Objective 3.1 · Domain 3 · 19% of the exam
Evaluate tool/agent configuration for capability bloat
Capability bloat is what happens when an agent is given more tools than the task needs. Every additional tool consumes context, adds a way to select wrongly, and widens the blast radius of a mistake. Expect scenarios where an agent is misbehaving and the credited fix is removing or narrowing its tools instead of improving the prompt that chooses between them.
5 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.
- 3.2Analyze 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)
- 3.8Evaluate progressive discovery vs. monolithic context strategy(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 →