Example · 3 days
Python, data and AI
Engineering-grade Python, analysis with pandas, classical machine learning, then language models and retrieval on your own data.
For analysts and data scientists.
Day 1
Python for engineers: types and design
Quarter day · Python and data · Intermediate
- Type hints and checking with mypy or pyright.
- Dataclasses and Protocols.
- Packaging with uv, linting and formatting with Ruff.
- Lab: turn a script into a typed, tested package.
pandas: loading and cleaning data
Quarter day · Python and data · Foundation
- DataFrames, Series and indexes.
- Loading from CSV, Excel and databases.
- Missing values, types and reshaping.
- Lab: clean a messy real-world dataset.
pandas: analysis and charts
Quarter day · Python and data · Foundation
- Grouping, joining and pivoting.
- Time series.
- Charts that answer a question.
- Lab: answer business questions from the cleaned data.
Machine learning: framing and metrics
Quarter day · Python and data · Intermediate
- Turning a business question into a prediction problem.
- Choosing a metric that matches the cost of errors.
- Train, validation and test sets.
- Exercise: frame three candidate problems.
Day 2
Machine learning: features and pipelines
Quarter day · Python and data · Intermediate
- Feature engineering for tabular data.
- scikit-learn pipelines and transformers.
- Avoiding leakage.
- Lab: build a preprocessing pipeline.
Machine learning: models and validation
Quarter day · Python and data · Intermediate
- Linear models, trees and gradient boosting.
- Cross-validation and hyperparameter search.
- Classification and regression compared.
- Lab: train and compare models.
Working with LLM APIs
Quarter day · AI engineering · Intermediate
- API keys and authentication.
- Sending and receiving requests, structured JSON and streaming.
- Managing context and conversation state.
- Cost and token management.
- Enough Python to understand and change the examples. All code is supplied, with starting points and worked solutions.
Prompts and schemas as tested interfaces
Quarter day · AI engineering · Intermediate
- Prompts as code: instructions, examples, constraints and versioning.
- Structured outputs and JSON Schema: a request, not a guarantee.
- Separating trusted instructions from untrusted input.
- Lab: write a prompt with tests, then break it with realistic inputs.
Day 3
RAG as an architecture
Quarter day · RAG and agents · Intermediate
- The stages: ingest, index, retrieve, assemble, generate and cite.
- Where RAG fits, and where fine-tuning or plain search fits better.
- The failure modes of each stage.
- Choosing a vector store and a framework, or neither.
Embeddings and vector search
Quarter day · RAG and agents · Intermediate
- Embedding models: choosing, comparing and versioning.
- Vector indexes, similarity and approximate search.
- Filters and namespaces.
- Lab: index a corpus and run a question set against it.
Grounded answers and citations
Quarter day · RAG and agents · Intermediate
- Assembling a grounded prompt from retrieved chunks.
- Citations a reader can follow back to the source.
- Refusing when retrieval is empty or sources conflict.
- Lab: complete the RAG path and test it on held-out questions.
Golden datasets and evaluators
Quarter day · AI engineering · Intermediate
- Building a golden set from real traffic and expert input.
- Code-based evaluators and LLM-as-judge.
- Calibrating a judge against human labels.
- Lab: build a golden set and score two prompt versions.