Learning path
Become an AI engineer
Learn to build applications on top of language models: calling them, grounding them in your data, measuring them and keeping them safe.
You will be able toYou'll finish able to build, evaluate and secure an LLM-backed application.
Stage 01
Foundations
Assumes: Nothing. A computer you can install software on.
Learn enough Python to work with model APIs, and make your first call.
Series: Python from zero
How to Install Python 3.15 and Run Your First Script
You will install uv 0.13 from a checksum-verified release on Ubuntu 26.04, use it to install Python 3.15 next to the system Python, and write and run your first script.
Beginner · 12 min
How to Use Virtual Environments and Install Packages in Python
You will create an isolated Python 3.15 environment for a project, install a package into it with pip, record the exact versions, rebuild the environment from that record, and then manage the same project with uv.
Beginner · 14 min
How to Read and Write Files and JSON in Python
You will read and write text files with pathlib, convert Python data to JSON and back, and use both to build a small task list that keeps its data in a JSON file and survives a damaged file.
Beginner · 16 min
How to Call a Web API from Python with httpx
You will install httpx 0.28, write a small local API to practise on, then call it from Python by fetching JSON, add query parameters and a reusable client, handle bad statuses, timeouts and network failures, send JSON in a POST request, and make several requests at once with async code.
Beginner · 18 min
How to Write and Run Tests in Python with pytest
You will install pytest 9.2 in a uv project, write tests for a small price-parsing module, run many cases from one test with parametrize, read a failure and fix the code, and use a fixture that gives each test its own temporary folder.
Intermediate · 18 min
How to Call a Large Language Model API from Python
You will store an API key safely, install Anthropic's Python SDK 2.8.0, send Claude Sonnet 5.5 a first request, give it instructions and a conversation history, handle the errors an API call can raise, and work out what each call costs.
Beginner · 18 min
Stage 02
Core skills
Assumes: You can write and run Python scripts.
Get structured output from models and serve it through an API.
How to Get Reliable JSON Output from an LLM
You will make Claude Haiku 5.5 return a support ticket as typed data with Anthropic's structured outputs and a Pydantic model, see the schema the API receives, and handle the three ways a reply can still fail to match.
Intermediate · 20 min
How to Build a REST API with FastAPI
You will build a small items API with FastAPI 0.163 on Python 3.15 that validates its input, returns the right HTTP status codes, never shows a stack trace to callers, documents itself, and has automated tests.
Beginner · 22 min
Stage 03
Build projects
Assumes: You can call a model API and build a small web API.
Build a retrieval-augmented app from scratch and measure how well it answers.
Series: Build a RAG app from scratch
How to Split Documents into Chunks for a RAG App
You will write a Python chunker with no dependencies that splits Markdown help pages at their headings and sentences into overlapping pieces, saves them with their source and heading, and checks that no text was lost and no piece is too long.
Beginner · 18 min
How to Do Vector Similarity Search in PostgreSQL with pgvector
You will install PostgreSQL 18 with the pgvector extension on Ubuntu 26.04, store and compare vectors with SQL, load the chunks from the previous tutorial into a table, and add an HNSW index to make nearest-neighbour search fast.
Intermediate · 22 min
How to Build a RAG Question-Answering Endpoint in Python
You will embed your document chunks with Voyage AI, store the vectors in PostgreSQL, and serve a FastAPI endpoint that retrieves the closest chunks and has Claude answer from them with cited sources, and you will make the endpoint fail safely.
Intermediate · 30 min
How to Evaluate and Improve a RAG App with a Test Set
You will write a test set of questions with known answers, measure retrieval with hit rate and mean reciprocal rank and the full pipeline with pass or fail checks, then use the results to add a distance cutoff that makes the app decline questions it cannot answer.
Advanced · 28 min
Stage 04
Job-ready
Assumes: You have built an LLM app that uses your own data.
Defend what you built against the attacks LLM apps face.
How to Defend an LLM App Against Prompt Injection
You will build the layers that limit the damage of prompt injection in a mail-summarising assistant, which are separated data, a tool allowlist per task, validated actions, filtered output and human approval of side effects, and write tests that check each layer without a model.
Advanced · 28 min