---
id: "concept-planner-sub-agent-architecture"
type: "concept"
source_timestamps: ["00:11:07", "00:11:13"]
tags: ["systems-architecture", "agentic-ai"]
related: ["concept-task-decomposition"]
definition: "A multi-agent design pattern where a central 'Planner' agent orchestrates and delegates discrete tasks to specialized 'Sub-Agents'."
sources: ["s42-job-market-split"]
sourceVaultSlug: "s42-job-market-split"
originDay: 42
---
# Planner and Sub-Agent Architecture

## The pattern

Instead of relying on a single monolithic prompt or agent to handle a complex task, the architecture utilizes a **'Planner'** agent. The Planner's sole responsibility is to:

- Maintain the overall goal.
- Keep a record of required tasks.
- Orchestrate a variety of specialized **'Sub-Agents'**.
- Delegate specific, decomposed tasks to those sub-agents.
- Review their output and determine the next step.

This mimics a human manager overseeing a team of specialists — directly enabled by the [[concept-task-decomposition]] skill.

## Adjacent literature

Frameworks such as **LangGraph** (supervisor nodes) and **CrewAI** (managers) implement this pattern in code, with shared state and failure retries.

## Failure modes to design against

- [[concept-cascading-failure]] — unverified errors flowing down the chain.
- [[concept-tool-selection-error]] — sub-agents picking the wrong API.
- [[concept-specification-drift]] — agents losing track of their original mandate.