Task decomposition: chains vs dynamic plans
How to split complex work for Claude: fixed prompt chains for predictable multi-aspect reviews, parallel sections for independent checks, per-file passes plus a cross-file integration pass for large reviews, and adaptive plans that map, prioritize and re-plan for open-ended tasks.
Design task decomposition strategies for complex workflows
~8 min read · 11 practice questions ·
What the exam expects
- Choose a fixed prompt chain for predictable multi-aspect work and dynamic, adaptive decomposition for open-ended investigation, from signals in the requirement.
- Run independent checks in parallel and sequence steps that depend on another step's output (the schema before its implementers).
- Split a large code review into per-file local passes plus a separate cross-file integration pass to avoid attention dilution.
- Decompose an open-ended task ("add comprehensive tests to a legacy codebase") by mapping structure, finding high-impact areas and writing a prioritized plan that adapts as dependencies appear.
- Run a large mechanical change as a task list, one
claude -pcall per item, piloted on a few items first.
Key terms: prompt chaining (each call processes the previous call's output); sectioning (independent subtasks run in parallel and aggregated); orchestrator-workers (a central model breaks the task down at run time); attention dilution (quality falling as one pass covers too much); adaptive plan (a plan rewritten from intermediate findings).
Key facts
- Detail
- Each call processes the previous output; for fixed subtasks
- Detail
- More latency for higher accuracy; gates on intermediate steps
- Detail
- To inspect intermediate outputs or enforce a pipeline structure
- Detail
- Independent subtasks in parallel, aggregated programmatically
- Detail
- Subtasks determined at run time; e.g. file count depends on the task
- Detail
- Per-file local passes plus a cross-file integration pass
- Detail
- Lead agent decides whether more research is needed and spawns more subagents
- Detail
- Short, broad queries first, then narrow
- Detail
- Refine the prompt on the first 2-3 files, then run the full set
Sources for this section (5)
- Building effective agentswww.anthropic.com (opens in a new tab)
- Prompting best practicesplatform.claude.com (opens in a new tab)
- Exam Guideeverpath-course-content.s3-accelerate.amazonaws.com (opens in a new tab)
- Multi-agent research systemwww.anthropic.com (opens in a new tab)
- Best practicescode.claude.com (opens in a new tab)
- When should you choose orchestrator-style dynamic decomposition over a prompt chain?
- Why does a separate cross-file integration pass catch bugs that per-file passes miss?
- What do you gain and lose by turning one generation call into a three-step chain?
- Why should research subagents start with short, broad queries?
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 (11 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.