course contents
Associate Foundations · 12% of the exam
product and model selection
share
This exam domain is about an eighth of the exam. It covers two choices you make before Claude writes a word: which part of the Claude apps the work belongs in, and which model family does it. It also covers what to do when a long conversation stops holding what was agreed at its start.
Every domain follows Wrenfield Housing, the course's own example rather than an exam scenario. Wrenfield is a regional, not-for-profit housing provider with about 300 staff. Its operations, communications and project teams use Claude on the organisation's Team plan. Its AI policy has two rules: tenants' personal data stays out of anything sent to Claude unless it is anonymised first, and a person checks anything that goes to tenants, the board or the regulator.
Domain 3 gives Wrenfield's teams their choices of tool. The communications team stops pasting its style guide into a new chat every week and gives the weekly letters a home of their own (3.1). Two operations officers get different answers to the same request because one chat was left on a different model family (3.2). The appointment confirmations move to a faster family, and the board's case stays on the most capable one (3.3). The annual report's long chat is restarted from a checked summary, and its style decisions are kept where every colleague will find them (3.4).
Start hereThe words used throughout this domain
- Project
- A workspace in the Claude apps whose instructions and knowledge files Claude uses in every chat inside it, which a Team plan can share (3.1).
- model family
- One of Claude's lines of models: Haiku, the fastest; Sonnet, the balance of speed and intelligence; Opus, the most capable of the guide's three (3.2).
- usage limit
- The amount of Claude use a plan allows over a period. On a Team plan it is per member, with a five-hour session limit and a weekly limit (3.3).
- extended thinking
- A setting that lets Claude spend more time breaking down a problem before it answers: slower, and heavier on your usage limit (3.3).
- context window
- The limit on how much text Claude can work with at once in a chat, counted in tokens (small pieces of text): messages, files and a Project's knowledge files together (3.4).
- memory
- The feature that lets Claude carry what it learns about your work between your own chats. It belongs to one member, not to a team (3.4).