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

# Prompts And Welcome Messages In DialNexa

> Understand DialNexa prompts, system prompts, welcome messages, conversation start modes, first sentence behavior, and prompt review.

Prompts and welcome messages tell a DialNexa agent what to do and how the call begins. The prompt controls the conversation goal, the system prompt adds higher-level rules, and the welcome message controls the first spoken turn when the agent starts the conversation.

<img src="https://mintcdn.com/dialnexa/0efoAN-6So4r-6NC/images/documentation/screenshots/agent-prompt-editor.png?fit=max&auto=format&n=0efoAN-6So4r-6NC&q=85&s=60f45f90e53a644a08e11e20c0fd3346" alt="DialNexa prompt editor showing the Welcome Message field above detailed Agent Prompt instructions." style={{ width: '100%', maxWidth: '1100px', margin: '8px 0 24px', border: '1px solid #e5e7eb', borderRadius: '6px' }} width="2776" height="1752" data-path="images/documentation/screenshots/agent-prompt-editor.png" />

<Note>
  The first sentence has a job: make the caller stay on the line long enough for the second sentence to matter.
</Note>

## Prompt Fields And Meaning

Write each field for a different purpose.

| Field            | Use it for                                                                                          |
| ---------------- | --------------------------------------------------------------------------------------------------- |
| Prompt text      | The main instructions: goal, script, objections, eligibility rules, tone, and call ending behavior. |
| System prompt    | Higher-level behavior constraints and persistent rules.                                             |
| Agent identity   | Who the agent is in a conversational flow setup.                                                    |
| Agent background | Context the agent should remember while handling flow nodes.                                        |
| Welcome message  | The first message when the agent is configured to start.                                            |

## Variable Syntax Validation

The agent builder validates dynamic variable placeholders before saving, testing, or publishing prompt-related text. Use simple double-brace syntax such as `{{first_name}}`.

| Problem                             | Example          | Fix                                                                   |
| ----------------------------------- | ---------------- | --------------------------------------------------------------------- |
| Unclosed variable                   | `{{first_name`   | End every opening `{{` with `}}`.                                     |
| Empty variable                      | `{{}}`           | Add a variable key.                                                   |
| Extra brace or spacing before close | `{{amount} }`    | Use `{{amount}}`.                                                     |
| Invalid variable name               | `{{first name}}` | Use letters, numbers, underscores, or dots, such as `{{first_name}}`. |

The validation message points to the first affected line and can report additional errors after that. Fix malformed variables before changing the prompt content itself.

## Conversation Start Modes

<Tabs>
  <Tab title="User starts">
    The caller speaks first. Good for inbound calls where the caller has a reason to call.
  </Tab>

  <Tab title="Agent defined">
    The agent uses a fixed welcome message. Good for outbound reminders or introductions.
  </Tab>

  <Tab title="Agent dynamic">
    The first turn can use dynamic values. Good when the greeting needs caller-specific context.
  </Tab>
</Tabs>

## Write Prompt Instructions That Survive Real Calls

<Steps>
  <Step title="Name the caller goal">
    Tell the agent the single most important outcome.
  </Step>

  <Step title="Define what not to do">
    Add boundaries for speculation, pricing, escalation, or unsupported requests.
  </Step>

  <Step title="Use examples">
    Include phrasing for short answers, objections, wrong number, busy caller, and language switch.
  </Step>

  <Step title="Connect tools to intent">
    Tell the agent when to use functions, not just that functions exist.
  </Step>

  <Step title="Make the ending explicit">
    Tell the agent when to end, transfer, schedule, or summarize.
  </Step>
</Steps>

## Prompt Review Questions

<AccordionGroup>
  <Accordion title="Does the agent know success?">
    If success is vague, post-call fields and summaries will be vague too.
  </Accordion>

  <Accordion title="Are variables wrapped correctly?">
    Use placeholders such as `{{first_name}}` and define defaults where needed.
  </Accordion>

  <Accordion title="Does the welcome message match the route?">
    Inbound and outbound openings usually need different wording.
  </Accordion>

  <Accordion title="Can the prompt be shorter?">
    Long prompts are sometimes necessary, but repeated rules and unclear sections make behavior harder to debug.
  </Accordion>
</AccordionGroup>

## Related Reading

<CardGroup cols={2}>
  <Card title="Dynamic Variables" icon="braces" href="/agents/dynamic-variables">
    Add caller-specific values.
  </Card>

  <Card title="Single Prompt Agents" icon="sparkles" href="/agents/single-prompt-agents">
    Use one instruction set.
  </Card>

  <Card title="Testing Agents" icon="phone-call" href="/agents/testing-agents">
    Test the first turn and edge cases.
  </Card>
</CardGroup>
