Skip to main content
DialNexa agents can use integration-backed actions when those actions are available to the agent function surface. Use this when the agent should perform a specific external action during the call, such as sending a message after consent or triggering a follow-up.
Do not give a caller-facing agent an integration action just because the action exists. Give it a reason and a rule.

​
Before You Begin

Connect and validate the provider, identify the exact caller intent that should trigger the action, define required fields, and decide what the agent says when the action fails.

​
DialNexa Agent Integration Responsibilities

​
When To Use An Integration During A Call

​
Add An Integration Action To An Agent

1

Connect the integration

Set credentials and validate the connection first.
2

Choose the action

Pick the action that matches the caller-facing outcome, such as a Wati message or Resend email.
3

Write a strict function description

Tell the model when to use the action, what values it needs, and when not to call it.
4

Configure execution speech

In Execution Settings, keep Speak During Execution enabled when an action may take more than 2 seconds, and write the short holding message the caller should hear. The default is One moment please. Enable Speak After Execution only when the agent should announce the result after the action completes.
5

Collect required values

Use dynamic variables if the data is known before the call, or prompt the agent to ask the caller when the data is missing.
6

Test with caller phrases

Test direct requests, vague requests, no-consent cases, and missing-field cases.
7

Review call and invocation evidence

Confirm transcript, action timing, redacted request, provider response, and failure path.

​
Control What The Caller Hears

These settings change spoken behavior, not whether the integration request runs. Test both a fast response and a response longer than 2 seconds so the prompt, holding message, and result announcement do not repeat each other.

​
Agent Integration Risks

Tighten the function description and prompt. Require explicit caller intent or required data before the model can call the action.
Make the trigger condition clearer and test with direct caller language that should call the action.
Add dynamic variables, collect the value during the call, or move the action into a workflow after post-call extraction.
Validate the integration connection again before editing the agent prompt.
Check integration latency. If the action does not need to happen before the agent replies, move it to a workflow.

​
Verify The Agent Integration

Test a successful action, missing field, ambiguous caller request, and provider failure. Confirm the action runs only when intended and that the agent communicates the result accurately.

Agent Functions

Expose actions to agents.

Connecting Integrations

Set up credentials.

Integration Functions

Review invocation evidence.

Call Detail Page

Review action context.