CCA Prep Studio
—

CCA-F study guide · Domain 1: Agentic Architecture & Orchestration (27%)

Task 1.6: Task decomposition strategies

Big jobs need to be split, and there are two ways to split them. Prompt chaining fixes the steps in advance and suits predictable work such as a multi-aspect review. Dynamic decomposition creates the next subtask from what the last one found and suits open-ended investigation. Either way, keep each step focused so attention is not diluted.

Updated 10-26-2026 · Official guide §6, Task 1.6

Key points

  • Fixed sequential pipelines (prompt chaining) fit predictable work; adaptive decomposition fits work that depends on intermediate findings.
  • Prompt chaining for reviews: analyse each file individually, then run a cross-file integration pass.
  • Adaptive plans generate subtasks from what is discovered at each step.
  • Reviewing many files in one pass dilutes attention, producing uneven depth and contradictory findings.
  • Open-ended tasks start by mapping structure and identifying high-impact areas before planning.

Common misconceptions

  • "A bigger context window fixes attention dilution." It does not; focus comes from splitting the work.
  • "Adaptive is always better because it is flexible." It adds variability to work that should be consistent.
  • "Per-file passes alone are enough." Cross-file issues need the integration pass.

Watch for

Single-pass reviews of many files, fixed pipelines applied to investigations, and test plans that skip the structure-mapping step.

Practice Task 1.6

Start with the free 10-question check to see where you stand across all five domains. In CCA Prep Studio, 57 practice items cover this task, each tracked toward your mastery score.

CCA Prep Studio is an independent study product. It is not made, endorsed or sponsored by Anthropic. Claude is a trademark of Anthropic, PBC, and is used here only to name the exam and the technology it covers. Content is written in our own words and cites the official exam guide; no exam questions are reproduced. © 2026 NovaLinQs AI, LLC.