AI Agent Injections

Overview

Agent Injection lets you build a custom AI agent directly inside a workflow. These agents appear in the conversation like any other teammate. Behind the scenes, they’re powered by Conduit's AI.

Agent injection can be used in both text and VoiceAI

Use this node when you want an AI agent to:

• Guide a guest through a multi-step task

• Collect missing information

• Follow up repeatedly until a goal is met

You control the tone, the logic, and the follow-through.

To add Agent injection for both text and VoiceAI, open a workspace and create a trigger. After the trigger,

1. Select Add Action > Agent Injection or Agent Injection Phone

1. Name your agent

   • Give the agent a recognizable identity (e.g. Carl from Conduit).

2. Describe your agent

   • Add a short description that tells the AI how to act (ie. You are Alex and you are a friendly customer support representative).

3. Choose the Role

   

   • Action: The agent will work to get the user to do something (e.g. confirm a booking, upload a form)

   • Information: The agent will work to gather a specific piece of information (e.g. “What’s your ETA?”)

4. 

   • Write the instructions — Provide clear instructions to the agent about how to behave. Include tone, constraints, or fallback rules.

   • Set follow-ups — Choose how many times the agent should follow up, and how long to wait between attempts if the goal isn’t met.

5. Craft the first message — This is the initial message that kicks off the agent's behavior. You’ll choose:

   

   • Channel (e.g. Email, SMS, WhatsApp)

   • Sender identity

   • Subject line (if Email)

   • Message body with optional variables (e.g. {{guest.first_name}})

   Once sent, the AI will take over and handle replies until the task is complete — or the agent reaches the follow-up limit.