You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
subtitle: Learn about Vapi's visual builder for creating robust, deterministic conversation flows.
4
-
slug: workflows/overview
5
-
description: Learn about Vapi's visual builder for creating robust, deterministic conversation flows.
3
+
subtitle: Learn to create robust, deterministic conversation flows with a visual builder.
6
4
---
7
5
8
6
## Introduction
9
7
10
8
Workflows is a visual builder designed for creating robust, deterministic conversation flows. It empowers developers and low-code builders to design agents through an intuitive interface representing interactions via nodes and edges.
***Complex flow management** - Ideal for scenarios with numerous interaction paths, such as call centers, customer support, appointment scheduling, and onboarding processes
16
-
***Reliable determinism** - Offers stronger control compared to single-prompt Assistants, ensuring predictable conversational paths even in highly complex flows
17
-
***Developer-focused flexibility** - Fully configurable via API, enabling selection of models, transcribers, and voices available throughout the Vapi platform
14
+
## Key Benefits
18
15
19
-
## Common use patterns
16
+
-**Visual Conversation Builder:** Easily prototype and demonstrate conversation flows visually.
17
+
-**Complex Flow Management:** Ideal for scenarios with numerous interaction paths, such as call centers, customer support, appointment scheduling, and onboarding processes.
18
+
-**Reliable Determinism:** Offers stronger control compared to single-prompt Assistants, ensuring predictable conversational paths even in highly complex flows.
19
+
-**Developer-Focused Flexibility:** Fully configurable via API, enabling selection of models, transcribers, and voices available throughout the Vapi platform.
20
+
-**Multilingual Support:** Seamlessly build multilingual conversation flows with language-specific nodes and prompts.
20
21
21
-
***User intent manager** - Route user interactions based on specific intents
22
-
***Human escalation paths** - Allow users to transfer to human agents at any workflow stage
23
-
***Customer-specific flows** - Differentiate workflows based on user profiles, such as new versus existing customers
22
+
## Common Use Patterns
24
23
25
-
## Workflows structure
24
+
-**User Intent Manager:** Route user interactions based on specific intents.
25
+
-**Human Escalation Paths:** Allow users to transfer to human agents at any workflow stage.
26
+
-**Multilingual Flows:** Create dedicated conversation branches for different languages.
27
+
-**Customer-Specific Flows:** Differentiate workflows based on user profiles, such as new versus existing customers.
26
28
27
-
Workflows consist of nodes and edges. There are multiple types of nodes and a Workflow must have a start node, which is the main entry point for the conversation flow.
29
+
## Workflow structure
28
30
29
-
By default a Conversation Node is the start node, but it can be changed to a different type of node. Start nodes cannot be deleted and a Workflow must have exactly one.
31
+
Workflows consists of node and edges. There are multiple types of nodes and a Workflow must have a start node, which is the main entry point for the conversation flow.
30
32
31
-
---
33
+
By default a Conversation Node is the start node, but it can be changed to a different type of note. Start nodes cannot be deleted and a Workflow must have exactly one.
32
34
33
-
## Node types
35
+
## Node Types and Configuration
34
36
35
-
###Conversation Node
37
+
## Conversation Node
36
38
37
39
The Conversation Node is the default type of node. It's highly configurable and it's the main building block for conversation flows.
Specify the initial spoken message when entering the node. This configuration is helpful if developers want the agent to speak first without waiting for user to say something.
51
+
52
+
#### Prompt
53
+
54
+
Provide detailed instructions guiding agent responses and conversation direction, including response style and content.
55
+
56
+
The prompt is the most important part of the Conversation Node. Building reliable and high-quality voice agents heavily depend on the quality of the prompt supplied.
57
+
58
+
#### Global Node
59
+
60
+
Allows routing to this node from any point in the workflow, commonly used for escalation purposes e.g. when user wants to jump from the pre-determined conversation flow to speaking to a human to address specific needs. This feature can be enabled via the Global toggle; developers must specify an Enter Condition that defines the condition for routing to the Global Node.
40
61
41
-
***First Message** - Specify the initial spoken message when entering the node
42
-
***Prompt** - Provide detailed instructions guiding agent responses and conversation direction
43
-
***Global Node** - Allows routing to this node from any point in the workflow
44
-
***Model/Voice/Transcriber Settings** - Individually configure AI model, voice, and transcription services per node
45
-
***Extract Variables** - Gather variables from conversation using liquid syntax `{{ variable_name }}`
62
+
#### Model/Voice/Transcriber Settings
46
63
47
-
#### Variable extraction
64
+
Individually configure the AI model, voice, and transcription services per node. This is similar to configuring Single Prompt Assistants.
65
+
66
+
#### Extract Variables
67
+
68
+
Extract Variables lets users gather/extract variables from a conversation. These variables can be used as dynamic variables for the rest of the workflow via liquid syntax `{{ variable_name }}`.
48
69
49
70
Variables can be configured by:
50
-
* Defining variable name and data type (String, Number, Boolean, Integer)
51
-
* Writing a clear extraction prompt describing what data to extract
52
-
* Setting enums for String-type variables to constrain values to a specific set
53
71
54
-
### API Request Node
72
+
- Defining variable name and data type (String, Number, Boolean, Integer)
73
+
- Writing a clear extraction prompt (a description of the variable to help determine how/what data to extract)
74
+
- Setting enums for String-type variables to constrain values (to map to a specific set)
The API Request Node allows developers to make HTTP requests to their API, custom endpoints, or automation services like Make, n8n, or Zapier.
80
+
##API Request Node
57
81
58
-
* Configure GET and POST requests
59
-
* Request bodies must be formatted in [JSON Schema](https://json-schema.org/)
60
-
* Body UI builder automatically handles JSON Schema formatting
82
+
The API Request Node allows developers to make HTTP Requests to their API, custom endpoints, or automation services like Make, n8n, or Zapier. Developers can configure it to perform GET and POST requests. Request bodies must be formatted in [JSON Schema](https://json-schema.org/) (the body UI builder automatically does this).
Transfer calls to another phone number, including human agents or specialized voice agents.
65
91
66
-
* Specify a phone number destination
67
-
* Configure a [transfer plan](/call-forwarding#call-transfers-mode) to provide context to the receiving party
68
-
* Include a message or summary of the call before connecting
92
+
Developers can specify a phone number destination and a [transfer plan](https://docs.vapi.ai/call-forwarding#call-transfers-mode), which lets them specify a message or a summary of the call to the person or agent picking up in the destination number before actually connecting the call.
Workflows without a defined End Call Node risk unintended minutes usage. Ensure all workflows have clear termination points to ensure the call eventually ends.
76
108
</Warning>
77
109
78
-
###Tool Node
110
+
## Tool Node
79
111
80
-
Integrate existing Tools library functionalities. Select tools previously created for use within Workflows, maintaining consistency with Assistant configurations.
112
+
Integrate existing Tools library functionalities. Select tools previously created for use within Workflows, maintaining consistency with Assistant configurations.
A node is connected to another node via an edge. Developers can specify a condition (within the edge) that must be true (satisfied) for the conversation to flow from one node to the next.
A node is connected to another node via an edge. Developers can specify a condition (within the edge) that must be true for the conversation to flow from one node to the next.
87
126
88
127
### Types of conditions
89
128
90
129
**AI-based conditions** - Written in plain language and evaluated by LLMs:
91
130
```txt
92
-
User wants to talk about voice agents
131
+
User wanted to talk about voice agents
93
132
```
94
133
95
134
**Logical conditions** - For precise control using variables:
@@ -105,11 +144,12 @@ User wants to talk about voice agents
105
144
### Best practices for conditions
106
145
107
146
* Use descriptive, natural language for AI-based conditions
147
+
* Format conditions as: "User [verb][rest of condition]"
108
148
* Extract variables as enums to enable reliable branching
109
149
* Test all conditional paths thoroughly
110
150
* Keep conditions simple and specific
111
151
112
-
---
152
+
A useful combination of features is to extract variables as enums and use them to branch conversation flows based on a specific set of tasks that the agent can help users with.
113
153
114
154
## Best practices
115
155
@@ -140,4 +180,4 @@ Ready to start building? Check out these resources:
140
180
*[**Workflows quickstart**](/workflows/quickstart) - Build your first workflow step-by-step
141
181
*[**Workflow examples**](/workflows/examples) - Explore pre-built workflows for common use cases
142
182
*[**Custom Tools**](/tools/custom-tools) - Integrate external APIs and services into your workflows
143
-
*[**Dynamic Variables**](/assistants/dynamic-variables) - Advanced variable usage and personalization techniques
183
+
*[**Dynamic Variables**](/assistants/dynamic-variables) - Advanced variable usage and personalization techniques
0 commit comments