liveBook · Manning

Decomposition

As explained in Agent Design Patterns

The division of a complex task or workflow into smaller, focused units.

A single agent asked to reason across a sprawling archive may miss details even when the input fits its context window. It may also choose the wrong tool or make a consequential change without enough experimentation. Decomposition addresses these limits by dividing work into smaller units whose inputs, responsibilities, and outputs can be controlled more closely. section 3.1 section 8.0

Two useful boundaries are the workflow and the input:

  • Split an agent workflow into flow-controlling components, which decide what runs next, and action-performing components. A leaf action can be an errand: a focused intelligent subroutine with unidirectional information flow and no direct effect on agent state. section 3.1 section 3.5
  • Split a large input using Decompose-Process-Recompose (DPR). Divide it into fitting fragments, process each fragment, then combine the intermediate results into one answer. The decomposition should preserve the information needed for recomposition. section 8.2
Figure 8.1 The AFD of the DPR pattern. The input is first decomposed into fragments. Each fragment is then fed to an instance of the processor IE, which produces an intermediate result per fragment. The intermediate results are then gathered and passed into the recomposer, which produces the final result.

The data-flow diagram makes the DPR boundary explicit: fragments go to processor instances, and their intermediate results converge at a recomposer. section 8.2

Processing a large archive

For an archive too large for reliable direct analysis, partition the input into manageable fragments, run the focused operation on each, and recompose the results into a global answer. Map-reduce document summarization is one application; recomposition should not leave the final answer looking like disconnected fragments. section 8.0 section 8.2 section 8.5

The trade-off is orchestration and cost. Separate errands can improve focus, testing, maintenance, and parallel execution, but repeated shared context across model calls adds overhead. Input decomposition likewise needs a recomposition step; merely splitting work does not produce a coherent final result. section 3.2.1 section 3.5 section 8.2

How Agent Design Patterns covers it

How deep it goes
Explains a component hierarchy and DPR’s decomposition, processing, and recomposition data flow, including properties of fragments and final results.
Examples
Uses batched file processing, large archives, and map-reduce document summarization to illustrate focused work and fragmented-input processing.
What you can do after
Apply it via Errand and DPR patterns to organize agent actions or process large inputs as focused, recomposable units.
How it connects
Connects decomposition to errands, model context limits, orchestration, and Decompose-Process-Recompose.

Also explained in

Compare how 11 books explain decomposition →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Agent Design Patterns. The section links point to the parts of the book it draws on.