---
title: "Sequential · agent topology · Agent Fieldbook"
url: https://agentfieldbook.org/design/topologies/sequential/
description: "Linked nodes in a horizontal pipeline; each output feeds the next."
section: "Design · Topologies"
source: Agent Fieldbook — generated from the published page
---

# Sequential

Linked nodes in a horizontal pipeline; each output feeds the next.

Verified against [anthropic.com](https://www.anthropic.com/engineering/building-effective-agents)

- [anthropic.com](https://www.anthropic.com/engineering/building-effective-agents)

A sequential agent runs as a fixed pipeline: each node takes the previous node's output, transforms it, and passes it on, in a set order, until the last node produces the result. There is no re-planning and no loop; the path is decided in advance. It is the simplest and most predictable shape, because every run follows the same steps, which makes it easy to trace, test and cost, but unable to adapt when a step's output is surprising. In anatomy terms it is a chain of scoped reasoning or effector stages with no central orchestrator.

## In the anatomy

A fixed chain of stages, each a scoped model call or effector, wired output-to-input; no orchestrator and no feedback loop; the perimeter gates any external write within the chain.

## At a glance

| Field | Value |
| --- | --- |
| Pattern | Sequential |
| State model | session |
| Example | Document/data pipelines |

## Common use cases

## Strengths

## Weaknesses

## Agents using this pattern · 24

Mapping classified by the Field Book from each agent's documented control flow.

## Basis

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

## Verified against

- [https://www.anthropic.com/engineering/building-effective-agents](https://www.anthropic.com/engineering/building-effective-agents)

The corpus does not rewrite vendor documentation. Where copy is quoted verbatim it is marked as such and attributed to its source.