---
title: "Workflow | AgentRQ Glossary"
url: https://agentrq.com/glossary/workflow
description: "A workflow is a defined sequence of steps that an AI agent follows to complete a task, specifying the order of actions, decision points, and human touchpoints across the process."
---

[Back to Glossary](https://agentrq.com/glossary/)

# Workflow

A **workflow** is a defined sequence of steps that an AI [agent](https://agentrq.com/glossary/agent) follows to complete a task. Workflows specify the order of actions, decision points, tool calls, and [human-in-the-loop](https://agentrq.com/glossary/human-in-the-loop) touchpoints that guide an agent from a starting state to a desired outcome.

## Workflows vs. Agentic Workflows

The term *workflow* is broad. In the context of AI agents, an [agentic workflow](https://agentrq.com/glossary/agentic-workflow) is a workflow where the agent has autonomy to decide its own path rather than following a rigid script.

| Type | Agent Freedom | Human Involvement |
| --- | --- | --- |
| Scripted workflow | Follows fixed steps | Defined checkpoints |
| Agentic workflow | Adapts based on results | Dynamic oversight |

## Components of an Agent Workflow

A typical agent workflow includes:

1. **Trigger** — An event or instruction that starts the workflow
2. **Planning** — The agent determines the approach
3. **Execution** — The agent runs tools and produces outputs
4. **Checkpoints** — Points where the agent pauses for human [approval](https://agentrq.com/glossary/approval) or input
5. **Completion** — The agent signals the workflow is done

## Designing Workflows with AgentRQ

AgentRQ enables you to build [human-in-the-loop](https://agentrq.com/glossary/human-in-the-loop) workflows for [Claude Code](https://agentrq.com/glossary/claude-code) agents. A well-designed AgentRQ workflow looks like:

1. Agent receives a task (e.g., "implement OAuth login")
2. Agent calls `workspace` get to understand project context
3. Agent creates a [task](https://agentrq.com/glossary/task) via `task` create and sets it `ongoing` with `task` updateStatus
4. Agent works autonomously — reading code, writing implementation
5. Agent sends [notification](https://agentrq.com/glossary/notification) via `task` reply when it reaches a decision point
6. Human reviews and responds
7. Agent continues to completion
8. Agent calls `task` updateStatus to mark the task `completed`

## Related Terms

- → [Agentic Workflow](https://agentrq.com/glossary/agentic-workflow)
- → [Task](https://agentrq.com/glossary/task)
- → [Human-in-the-Loop](https://agentrq.com/glossary/human-in-the-loop)
- → [Approval](https://agentrq.com/glossary/approval)
- → [Agent](https://agentrq.com/glossary/agent)