Skip to main content
Your prompt is the primary way you configure how your agent behaves. This guide covers how to structure it, what to include, and what makes voice prompts different from text prompts.
Just getting started? See Prompt Basics first.

How Voice Differs from Text

Voice agents process language differently than chatbots. Keep this in mind when writing. Key principle: Write instructions that produce short, spoken responses — not written ones.

Quick Start: The 5-Minute Prompt Formula

Start here if you’re writing a prompt from scratch.
1

Who is your agent?

Give your agent a clear identity and personality.
2

What is the goal?

Define the specific, measurable outcome.
3

How does the conversation flow?

Map out the key steps in order.
4

What are the guardrails?

Define what your agent should never do and when to escalate.
5

How should it handle objections?

Prepare for common responses with exact wording.

Use this as a template when building out the full prompt.
Keeping these sections in a consistent order makes prompts easier to maintain and review.

Response Length

The most common voice AI mistake is responses that are too long. A response that reads fine as text can take 15+ seconds to speak — callers lose attention, interrupt, or hang up.

What to write

What to avoid

Pacing for important information


Natural Speech Patterns

Conversational flow

Guide the agent to use natural acknowledgment phrases that match how a person would speak:

Avoid written language

Some phrases read fine but sound robotic when spoken:

Numbers and dates


Conversation Structure

Opening

Keep it short. The caller wants to get to their reason for calling.

Turn-taking

Closing


Handling Difficult Moments

When the agent doesn’t know

When the caller is frustrated

When the caller goes off-topic

When collecting sensitive information


Writing Principles

Voice agents need conversational language, not corporate speak.Avoid:
Better:
Test: read it aloud. If it sounds stiff, simplify it.
Vague instructions leave too much room for inconsistency. Give enough detail that the agent knows what you mean — without scripting every word verbatim.Avoid:
Better:
Scripting exact sentences can help for critical moments like greetings or legal disclosures. For the rest, describe the intent and let the agent find natural phrasing.
Handle different scenarios with conditional logic.
Plan for success, objections, and edge cases.
Help the agent move smoothly between conversation stages.
Always verify critical information before taking action.

Referencing Tools

Always reference tools by the exact name configured in the UI. The agent uses that name to trigger the tool — ambiguous wording can break execution.

Example: Booking tool

Example: Transfer tool


Variables and Conditional Content

Use Jinja templating to personalize your prompt with dynamic values from contacts and context.
See Variable Sources and Template Syntax for the full reference.

Testing Your Prompts

  1. Read it aloud — if it sounds unnatural spoken, it will sound worse from the agent
  2. Time test responses — responses over 15 seconds need shortening
  3. Test interruptions — speak while the agent is talking to check handling
  4. Test edge cases — ask questions outside scope, give wrong information, stay silent
  5. Review recordings — listen to actual calls, not just transcripts

Next Steps

Template Syntax

Personalize prompts with dynamic values

Custom Pronunciations

Fix mispronounced words

VAD Turn Detection

Control conversation timing