Product and Model Selection

4 build exercises to practise the concepts in this domain.

3.1 — Audit Your Feature Choices

How to identify the kind of task before choosing a feature
How to name the dominant signal that picks each feature
How to spot the manual workaround in your own working pattern
How to decide when a recurring task deserves a Project

3.2 — Match a Week of Tasks to Tiers

How to label tasks as routine-at-volume, everyday middle, or high-stakes synthesis
How to check which models your own account offers in the picker
How to run a routine task on a lighter tier with a sampled quality check
How to name what depth gives you on a genuinely demanding task

3.3 — Assess a Mixed Workload in Three Currencies

How to name the currency a task needs most: cost, time or depth
How to run bulk work on a lighter tier with a sampled review
How to send a high-stakes output to the capable tier plus qualified human review
How to catch decisions made by prestige or by the habit of using one tier for everything in your own week

3.4 — Run the Handover Discipline on Your Longest Chat

How to extract a summary of decisions, current state and remaining work from a long conversation
How to verify a summary against source records before trusting it
How to open a fresh conversation from a verified brief
How to sort working outputs into three groups: paste into the next chat, artifact, and Project knowledge
How to test what memory does and does not carry into a new chat