CCAR-F domain 1 · 27% of the exam · 17 of 65 questions
Agentic Architecture and Orchestration
The heaviest domain at 27% of a scored form, and the one most sittings turn on. It covers how an agent actually runs: the loop that keeps calling tools until it stops, when work is worth splitting across several agents, what a subagent can and cannot see when it starts, and how a rule is enforced on a model that is free to ignore an instruction. Most items here offer two defensible designs, and the credited one is usually the simpler design that satisfies the constraint the stem has already named.
every one of the 54 pool items in this domain · explanations as you go · free
The 7 objectives in this domain
A real score report grades each of these separately, so a weakness here is addressable at this level rather than by re-reading the whole domain. Each one has its own drill.
The other 4 domains
Drilling one domain tells you about one domain. A full-length timed mock in blueprint proportions is what produces a score you can read.
Sit a timed mock →