Agent Studio is HighLevel’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.
TABLE OF CONTENTS
- What is Agent Studio?
- Key Benefits of Agent Studio
- Understanding the Agent Studio Interface
- Frequently Asked Questions
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Getting Started with Agent Studio
To create your first agent:
Navigate to AI Agents → Agent Studio
Click Create Agent
Choose to start from scratch or install a template
Add a Start Trigger
Drag an AI Agent node onto the canvas and connect it
Use Test to simulate behavior
Save and Publish the agent
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.
Related Articles
Was this article helpful?
That’s Great!
Thank you for your feedback
Sorry! We couldn't be helpful
Thank you for your feedback
Feedback sent
We appreciate your effort and will try to fix the article