> ## Documentation Index
> Fetch the complete documentation index at: https://www.voiceflow.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Playbooks and workflows

> Definitions for playbooks and workflows, with explanations of how each term fits into Voiceflow and links to the related documentation.

## Playbooks and workflows

### Framework

The choice made when a project is created. Agentic (recommended): the agent uses playbooks,
workflows, tools and reasoning to navigate conversations on its own. Conversation flow: you design the
path in the visual builder and the agent follows it step by step.

**Also asked as:**
- difference between an agentic project and a conversation flow project
- should I let the AI decide or draw every branch myself
- which project type to pick when starting

**Related:** [Playbook](#playbook) · [Workflow](#workflow)

**Documented in:** [Choosing a framework › Agentic vs. Conversation flow](/docs/documentation/build/framework/choosing-a-framework#agentic-vs-conversation-flow)

### Playbook

Agentic. Instructions driving toward a goal, calling tools as needed. Use for open-ended work:
booking, qualifying, handling a return.

**Also asked as:**
- an AI skill that works toward a goal using tools
- let the model handle an open-ended task on its own
- the agentic alternative to a drawn flow

**Related:** [Workflow](#workflow) · [Crew](#crew) · [Playbook step](/docs/resources/glossary/build/steps#playbook-step) · [Entry conditions](#entry-conditions)

**Documented in:** [Playbooks](/docs/documentation/build/playbooks) · [Playbooks › Writing good instructions](/docs/documentation/build/playbooks#writing-good-instructions) · [Build (API)](/docs/api-reference/sections/build)

### Workflow

Deterministic. Steps drawn on a canvas from the Start chip. Use where the path must be fixed:
authentication, IVR menus, scripted onboarding.

**Also asked as:**
- a fixed step-by-step flow on the canvas
- a scripted path the conversation must follow exactly
- the deterministic alternative to a playbook

**Related:** [Playbook](#playbook) · [Step](#step) · [Workflow step](/docs/resources/glossary/build/steps#workflow-step) · [Nesting workflows](#nesting-workflows)

**Documented in:** [Workflows](/docs/documentation/build/workflows) · [Workflows › Steps](/docs/documentation/build/workflows#steps)

### Step

One node on a workflow canvas. Named with only the first word capitalised: Message step, API step,
Function step. Steps come in four categories: agentic, conversation, logic and tools.

**Also asked as:**
- a block on the canvas
- the building pieces of a flow
- the individual pieces I drag onto the canvas
- what each box in a workflow does

**Related:** [Workflow](#workflow) · [Actions](#actions)

**Documented in:** [Workflows › Steps](/docs/documentation/build/workflows#steps)

### Actions

Steps attached to a port without being drawn on the canvas, keeping the canvas clean without losing
any functionality.

**Also asked as:**
- attach something to a port without cluttering the canvas
- hide small steps behind a connection
- tuck a small step behind a connector
- keep the canvas tidy

**Related:** [Step](#step)

**Documented in:** [Workflows › Actions](/docs/documentation/build/workflows#actions)

### Nesting workflows

Calling one workflow from another with the Workflow step, so a process is built once and reused.

**Also asked as:**
- reuse a flow inside another flow
- call a sub-flow from the main one
- break a big process into smaller flows
- a workflow that calls another workflow

**Related:** [Workflow step](/docs/resources/glossary/build/steps#workflow-step)

**Documented in:** [Workflows › Nesting workflows](/docs/documentation/build/workflows#nesting-workflows)

### Entry conditions

Deterministic checks that must evaluate to true before the agent can route to a playbook or workflow.
While they fail, it stays unavailable. They apply only when the agent routes there directly.

**Also asked as:**
- only allow a skill once a condition is met
- gate a playbook behind a check
- the agent should not route to a flow until something is true

**Related:** [Required variables](#required-variables) · [Exit conditions](#exit-conditions)

**Documented in:** [Playbooks › Entry conditions](/docs/documentation/build/playbooks#entry-conditions) · [Workflows › Entry conditions](/docs/documentation/build/workflows#entry-conditions)

### Required variables

Variables that must hold a value before the agent can route into a playbook or workflow. Until every
one is filled, the playbook or workflow stays unavailable.

**Also asked as:**
- don't start the booking skill until we know the customer's email
- a playbook that needs certain details before it can run
- force the agent to collect information first

**Related:** [Entry conditions](#entry-conditions) · [Variable](/docs/resources/glossary/knowledge-and-data#variable)

**Documented in:** [Playbooks › Required variables](/docs/documentation/build/playbooks#required-variables) · [Workflows › Required variables](/docs/documentation/build/workflows#required-variables)

### Exit conditions

Situations in which a playbook hands control back to the workflow through a named path. They apply
when the playbook runs through a Playbook step (or globally on a Crew step); when the agent routes to
the playbook directly they are ignored.

**Also asked as:**
- leave a skill and carry on with the flow when something happens
- get out of the AI part back into the fixed steps
- a playbook inside a workflow that should stop under a condition

**Related:** [Playbook step](/docs/resources/glossary/build/steps#playbook-step) · [Crew](#crew) · [Entry conditions](#entry-conditions)

**Documented in:** [Playbooks › Exit conditions](/docs/documentation/build/playbooks#exit-conditions) · [Playbook step › Exit conditions](/docs/documentation/build/steps/playbook#exit-conditions) · [Crew › Exit conditions](/docs/documentation/build/steps/crew#exit-conditions)

### Initialization workflow

A workflow that runs before the agent takes control of a conversation: load context from your
systems into variables, send a fixed greeting, verify identity, or collect required details up front.

**Also asked as:**
- run something before the first message
- check who the visitor is before the assistant speaks to them
- fetch account data at the start of every session

**Related:** [Workflow](#workflow) · [Start message](/docs/resources/glossary/build/agent-setup#start-message) · [Transaction safety](/docs/resources/glossary/build/agent-setup#transaction-safety)

**Documented in:** [Initialization workflow › Setting an initialization workflow](/docs/documentation/build/framework/initialization-workflow#setting-an-initialization-workflow) · [Initialization workflow › Authentication](/docs/documentation/build/framework/initialization-workflow#authentication) · [Initialization workflow › Loading context](/docs/documentation/build/framework/initialization-workflow#loading-context) · [Initialization workflow › Onboarding](/docs/documentation/build/framework/initialization-workflow#onboarding)

### Crew

Groups several playbooks so they hand off to each other inside one step, rather than routing through a
separate agent. Lower latency than routing out and back. A root playbook is triggered first; exit
conditions are global to the crew.

**Also asked as:**
- several skills working together in one step
- pass control between playbooks without going back to the router
- a team of sub-agents inside a workflow

**Related:** [Playbook](#playbook) · [Exit conditions](#exit-conditions)

**Documented in:** [Crew › Using the Crew step](/docs/documentation/build/steps/crew#using-the-crew-step) · [Crew › Configuration](/docs/documentation/build/steps/crew#configuration)


### Legacy steps

The steps and concepts from the V3 canvas that no longer exist in V4, and what replaced each: the AI
Response step (now the Message step's prompt mode), the AI Set step, NLU intent classification,
flows/topics/components, explicit intent triggers, and the Choice step (now Buttons or a Playbook step).

**Also asked as:**
- which old steps are gone in the new version
- what happened to the AI Response step
- migrating a V3 agent to V4

**Related:** [Message step](/docs/resources/glossary/build/steps#message-step) · [Buttons step](/docs/resources/glossary/build/steps#buttons-step) · [Operator step](/docs/resources/glossary/build/steps#operator-step)

**Documented in:** [V4 migration guide](/docs/v4-migration-guide) · [V4 migration guide › AI Response Step (Deprecated)](/docs/v4-migration-guide#ai-response-step-deprecated) · [V4 migration guide › Choice Step (Legacy)](/docs/v4-migration-guide#choice-step-legacy)

### Message

The fixed text the agent says: what a workflow step or its reprompt says, and what a tool says when
it starts, finishes, fails or is delayed. A message holds one or more variants, which are alternatives,
each with its own text, an optional delay and an optional condition.

**Also asked as:**
- the exact words a step says
- give a response a few different wordings
- what the agent says while a tool is running

**Related:** [Step](#step) · [Workflow](#workflow) · [Agent tools](/docs/resources/glossary/build/agent-setup#agent-tools)

**Documented in:** [Workflows › Steps](/docs/documentation/build/workflows#steps) · [Build (API)](/docs/api-reference/sections/build)


### Playbook path

A named exit from a playbook, with the exit condition the model reads to decide when to take it. Each
path becomes an output port on the Playbook step that runs the playbook, so the workflow can carry on
from whichever path the playbook leaves by.

**Also asked as:**
- the named ways a playbook can finish
- connect what the playbook decided to the next steps of the flow
- add an exit to a skill so the workflow can branch on it

**Related:** [Exit conditions](#exit-conditions) · [Playbook](#playbook) · [Playbook step](/docs/resources/glossary/build/steps#playbook-step)

**Documented in:** [Playbooks › Exit conditions](/docs/documentation/build/playbooks#exit-conditions) · [Build (API)](/docs/api-reference/sections/build)