Build Fast with AI logo
RoadmapProjectsCareer PathsCheckpoints
Start Level 0
Learning path
★Roadmap overview0Environment & Foundations1LLM Fundamentals & APIs2Building Simple GenAI Applications3RAG Systems & Intelligent Agents4Production Systems & Deployment5Advanced GenAI Techniques6Choose Your Specialization Path
Resources
Projects & notebooksCareer pathsCheckpoint tasks
  1. Home
  2. GenAI Roadmap
  3. Level 3
3Level 3 of 6 · Intermediate

Level 3: RAG and AI Agents Roadmap

Level 3 covers the two patterns behind most real GenAI products: retrieval-augmented generation (RAG), which grounds answers in your own documents, and agents, which call tools to take actions. You learn embeddings, vector databases such as Pinecone, Weaviate and Qdrant, tool calling, handoffs between agents and how to trace what went wrong. It takes about 25 hours over 3 to 4 weeks.

By the Build Fast with AI team·Published April 10, 2026·Updated November 19, 2026

Duration
3-4 weeks
Difficulty
Intermediate
Study time
~25 hours
Checkpoints
6 tasks
On this page
  1. What you will learn
  2. Topics and tools
  3. Checkpoint tasks
  4. Notebooks and projects
  5. FAQ
  6. Related guides

Outcomes

What you will learn in Level 3

  • Implement RAG systems from scratch
  • Build intelligent agents that make decisions
  • Orchestrate multiple agents working together
  • Trace and evaluate agent behavior
  • Evaluate RAG and agent performance
  • Handle complex multi-step reasoning

Syllabus

Topics and tools in Level 3

  1. 01Vector databases (Pinecone, Weaviate, Qdrant)
  2. 02Embeddings and semantic search
  3. 03Retrieval-augmented generation (RAG)
  4. 04Agent architectures and handoffs
  5. 05Tool calling and function execution
  6. 06Multi-agent orchestration
  7. 07Memory strategies for agents
  8. 08Tracing and evaluation metrics
Tools:EmbeddingsPineconeWeaviateQdrantOpenAI Agents SDKOpikAgentOps

Practice

Level 3 checkpoint tasks

Finish these 6 tasks before moving on. Open a task to see its steps.

  1. 1

    Basic RAG system

    2 hours
    • Load and chunk a set of documents
    • Embed the chunks and store them in a vector database
    • Answer questions using the retrieved chunks, with sources cited

    Time: 2 hours

  2. 2

    Vector database comparison

    1.5 hours
    • Load the same data into two vector databases
    • Compare query speed, metadata filtering and setup effort

    Time: 1.5 hours

  3. 3

    Agent with tools

    2 hours
    • Give an agent two tools, for example web search and a calculator
    • Log every tool call and its result

    Time: 2 hours

  4. 4

    Better retrieval

    2 hours
    • Try two chunk sizes and add a reranker
    • Measure answer accuracy on 10 test questions before and after

    Time: 2 hours

  5. 5

    Multi-agent system

    3 hours
    • Split one task across two or three agents with handoffs
    • Trace the full run with Opik or AgentOps

    Time: 3 hours

  6. 6

    RAG plus agent

    3 hours
    • Build an agent that decides when to search your documents
    • Evaluate it on a fixed question set

    Time: 3 hours

Build

Notebooks and projects for Level 3

5 runnable notebooks, all free to open in Google Colab.

OpenAI Agents Quickstart

Notebook

Build triage, handoff, and tool-calling workflows with the OpenAI Agents SDK.

BeginnerLevel 0–3#agents#handoffs

Promptfoo GPT-5.4 Evaluation Cookbook

Notebook

Compare frontier models with cost, latency, and red-team checks using Promptfoo.

IntermediateLevel 1–4#promptfoo#evals

Gemini 3.1 Flash-Lite Guide

Notebook

Route simple tasks to Flash-Lite and harder ones to Pro with a practical hybrid router.

IntermediateLevel 2–3#gemini#routing

Opik LLM Evaluation and Monitoring

Notebook

Track traces, metrics, and evaluation runs for LLM and agent workflows.

IntermediateLevel 3–4#opik#monitoring

AgentOps Evaluation

Notebook

Add replay analytics, benchmarking, and monitoring to multi-agent systems.

IntermediateLevel 3–6#agentops#monitoring
12 more project ideas to build yourself

RAG-Powered Chatbot

Brief

Build a chatbot that retrieves and references documents in its responses.

IntermediateLevel 3#rag#vector-db

Web Research Agent

Brief

Create an autonomous agent that can search the web and synthesize information.

IntermediateLevel 3#agent#tools

Multi-Document Analysis System

Brief

Build a system to analyze and extract patterns across multiple documents.

AdvancedLevel 3#rag#analysis

AI-Powered Code Editor

Brief

Full-stack application with AI code completion and intelligent suggestions.

AdvancedLevel 2–5#app-dev#frontend

Real-Time Collaborative AI App

Brief

Build a collaborative app with WebSockets and AI features supporting multiple users.

AdvancedLevel 2–4#app-dev#websockets

Mobile AI Assistant

Brief

Create a mobile app (iOS/Android) powered by GenAI with offline capabilities.

AdvancedLevel 3–5#app-dev#mobile

Scalable RAG Platform

Brief

Engineer a large-scale RAG system supporting millions of documents and high QPS.

AdvancedLevel 3–5#engineer#rag

Distributed Multi-Agent System

Brief

Design and implement distributed agents orchestrating complex workflows.

AdvancedLevel 3–5#engineer#agents

Novel RAG Architecture Research

Brief

Research and implement innovative RAG approaches with published benchmarks.

AdvancedLevel 3–5#research#rag

Agent Architecture Research

Brief

Research optimal agent architectures for different problem classes.

AdvancedLevel 3–5#research#agents

AI Product Market Research

Brief

User and market research for positioning an AI product.

IntermediateLevel 2–4#product#research

Competitive Benchmarking Study

Brief

Analyze competitive AI products and create detailed feature benchmarks.

IntermediateLevel 3–4#product#competitive-analysis

FAQ

Level 3 questions, answered

What is a RAG roadmap?

A RAG roadmap is the order in which to learn retrieval-augmented generation: embeddings, chunking, vector databases, retrieval, prompting with context, then evaluation and reranking. On this roadmap that sequence is Level 3, after you can already build a basic LLM app.

Should I use RAG or fine-tuning?

Use RAG when the model needs facts it does not know or that change often, such as company documents. Use fine-tuning to change style, format or behaviour. Most teams start with RAG because it is cheaper to update and easier to debug.

Which vector database should I learn first?

Any one of Pinecone, Weaviate, Qdrant or Chroma teaches the core ideas: embeddings, similarity search and metadata filters. Pick a managed service if you want zero setup, or Qdrant or Chroma if you want to run it locally.

What is the difference between a RAG system and an AI agent?

A RAG system retrieves context and then answers once. An agent runs a loop: it picks a tool, reads the result and decides what to do next. Many production agents use RAG as one of their tools.

How do I evaluate a RAG system or an agent?

Build a fixed set of 20 to 50 questions with known answers, then measure retrieval hit rate and answer correctness every time you change something. Tracing tools such as Opik and AgentOps show which step failed.

Read next

Related guides

  • What is RAG?
  • What is a vector database?
  • What are embeddings?
  • RAG vs fine-tuning
  • What is an AI agent?
  • Build a RAG chatbot, step by step
  • RAG interview questions
← PreviousLevel 2: Building Simple GenAI ApplicationsNext →Level 4: Production Systems & Deployment

On this page

  • What you will learn
  • Topics and tools
  • Checkpoint tasks
  • Notebooks and projects
  • FAQ
  • Related guides
Build Fast with AI logoBuild Fast with AI

A free, project-based roadmap for learning generative AI, from your first API call to production systems.

Levels

  • Level 0: Environment & Foundations
  • Level 1: LLM Fundamentals & APIs
  • Level 2: Building Simple GenAI Applications
  • Level 3: RAG Systems & Intelligent Agents
  • Level 4: Production Systems & Deployment
  • Level 5: Advanced GenAI Techniques
  • Level 6: Choose Your Specialization Path

Career paths

  • AI App Developer Roadmap
  • AI Engineer Roadmap
  • ML Researcher Roadmap
  • AI Product Manager Roadmap
  • All projects and notebooks
  • Checkpoint tasks

Keep learning

  • AI concepts explained
  • AI glossary
  • AI project ideas
  • AI interview prep
  • Blog
  • Notebooks on GitHub

© 2026 Build Fast with AI. All rights reserved.

Privacy PolicyTerms