| 1 | Coding with AI agents | Pick a coding agent, work out what it costs, and make it reliable in your repository. |
| 2 | Models, APIs and plans | Choose a model tier by task, then a vendor; read prices and vendor scores critically. |
| 3 | Building agents | Add a tool, a Skill or an MCP server to the agent you use, or write your own loop. |
| 4 | Retrieval, context and memory | Decide which material reaches the context and what persists across sessions. |
| 5 | Evaluation and evidence | Test a model or system on your own task, and judge what other people’s scores show. |
| 6 | Running locally | Decide whether to run a model on your machine at all, then pick a setup that fits and is fast enough. |
| 7 | How LLMs work | Follow one prompt through tokens, decoding, attention, the KV cache and post-training. |
| 8 | ML and deep-learning foundations | Reference shelf: classical learning, neural building blocks, generative models and data, for readers who train their own models. |