27% of exam score
Agentic Architecture & Orchestration
The biggest domain. Loops, orchestration, guardrails.
Designing systems where an LLM decides its own next step: agentic loops, subagents, orchestration patterns, and the guardrails that keep them safe in production.
Key insight
Subagents do NOT share memory with the coordinator and do NOT inherit conversation history. Every piece of context must be passed explicitly in each subagent prompt. This is the single most misunderstood concept on the exam.
The exam rewards
- Determine loop completion using stop_reason — never parse natural language signals or apply arbitrary iteration caps
- For financial or security-critical operations, enforce tool ordering programmatically with hooks; prompt instructions alone have a non-zero failure rate
- In hub-and-spoke orchestration, all communication routes through the coordinator — subagents never communicate directly with each other
- Emit multiple Task tool calls in a single response to spawn subagents in parallel and reduce round-trip latency
- Trace failures to their root cause: a research report missing entire topic areas is a coordinator decomposition failure, not a subagent failure
Common anti-patterns
- Parsing natural language to detect when the agentic loop should stop
- Treating iteration caps as the primary stopping mechanism
- Assuming subagents automatically inherit the coordinator's context
- Using prompt instructions to enforce critical business rules