Skip to content
Start learning
Coming soon

AI with Python

Move past toy prompts to build production-ready AI applications: structured outputs, semantic search, RAG, and autonomous tool-using agents.

  • 12 modules
  • 12 lessons
  • Shallows to Landfall
  • Video + reading

This course is being written. The outline below is what it will teach; follow the Telegram channel to hear the day it opens.

Get notified on Telegram

What you'll be able to do

  • Call leading LLM APIs programmatically and reliably
  • Extract validated data using Pydantic structured outputs
  • Implement semantic search and retrieval-augmented generation (RAG)
  • Build autonomous tool-using AI agents that solve complex workflows

The full syllabus

12 modules, from the Shallows down. Open any module to see its lessons.

The Shallows

Understanding LLMs, calling APIs from Python, and prompt engineering.

  1. 1How LLMs workIntuition for tokens, context windows, and probabilistic text generation.
    1. 1.1Tokens and context windowsSoon
  2. 2Calling LLM APIsConnect to model APIs from Python, manage keys, and stream responses.
    1. 2.1Your first LLM API callSoon
  3. 3Prompt engineeringInstructions, few-shot examples, system messages, and role definitions.
    1. 3.1Writing effective promptsSoon

Currents

Structured outputs, data manipulation, embeddings, and RAG.

  1. 4Structured outputs with PydanticEnforce strict JSON schemas and parse LLM outputs into typed objects.
    1. 4.1Extracting structured dataSoon
  2. 5Data essentials: NumPy & pandasJust enough data handling for vectors, matrices, and tabular datasets.
    1. 5.1Working with datasetsSoon
  3. 6Embeddings and semantic searchConvert text into high-dimensional vectors and perform cosine similarity search.
    1. 6.1Generating text embeddingsSoon
  4. 7Retrieval-augmented generation (RAG)Chunk documents, retrieve relevant contexts, and synthesize grounded answers.
    1. 7.1Building a RAG pipelineSoon

Deep Water

Tool calling, autonomous agents, evaluation, and production safety.

  1. 8Tool use and agentsLet an LLM call Python functions, search databases, and take actions.
    1. 8.1Function calling and tool useSoon
  2. 9Evaluating AI featuresMeasure accuracy, hallucinations, and regression across prompt revisions.
    1. 9.1Automated AI evaluationsSoon
  3. 10Cost, latency, and safetyRate limiting, caching, cost monitoring, and guardrails for production.
    1. 10.1Production guardrails and costSoon

Landfall

Ship AI behind FastAPI and complete the document assistant capstone.

  1. 11Shipping AI behind FastAPIExpose streaming AI features and RAG pipelines via fast web endpoints.
    1. 11.1Streaming API endpointsSoon
  2. 12Capstone: Document assistantBuild an end-to-end assistant that answers questions over custom PDF and markdown files.
    1. 12.1Building the document assistantProjectSoon

Who it's for

  • Python developers wanting to integrate modern AI into real products
  • Software engineers who want to build with RAG, embeddings, and agents
  • Students aiming for practical AI engineering skills beyond theory

What you need

  • Comfortable with Python functions, dictionaries, and virtual environments
  • An internet connection and an API key for experimentation

AI with Python is coming

Enrollment opens when the first modules are ready. The channel announces it first.

Get notified on Telegram

What it will include

  • Coding walkthroughs and the architecture of real AI features
  • Complete reference repositories for RAG and agent patterns
  • Private Telegram community with direct instructor guidance