Objective 1.3 · Domain 1 · 17% of the exam
Select appropriate architectural patterns (workflow, agentic, augmented LLM)
Choosing between a fixed workflow, an augmented LLM and an agentic loop. The governing principle is that agency is a cost rather than a feature: an agent that plans its own steps is harder to test, harder to bound and slower. Pick the simplest pattern whose failure modes you can live with. When a stem emphasises predictability, auditability or a fixed sequence, it is pointing at a workflow even if it uses the word "agent".
6 questions · answers and explanations shown as you go · free, no sign-up
The rest of domain 1: Solution Design & Architecture
This domain is 17% of a scored form, about 11 of the 63 questions, spread across 6 objectives. Drill the whole domain or pick another objective below.
- 1.1Translate business problems into Claude-based AI solutions(6)
- 1.2Design end-to-end architectures (input → processing → output → feedback loops)(6)
- 1.4Design multi-agent systems and orchestration strategies(5)
- 1.5Apply decomposition techniques for complex problem solving(5)
- 1.6Align solutions to business value pillars (efficiency, transformation, productivity, cost, performance SLAs)(6)
One objective is a narrow slice. A full-length timed mock is what tells you whether the whole thing holds together.
Sit a timed mock →