, priorities, and execution quality.

UX and Experience Leaders (UX, service design, research) shaping human-agent workflows, trust, and adoption.

Agentic AI

Coding with AI

AI Workflows

Claude Code

OpenClaw

Vibe Coding

AI Evals

AI Transformation

RAG & Search

AI for PMs

AI for Engineers

AI for Designers

AI for Marketers

AI for Founders

Product Sense

Product Discovery

User Research

Prototyping

Growth

Analytics

Tech Foundations

Strategy

Influence

Leadership

Career Growth

Machine Learning

LLM Ops

Context Eng

Security

System Design

Figma

Design Systems

Visual Design

Design Strategy

Automation

Content Marketing

Demand Gen

Go-to-Market

Product Marketing

Positioning

Social Media

Brand

B2B Marketing

SEO & AEO

AI for Leaders

AI Governance

Communication

Management

People Operations

Exec Presence

Storytelling

Goal-setting

Personal Brand

Fundraising

Everyone

Operators

Data Scientists

Business Analysts

User Researchers

Customer Success

Project Managers

HR Professionals

Sales People

Lawyers

Finance

Investors

Real Estate

Educators

Creators

Engineers and engineering leaders who build, deploy, and scale software systems.

Applying AI tools and techniques to professional workflows — assign alongside more specific AI topics.

Building autonomous AI agent systems that take actions, use tools, and orchestrate multi-step workflows.

Building retrieval-augmented generation and search systems — vector databases, embeddings, ranking, and retrieval pipelines.