---
title: "Map-Reduce · agent topology · Agent Fieldbook"
url: https://agentfieldbook.org/design/topologies/map-reduce/
description: "Fan-out across data partitions in parallel; a reduce node aggregates the outputs. Built-in parallelism."
section: "Design · Topologies"
source: Agent Fieldbook — generated from the published page
---

# Map-Reduce

Fan-out across data partitions in parallel; a reduce node aggregates the outputs. Built-in parallelism.

A map-reduce agent splits a job across partitions, processes each in parallel, then aggregates the partial results in a reduce step. It is the classic parallel shape: the same operation applied independently to many pieces, then combined, so throughput scales with the number of workers. It suits embarrassingly-parallel work over large inputs, where the pieces do not depend on each other. In anatomy terms it is a coordinator that fans work out to identical scoped cores and folds their outputs back together.

## In the anatomy

A coordinator maps the input across N identical worker cores in parallel, then a reduce core aggregates their outputs; workers are independent and hold no shared state; the perimeter gates the coordinator's writes.

## At a glance

| Field | Value |
| --- | --- |
| Pattern | Map-Reduce |
| State model | stateless |

## Common use cases

## Strengths

## Weaknesses

## Basis

Description, use cases and trade-offs: Field Book analysis, synthesised from established agent-architecture literature.