State

State is the information that describes a system or task at a particular point and is carried into later steps.

Plan for this page

Understand one concept in plain language and connect it to nearby ideas.

You will leave with: State can include completed actions, pending work, tool results, variables, plans, approvals, errors, or environment observations. Some state is temporary; some is stored durably and then also becomes a memory and governance concern.
Time: 3–8 min
Before you begin: No prerequisite. Keep one real example in mind.
Do this now: Read the explanation, then compare the example with the common misunderstanding.

Prepared next stepFollow state through an agent loop

StateState is the information that describes a system or task at a particular point and is carried into later steps.

Agent
Workflow
Memory

Plain explanation

State can include completed actions, pending work, tool results, variables, plans, approvals, errors, or environment observations. Some state is temporary; some is stored durably and then also becomes a memory and governance concern.

Example

A booking system records selected flights, passenger details, current price, pending approval, and whether payment has occurred.

Why it matters

Correct continuation depends on accurate, current, and authorized state. Lost, duplicated, stale, or tampered state can cause repeated or inappropriate action.

Common misunderstanding

Misconception: state is only the chat transcript. Correction: it can include structured records and external environment changes beyond conversation text.

Related concepts

Follow relationships, not only the alphabet

AgentAn AI agent is a system that continues across steps toward a goal and can select or use actions, tools, or information within defined controls.WorkflowA workflow is an organized sequence of tasks, decisions, handoffs, information, and checks used to produce an outcome.MemoryMemory is information a system retains or can retrieve for use beyond the immediate step or context.

Follow state through an agent loop

Sources and scope

What supports this object

Hugging Face Agents Course — IntroductionHugging Face

Illustrates iterative observations and task progression; state representations and persistence differ across implementations.

Open source

Loading page content...

…