Main Flows

What is the Main Flow?

Every Script has exactly one Main Flow. When a call starts:

The Script is loaded
The Main Flow is identified via the Script’s main_flow_id
The assistant begins execution at step 0 of the Main Flow
The conversation continues until an end condition is reached

Main Flow Structure

A Main Flow contains an ordered sequence of steps, each step can branch to other steps or sub-flows based on conditions.

Starting the Conversation

The opening line comes from the first step of the Main Flow that actually speaks: Outbound Calls:

The assistant can wait briefly for the caller to speak
Example: “Hi, this is Sarah from Voxworks.”
To hold the opening until whoever answered has spoken, and choose the opening line based on what they said, start the Main Flow with the Outbound Opening | Message Check tool

Inbound Calls:

The assistant speaks first with a greeting
Example: “Thank you for calling Voxworks. How can I help you today?”

Doing work before the greeting

The Main Flow does not have to start with a voice step. If the first steps are Tool, Code or Flow steps, they run while the call is still connecting — Voxworks works forward through them until it reaches the first step that speaks, and that step’s script becomes the opening line, with its variables already filled in. That means a script can look the caller up in your CRM, check opening hours, or route to the right sub-flow before it says a word, and greet the caller with what it found:

Step 1 (Tool)  Look up the caller in the CRM
Step 2 (Flow)  Route to the right sub-flow for their account type
Step 3 (Voice) "Hi {{contact.first_name}}, I can see your booking for Tuesday —
                are you calling about that?"

Keep those leading steps quick: the caller is waiting through them, so a slow lookup is silence on the line.

From any voice step, conditions determine where to go next:

Condition Type	Description	Example
Specific match	User response matches a defined scenario	”User wants to book” → Booking step
Otherwise	Fallback when no specific condition matches	Clarification step

Knowledge Base and Guidelines

When a user asks a question during the conversation, it is compared against the questions in your Knowledge Base. If one matches, the assistant answers from that entry; if none does, it answers from the step and your Guidelines. If the assistant has information to respond:

The assistant answers the question using available knowledge
The conversation stays on the current step
The assistant continues with the current step’s objective

This allows the assistant to handle ad-hoc questions without derailing the flow. For example:

Step: "Would you like to schedule a demo?"

User: "How much does it cost?"

→ Assistant answers from Knowledge Base: "We offer flexible pricing
  on a cents per minute basis. Would you like to schedule a demo
  to discuss your specific needs?"

→ Conversation remains on the same step, waiting for demo response

If the assistant doesn’t have relevant information, it follows the Guidelines for handling unknown questions (e.g., offering to follow up later).

Ending the Conversation

The Main Flow ends when:

End condition reached — A step’s condition has end_flow: success or fail
User hangs up — The participant disconnects
Maximum duration — The configured time limit is reached
Assistant hangup — The assistant determines the call should end

When the Main Flow ends, the call terminates.

Main Flow vs Sub-Flows

Aspect	Main Flow	Sub-Flow
Entry	Automatic at call start	Invoked by a Flow step
Exit	Ends the call	Returns to parent flow
Required	One per Script	Optional, unlimited
Reusability	Specific to Script	Can be shared across Scripts

Maximising Reusability

While the Main Flow is specific to each Script, you can maximise reusability by keeping it minimal:

Opening message — Greet the caller
Flow step — Route immediately to a reusable sub-flow
Closing messages — Handle success and failure outcomes from the sub-flow

This pattern lets you reuse the core conversation logic across multiple Scripts, with only the opening and closing messages varying per Script.

Interrupts

During a conversation, users can interrupt the assistant while it is speaking. How interrupts are handled depends on the step type:

Step Type	Interruptible	Behaviour
Voice	Yes (default)	User can interrupt; assistant stops speaking and processes the interruption
Tool	No	User cannot interrupt while the tool executes

Any step can be set to Uninterruptible (or one of the other modes) from the Interruptions item on its menu, when you need the assistant to complete critical information without being cut off. See Interruptions. For more on how the assistant handles interruptions, see Assistant Behaviour.

Best Practices

Start with a clear opening — Set expectations immediately
Keep the main path simple — Use sub-flows for complex branches
Handle common objections — Include conditions for typical responses
Plan your exit points — Define clear end conditions
Test the full journey — Walk through every possible path

Next Steps

Sub-Flows — Create reusable conversation modules
Voice Steps — Design interactive conversation turns
Steps Overview — Learn about all step types

Get Started & Build

Calls, Contacts & Batches

Numbers & Routing

Tools, Automations & Integrations

Account, Billing & Security

What is the Main Flow?

Main Flow Structure

Starting the Conversation

Doing work before the greeting

Flow Navigation

Knowledge Base and Guidelines

Ending the Conversation

Main Flow vs Sub-Flows

Maximising Reusability

Interrupts

Best Practices

Next Steps

​What is the Main Flow?

​Main Flow Structure

​Starting the Conversation

​Doing work before the greeting

​Flow Navigation

​Knowledge Base and Guidelines

​Ending the Conversation

​Main Flow vs Sub-Flows

​Maximising Reusability

​Interrupts

​Best Practices

​Next Steps

What is the Main Flow?

Main Flow Structure

Starting the Conversation

Doing work before the greeting

Flow Navigation

Knowledge Base and Guidelines

Ending the Conversation

Main Flow vs Sub-Flows

Maximising Reusability

Interrupts

Best Practices

Next Steps