Coordinator-subagent orchestration
How a coordinator agent routes, scopes and checks the work of specialist subagents: hub-and-spoke communication, description-based selection, effort scaling, scope partitioning, the gap-filling refinement loop, when multi-agent is worth its token cost, and how to cap and trace the agent tree.
Orchestrate multi-agent systems with coordinator-subagent patterns
~8 min read · 14 practice questions ·
What the exam expects
- Design a coordinator that owns decomposition, delegation, routing, error handling, logging and aggregation, with all subagent traffic flowing through it.
- Make the coordinator select only the subagents a query needs and scale effort to query complexity, triggered by clear
descriptiontext or by naming the subagent. - Partition scope across subagents to avoid duplicated work, and recognise over-narrow decomposition as the cause of missing coverage.
- Add an iterative refinement loop: evaluate the synthesis for gaps, re-delegate targeted queries, re-synthesize.
- Decide when multi-agent is worth its token cost, and cap and trace the agent tree with enforced limits.
Key terms: coordinator (lead agent that plans, delegates and synthesizes); hub-and-spoke (subagents talk only to the coordinator, never to each other); effort scaling (subagent count and tool calls matched to query complexity); spawn depth (how many layers of subagents may nest).
Key facts
- Detail
- Claude matches the task to each subagent's
description
- Detail
- Name it in the prompt; bypasses automatic matching
- Detail
- 1 agent / 3-10 calls; 2-4 subagents / 10-15 calls each; 10+ subagents for complex research
- Detail
- Objective, output format, tools and sources, task boundaries
- Detail
- Save plan, constraints and finished subtasks to external memory; re-read after truncation
- Detail
- Agents about 4× chat; multi-agent about 15× chat
- Detail
- 3 layers;
1stops nested spawning
- Detail
- 20
- Detail
max_budget_usdincludes subagents; ends witherror_max_budget_usd
- Detail
tool_usename"Agent"(match"Task"too)
- Detail
parent_tool_use_idon messages from inside a subagent
- Why route every subagent message through the coordinator?
- Why should a coordinator in a multi-hour run persist its plan and the user's constraints outside its context?
- When should a prompt name a subagent explicitly instead of relying on its description?
- When is a multi-agent design a poor fit despite its power?
- Which field lets a tracing dashboard attribute streamed messages to the subagent that produced them?
The questions are free to read. Answers with their sources and self-grading are included with the pack.
Keep reading with the Claude Certified Architect - Foundations pack
- Core concepts
- Exam traps
- Worked scenario
The pack includes:
- All 30 lessons of the Claude Certified Architect - Foundations guide, with reading progress
- Interactive decision walks and step-by-step sequence steppers
- Inline practice questions and one-click topic practice (14 questions for this lesson)
- An official source cited for every claim
- An AI tutor that answers from the guide
- Unlimited timed practice exams
Practice for the Claude Certified Architect - Foundations exam
Certifyforce is an independent study resource and is not affiliated with, endorsed by or sponsored by Anthropic. Claude is a trademark of Anthropic.