Objective 3.8 · Domain 3 · 19% of the exam
Evaluate progressive discovery vs. monolithic context strategy
Progressive discovery against loading everything up front. Handing an agent a small entry point and letting it fetch what it needs keeps context small and scales to corpora that would never fit; loading everything is simpler and lower-latency when the material is genuinely small and bounded. The exam tests the judgement rather than a preference, so a stem describing a fixed, small reference set is not asking for progressive discovery.
4 questions · answers and explanations shown as you go · free, no sign-up
The rest of domain 3: Integration
This domain is 19% of a scored form, about 12 of the 63 questions, spread across 8 objectives. Drill the whole domain or pick another objective below.
- 3.1Evaluate tool/agent configuration for capability bloat(5)
- 3.2Analyze authentication and authorization requirements to identify security gaps(5)
- 3.3Evaluate accuracy-latency trade-offs and justify configuration decisions(5)
- 3.4Analyze observability challenges and select monitoring strategies at scale(5)
- 3.5Design a RAG pipeline with appropriate chunking and indexing strategies(5)
- 3.6Apply retrieval strategies matched to data shape and query pattern(5)
- 3.7Evaluate connection protocols and select the appropriate integration mechanism (MCP, API/CLI, agent-to-agent)(4)
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 →