Learning paths
Ordered reading lists that take you through a field one stage at a time, from the basics to production.
All learning paths
Agentic AI: from your first agent to production
A step-by-step learning path for agentic AI: how agents plan and call tools, which frameworks and protocols to use, and how to run agents safely in production.
Building with large language models
A step-by-step learning path for building with LLMs: how the models work, prompting and context, retrieval, fine-tuning, and serving and evaluating them.
Machine learning foundations
A step-by-step learning path for machine learning: the core models from linear regression to gradient boosting, and how to evaluate, tune and trust them.
Deep learning essentials
A step-by-step learning path for deep learning: how neural networks learn, the main architectures from CNNs to transformers, and how to train them well.
From tabular machine learning to large tabular foundation models
A step-by-step learning path for AI on tables: classical boosted trees, deep tabular models, in-context learning and large tabular foundation models.
Shipping machine learning to production
A step-by-step learning path for MLOps: packaging and running models, tracking experiments, serving at scale, monitoring in production and AI governance.
How these paths work
Each path is an ordered reading list of guides and articles on this site, grouped into stages. The steps show each page's own summary, and the paths are updated as new guides are published.