Build with AI, knowing how it actually works
Developers, analysts and operations teams get more from AI when they understand the machinery. Your path starts with the kinds of model and who makes them, then prompting and tool choice for real work, then how large language models produce text: tokens, context windows, temperature and training.
What usually gets in the way
- Tutorials that show one clean demo and skip why it breaks on your data
- A new model or coding tool every month, and no fair way to compare them
- Hand-waving about how models work, when what you want is the mechanism
What changes
- A precise working model of how LLMs generate text, and why they fail where they do
- Fair, dated comparisons of coding agents, app builders and model platforms
- Prompt templates built to survive a model update, and a routine for re-testing them
- The Builder modules on retrieval, APIs, automation, agents, evaluation and security, added to your path as each one is released
What comes first for builders
Everyone gets the same 18 released modules. What differs is the order — and what the placement check lets you skip. For builders, the path leads with these:
- 01Meet the models
Language, image, speech and video models; open and closed; large and small; reasoning models: the kinds of model behind the tools, and who makes them.
- 02Prompting well
Context, examples, structure and iteration: how to ask for what you actually want, and get it the first or second time.
- 03The Tool Atlas: choosing the right tool
The 32 tools that matter, from ChatGPT to n8n: what each is good at, what to watch out for, and how to judge any new one in five questions.
- 04How large language models work
Tokens, embeddings, attention, context windows, temperature and training: what is actually happening when a model answers you.
Find your starting point
Five minutes, no card. You’ll get your level in five skill areas and a path built around being a builder.
Start free