Skip to content
AI Employee

How to Setup Flow Agents in Agent Studio

Learn how GHL Customer Care Agent Studio works. Explore triggers, nodes, templates, and AI tools to build, test, and publish intelligent AI agents.

6 min read1,345 words9 explained imagesUpdated Wed, 8 Jul at 7:13 AM
View as markdownOpen in ClaudeOpen in ChatGPT
Each image has a one line explanation. Switch to full detail for the step it belongs to, the fields and buttons involved, examples and the whole procedure.
On this page
  1. Key Benefits of Agent Studio
  2. Understanding the Agent Studio Interface
  3. Agent Studio Dashboard
  4. Creating a New Agent
  5. Agent Template Library
  6. The Builder Canvas
  7. Start Trigger
  8. Node Categories
  9. Variables and Global Prompt
  10. Testing and Publishing
  11. Frequently Asked Questions
  12. Related Articles

Video 1 Open in a new tab

Agent Studio is GHL Customer Care’s visual environment for building intelligent AI agents. It allows you to design how an agent is triggered, how it processes information, how it makes decisions, and what actions it performs all within a flexible, node-based canvas.

This article is intended for users who are exploring Agent Studio for the first time and want to understand its structure, purpose, and core components before building advanced automations.

Note: AI Studio and Agent Studio are two separate AI tools within GHL Customer Care, designed for different use cases.

AI Studio is a conversational, AI-powered builder that helps you quickly create websites, pages, and other web assets using prompts. Agent Studio is a visual builder used to create AI-powered agents that can respond to events, interact with users, and automate tasks.

TABLE OF CONTENTS

What is Agent Studio?

Agent Studio is a visual builder used to create AI-powered agents that can respond to events, interact with users, retrieve information, generate content, and connect with external systems.

Unlike simple rule-based automations, agents built in Agent Studio can interpret input, make contextual decisions, route conversations dynamically, and use tools such as knowledge search or APIs.

Each agent is built using connected nodes on a canvas, allowing you to define how it starts, how it processes information, and how it completes its task.

Key Benefits of Agent Studio

  • Visual AI Builder: Design agent behavior using a drag-and-drop canvas.
  • Event-Based Execution: Trigger agents using CRM events such as chat messages, form submissions, or lead tags.
  • Flexible Decision Logic: Route conversations based on AI intent detection or rule-based conditions.
  • Integrated Knowledge & Tools: Connect your Knowledge Base, search the web, or make API calls.
  • Multi-Modal Output: Generate text, images, audio, or video within a single flow.
  • Structured Data Collection: Capture emails, phone numbers, and user selections during interactions.

Understanding the Agent Studio Interface

Agent Studio Dashboard

When you navigate to AI Agents → Agent Studio, you’ll see a list of all agents in your account.

The dashboard allows you to:

  • View existing agents
  • Check status (Draft or Published)
  • See when they were created or last updated
  • Organize agents into folders
  • Create a new agent
  • Browse available templates

This is the central management area for your AI agents.

Agent Studio Dashboard (image 1 of 9) What this shows This is the central management area for your AI agents. What this shows Illustrates the "Agent Studio Dashboard" section of "How to Setup Flow Agents in Agent Studio". This screenshot appears in the "Agent Studio Dashboard" section of "How to Setup Flow Agents in Agent Studio". The text alongside this image reads: This is the central management area for your AI agents. This part of the guide covers 4 fields, listed below. Immediately after, the guide continues: From the dashboard, click Create Agent. Image 1 of 9 What this coversThis is the central management area for your AI agents.
Fields in this part of the guide View existing agentsSee when they were created or last updatedOrganize agents into foldersBrowse available templates
Buttons and menus referenced AI Agents → Agent Studio
Next stepFrom the dashboard, click Create Agent.
All 6 steps in this procedure
  1. View existing agents
  2. Check status (Draft or Published)
  3. See when they were created or last updated
  4. Organize agents into folders
  5. Create a new agent
  6. Browse available templates

Creating a New Agent

From the dashboard, click Create Agent.

You can choose to:

  • Start from scratch

  • Use a template from the Template Library

Starting from scratch gives you a blank canvas. Using a template provides a pre-built structure that you can customize.

Creating a New Agent (image 2 of 9) What this shows Starting from scratch gives you a blank canvas. What this shows Illustrates the "Creating a New Agent" section of "How to Setup Flow Agents in Agent Studio". This screenshot appears in the "Creating a New Agent" section of "How to Setup Flow Agents in Agent Studio". The text alongside this image reads: Starting from scratch gives you a blank canvas. Using a template provides a pre-built structure that you can customize. This part of the guide covers 1 field, listed below. Immediately after, the guide continues: The Template Library provides ready-made agent blueprints designed for common use cases. Image 2 of 9 What this coversStarting from scratch gives you a blank canvas. Using a template provides a pre-built structure that you can customize.
Fields in this part of the guide Start from scratch
Buttons and menus referenced Create Agent
Next stepThe Template Library provides ready-made agent blueprints designed for common use cases.
All 2 steps in this procedure
  1. Start from scratch
  2. Use a template from the Template Library

Agent Template Library

The Template Library provides ready-made agent blueprints designed for common use cases.

Instead of building from a blank canvas, you can:

  • Browse categorized templates

  • Preview how the agent is structured

  • Install a template into your account

  • Modify any part of the flow after installation

Templates typically include predefined triggers, AI nodes, routing logic, and actions. For first-time users, templates are often the fastest way to understand how agents are structured and connected.

Agent Template Library (image 3 of 9) What this shows Templates typically include predefined triggers, AI nodes, routing logic, and actions. What this shows Illustrates the "Agent Template Library" section of "How to Setup Flow Agents in Agent Studio". This screenshot appears in the "Agent Template Library" section of "How to Setup Flow Agents in Agent Studio". The text alongside this image reads: Templates typically include predefined triggers, AI nodes, routing logic, and actions. For first-time users, templates are often the fastest way to understand how agents are structured and connected. This part of the guide covers 4 fields, listed below. Immediately after, the guide continues: When you open or create an agent, you enter the visual builder canvas. Image 3 of 9 What this coversTemplates typically include predefined triggers, AI nodes, routing logic, and actions. For first-time users, templates are often the fastest way to understand how agents are structured and connected.
Fields in this part of the guide Browse categorized templatesPreview how the agent is structuredInstall a template into your accountModify any part of the flow after installation
Next stepWhen you open or create an agent, you enter the visual builder canvas.
All 4 steps in this procedure
  1. Browse categorized templates
  2. Preview how the agent is structured
  3. Install a template into your account
  4. Modify any part of the flow after installation

The Builder Canvas

When you open or create an agent, you enter the visual builder canvas.

This is where you:

  • Drag and connect nodes

  • Define execution logic

  • Configure each step of your agent

Agents are built by connecting nodes from left to right, beginning with a trigger and ending with an action or completion point. The connections between nodes define how the agent behaves in real scenarios.

The Builder Canvas (image 4 of 9) What this shows Agents are built by connecting nodes from left to right, beginning with a trigger and ending with an action or completion point. What this shows Illustrates the "The Builder Canvas" section of "How to Setup Flow Agents in Agent Studio". This screenshot appears in the "The Builder Canvas" section of "How to Setup Flow Agents in Agent Studio". The text alongside this image reads: Agents are built by connecting nodes from left to right, beginning with a trigger and ending with an action or completion point. The connections between nodes define how the agent behaves in real scenarios. This part of the guide covers 2 fields, listed below. Immediately after, the guide continues: Every agent begins with a Start Trigger. Image 4 of 9 What this coversAgents are built by connecting nodes from left to right, beginning with a trigger and ending with an action or completion point. The connections between nodes define how the agent behaves in real scenarios.
Fields in this part of the guide Define execution logicConfigure each step of your agent
Buttons and menus referenced create
Next stepEvery agent begins with a Start Trigger.
All 3 steps in this procedure
  1. Drag and connect nodes
  2. Define execution logic
  3. Configure each step of your agent

Start Trigger

Every agent begins with a Start Trigger.

The Start Trigger defines when the agent should run. Common examples include:

  • Chat Message

  • Form Submission

  • Lead Tag Added

Without a trigger, the agent will not execute. The trigger ensures the agent responds only when specific conditions are met.

Start Trigger (image 5 of 9) What this shows Without a trigger, the agent will not execute. What this shows Illustrates the "Start Trigger" section of "How to Setup Flow Agents in Agent Studio". This screenshot appears in the "Start Trigger" section of "How to Setup Flow Agents in Agent Studio". The text alongside this image reads: Without a trigger, the agent will not execute. The trigger ensures the agent responds only when specific conditions are met. This part of the guide covers 3 fields, listed below. Immediately after, the guide continues: In Agent Studio, everything on the canvas is built using nodes. A node is a building block that performs one specific function, such as starting the agent, generating a response, collecting information, or connecting to another system. By…. Image 5 of 9 What this coversWithout a trigger, the agent will not execute. The trigger ensures the agent responds only when specific conditions are met.
Fields in this part of the guide Chat MessageForm SubmissionLead Tag Added
Buttons and menus referenced Start Trigger
Next stepIn Agent Studio, everything on the canvas is built using nodes. A node is a building block that performs one specific function, such as starting the agent, generating a response, collecting information, or connecting to another system. By connecting nodes together, you define how your agent behaves from start to finish.
All 3 steps in this procedure
  1. Chat Message
  2. Form Submission
  3. Lead Tag Added

Node Categories

In Agent Studio, everything on the canvas is built using nodes. A node is a building block that performs one specific function, such as starting the agent, generating a response, collecting information, or connecting to another system. By connecting nodes together, you define how your agent behaves from start to finish.

Node Categories (image 6 of 9) What this shows In Agent Studio, everything on the canvas is built using nodes. What this shows Illustrates the "Node Categories" section of "How to Setup Flow Agents in Agent Studio". This screenshot appears in the "Node Categories" section of "How to Setup Flow Agents in Agent Studio". The text alongside this image reads: In Agent Studio, everything on the canvas is built using nodes. A node is a building block that performs one specific function, such as starting the agent, generating a response, collecting information, or connecting to another system. By connecting nodes together, you define how your agent…. Image 6 of 9 What this coversIn Agent Studio, everything on the canvas is built using nodes. A node is a building block that performs one specific function, such as starting the agent, generating a response, collecting information, or connecting to another system. By connecting nodes together, you define how your agent behaves from start to finish.
Buttons and menus referenced nodes

AI Agent: The AI Agent node is the “brain” of your flow. It reads incoming input, understands the context, and generates intelligent responses based on instructions you provide. For example, if a user asks about pricing, this node can interpret the question and generate a relevant reply.

Sequential: The Sequential node allows you to group multiple steps and run them in a fixed order. This is useful when certain actions must happen one after another, such as collecting an email first and then sending a confirmation message.

End Node: The End Node marks where the agent’s execution stops. Once the flow reaches this node, the interaction is complete.

Router: The Router node helps the agent choose between different paths based on conditions or AI-detected intent. Think of it like a decision point if a user asks about support, go one way; if they ask about sales, go another.

Search Knowledge Base: This node allows the agent to look up information stored in your connected Knowledge Base. For example, it can pull answers directly from your company’s documentation.

Search Web: The Search Web node enables the agent to gather information from online sources when needed. This is useful when responding to questions that require publicly available or current data.

MCP Server: The MCP Server node connects your agent to supported external tool servers. This allows advanced integrations where the agent can use external systems to perform specialized actions.

MCP Server: The MCP Server node connects your agent to supported external tool servers. This allows advanced integrations where the agent can use external systems to perform specialized actions. (image 7 of 9) What this shows Screenshot from "MCP Server: The MCP Server node connects your agent to supported external tool servers. This allows advanced integrations where the agent can use external systems to perform specialized actions.". What this shows Illustrates the "MCP Server: The MCP Server node connects your agent to supported external tool servers. This allows advanced integrations where the agent can use external systems to perform specialized actions." section of "How to Setup Flow Agents in Agent Studio". This screenshot appears in the "MCP Server: The MCP Server node connects your agent to supported external tool servers. This allows advanced integrations where the agent can use external systems to perform specialized actions." section of "How to Setup Flow Agents in Agent Studio". Image 7 of 9

API Call: The API Call node allows your agent to send or receive information from other applications. For example, it could send lead data to another system or retrieve customer details.

Audio Generation: This node allows the agent to generate spoken audio responses based on instructions within the flow.

Image Generation: The Image Generation node creates images based on descriptive prompts, useful for dynamic visual content.

Text Generation: The Text Generation node produces written content such as messages, summaries, or structured responses.

Email Address: This node collects a user’s email address during an interaction in a structured format.

Phone Number: The Phone Number node collects a user’s phone number in a standardized format for accurate storage.

Single Choice: The Single Choice node presents predefined options for the user to select from, helping guide structured decision-making.

Text Input: The Text Input node collects open-ended responses from users, allowing the agent to gather detailed information.

Variables and Global Prompt

At the top of the builder, you will find additional configuration tools that control how your agent behaves across the entire flow.

Variables

Variables act as reusable placeholders that store information. Instead of repeating the same value in multiple places, you define it once and reference it throughout the agent. For example, you could store a business name and use it consistently across responses.

Variables (image 8 of 9) What this shows Variables act as reusable placeholders that store information. What this shows Illustrates the "Variables" section of "How to Setup Flow Agents in Agent Studio". This animation appears in the "Variables" section of "How to Setup Flow Agents in Agent Studio". The text alongside this image reads: Variables act as reusable placeholders that store information. Instead of repeating the same value in multiple places, you define it once and reference it throughout the agent. For example, you could store a business name and use it consistently across responses. Immediately after, the guide continues: The Global Prompt defines overarching instructions that guide the agent’s behavior. It sets tone, personality, and rules the agent should follow in every interaction. Image 8 of 9 What this coversVariables act as reusable placeholders that store information. Instead of repeating the same value in multiple places, you define it once and reference it throughout the agent. For example, you could store a business name and use it consistently across responses. Next stepThe Global Prompt defines overarching instructions that guide the agent’s behavior. It sets tone, personality, and rules the agent should follow in every interaction.

Global Prompt

The Global Prompt defines overarching instructions that guide the agent’s behavior. It sets tone, personality, and rules the agent should follow in every interaction.

Global Prompt (image 9 of 9) What this shows The Global Prompt defines overarching instructions that guide the agent’s behavior. What this shows Illustrates the "Global Prompt" section of "How to Setup Flow Agents in Agent Studio". This animation appears in the "Global Prompt" section of "How to Setup Flow Agents in Agent Studio". The text alongside this image reads: The Global Prompt defines overarching instructions that guide the agent’s behavior. It sets tone, personality, and rules the agent should follow in every interaction. Immediately after, the guide continues: Before activating an agent, you can. Image 9 of 9 What this coversThe Global Prompt defines overarching instructions that guide the agent’s behavior. It sets tone, personality, and rules the agent should follow in every interaction. Next stepBefore activating an agent, you can:

Testing and Publishing

Before activating an agent, you can:

  • Use the Test feature to simulate execution

  • Save changes as a draft

  • Publish the agent when ready

An agent must be published in order to respond to real-world triggers.

Frequently Asked Questions

Q: Do agents run automatically?

Agents run only when their configured trigger conditions are met.

Q: How is Agent Studio different from workflows?

Workflows follow predefined automation rules. Agents can interpret input and make dynamic decisions using AI.

Q: Do I need to publish an agent for it to work?

Yes. An agent must be published to respond to real events.

Q: Can agents integrate with external systems?

Yes. API Call and MCP Server nodes allow external integrations.

Q: Can agents generate content beyond text?

Yes. Agent Studio supports image, audio, and video generation.

Was this guide helpful?

Related guides

Overview of Flow Agents in Agent Studio5 min read · 6 imagesAgent Studio - Setting Up Triggers for Flow Agents5 min read · 4 imagesAgent Studio - Router Tool (AI & Conditional Router)8 min read · 14 imagesHow to Create and Manage Folders in Agent Studio4 min read · 8 images