DATATWEETS
Courses
Get Started
Course

Generative AI & LLM Engineering

Build real applications with large language models — prompting, tool use, MCP, embeddings, RAG, and AI agents — hands-on in Python with the Anthropic API

Get started Browse all courses

At a glance

Level
Intermediate
Lessons
52 lessons across 10 modules
What you build
Tools, RAG apps, and AI agents
Cost
Free course · pay only for API usage

Projects you'll build

Every module ends with a guided project, so you finish with ten real, portfolio-ready LLM applications:

ProjectCLI assistant A command-line chat assistant backed by the Claude API.View project ProjectReusable prompt toolkit A library of tested, parameterized prompts with structured outputs.View project ProjectMulti-tool agent An agent that picks and calls the right tool in a function-calling loop.View project ProjectMCP integration Connect Claude to a live system through the Model Context Protocol.View project ProjectSemantic search engine Search by meaning with local embeddings — no API key, no cost.View project ProjectSearchable knowledge base Store and query embeddings at scale with a vector database.View project ProjectDocumentation Q&A bot A RAG bot that answers from your docs with grounded citations.View project ProjectResearch assistant An autonomous agent that plans, searches, and synthesizes findings.View project ProjectLangGraph agent Build a stateful, multi-step agent graph with LangChain and LangGraph.View project ProjectFastAPI AI service Wrap Claude in a deployable FastAPI service with logging, health checks, and validation.View project

Course syllabus

Work through the modules at your own pace. Each lesson is a self-contained, hands-on read.

1 Working with LLMs in Python 7 lessons · 1–2 weeks
2 Prompt Engineering 8 lessons · 1–2 weeks
3 Tool Use & Function Calling 5 lessons · 1–2 weeks
4 Model Context Protocol (MCP) 4 lessons · 1 week
5 Embeddings & Semantic Search 4 lessons · 1 week
6 Vector Databases 4 lessons · 1 week
7 Retrieval-Augmented Generation 5 lessons · 1 week
8 Building AI Agents 5 lessons · 1 week
9 LangChain & LangGraph 5 lessons · 1 week
10 Shipping AI Applications 5 lessons · 1 week

Before you start

You'll need comfortable Python — variables, functions, dictionaries, and a little experience with classes. If you want that first, our Python for Data Analytics and Python Advanced courses cover it. You'll write real code against the Anthropic API; the examples use the low-cost claude-haiku-4-5 model so you can follow along for pennies. No machine-learning background is required, though the Machine Learning course is a great companion.

Set up your environment

You can complete this course on any machine with Python 3.12+. Set up once and you're ready for every module.

  1. Get an Anthropic API key from the Anthropic Console, then store it in your environment as ANTHROPIC_API_KEY — never in your code.
  2. Install the packages the course uses:
pip install anthropic==0.112.0 \
  sentence-transformers chromadb==1.5.9 \
  langchain==1.3.11 langchain-anthropic==1.4.8 langgraph==1.2.6 \
  langchain-chroma==1.1.0 langchain-huggingface==1.2.2 \
  "fastapi[standard]==0.138.1"

Runs locally — no API key or cost: the Embeddings & Semantic Search and Vector Databases modules use open-source sentence-transformers and Chroma, so you can complete them fully offline. Expected API spend for every Claude-backed lesson combined is well under $1 on the default claude-haiku-4-5 model.

Tested with (June 2026)

  • python 3.12
  • anthropic 0.112.0
  • sentence-transformers
  • chromadb 1.5.9
  • langchain 1.3.11
  • langchain-anthropic 1.4.8
  • langgraph 1.2.6
  • langchain-chroma 1.1.0
  • fastapi 0.138.1
  • pydantic 2.x
  • uvicorn (fastapi[standard])
  • model: claude-haiku-4-5

LLM tooling moves fast. If an API or package has changed since these versions, the architecture and patterns still apply — adjust the syntax to what you have installed.

Course features

Free Course

Pay only for the API calls you make

From Prompt to Production

First API call through deployed apps

Real, Runnable Code

Live Claude API where it matters, local tools where they're cheaper

Tools, RAG & Agents

The full modern LLM-app toolkit

Claude + LangChain

Native SDK plus the wider ecosystem

Text-Based

Easy to copy, search, and reference

Ready to build with LLMs?

Begin with Working with LLMs in Python and work through all 10 modules, from your first API call to tool use, RAG, agents, and deployment.

Start the first lesson