Conduit
Book DemoEnroll in Course
  • Start Guide
  • Setup
    • Workspaces
    • Invite and Manage Members
    • Notifications
    • Mobile
    • Flexible Inboxes
      • Create an Inbox
      • Custom Fields
      • Workflow
  • Channels
    • Property Management System
      • Guesty
      • Track
      • Hostaway
      • BookingSync/Smily
      • Lodgify
      • Hostfully
      • OwnerRez
      • Beds24
      • Add and Remove Listings
    • Email
      • Receiving Emails in Conduit
      • Sending Emails from Conduit
      • Alternate Email Addresses
    • WhatsApp
    • Business Phone Number
      • Port Your Phone Numbers to Conduit
        • OpenPhone
        • Aloware
        • Google Voice
        • Dialpad
        • RingCentral
        • Aircall
        • Grasshopper
        • Zoom Phone
    • Chat Widget
    • Airbnb
      • Standalone
      • With a PMS
  • Using The Inbox
    • Inbox Zero
    • AI Messaging
    • Conversation Tags
    • Labels
    • Notes and Mentions
    • Assignment
    • Saved Replies
    • Insights
  • Building Your AI Agents
    • Road to Autopilot
    • Phase 1: Teaching
      • Sources
      • Required Info
      • Teach as You Go
    • Phase 2: Tuning
      • In the Sandbox
      • In the Inbox
      • Advanced Rules
    • Autopilot
  • Workflows
    • Getting Started
  • Create a Workflow
  • Trigger and Action Libraries
  • AI Agent Injections
  • Integrations
    • Slack
    • Zapier
  • Other
    • Conduit Certification
Powered by GitBook
On this page
  • Overview
  • Workflow

Was this helpful?

AI Agent Injections

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

PreviousTrigger and Action LibrariesNextSlack

Last updated 1 month ago

Was this helpful?

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