AI Agent Injections

Create an AI-powered agent to collect information or perform an action

Overview

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

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.

Workflow

  1. Build your AI Agent

    1. Name your agent

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

    2. Describe your agent

      1. Add a short description that tells the AI how to act (e.g. A charismatic booking agent helping renters schedule tours).

    3. Choose the Role

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

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

  2. Assign your agent a goal-oriented task

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

    2. 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.

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

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

    2. Sender identity

    3. Subject line (if Email)

    4. 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.

You can use Agent Injection across multiple channels — behavior will adjust based on format

Last updated

Was this helpful?