Bring Managed Agent reasoning directly into HighLevel Workflows with the Invoke Managed Agent action. Workflows can pass contact information, dynamic workflow context, and attachments to a published Managed Agent, then use the agent’s response in later automation steps. This gives you the predictable structure of Workflows while allowing a 

Managed Agent to analyze information, use its configured tools and CRM capabilities, and complete more flexible tasks. Use this feature when your automation needs AI-powered reasoning without moving the entire process outside your Workflow.

TABLE OF CONTENTS

• What is Invoke Managed Agent?
• Key Benefits of Invoke Managed Agent
• How Invoke Managed Agent Works
• Managed Agent Requirements
• Passing Context to the Managed Agent
• Using the Managed Agent Response in Later Workflow Steps
• Invoke Managed Agent vs. Other Workflow AI Options
• Common Use Cases for Invoke Managed Agent
• How To Setup Invoke Managed Agent
• Step 1: Configure the Managed Agent
• Step 2: Add Invoke Managed Agent to the Workflow
• Step 3: Write the Agent Instruction
• Step 4: Use the Response in Later Actions
• Step 5: Save, Test, and Publish the Workflow
• Frequently Asked Questions
• Related Articles

What is Invoke Managed Agent?

Invoke Managed Agent connects HighLevel Workflows with published Managed Agents so an automation can intentionally hand a task to an agent and continue after the agent completes its work. This makes it possible to place AI reasoning at a specific point in an otherwise structured Workflow while keeping the surrounding automation predictable.

When a Workflow reaches the Invoke Managed Agent action, it sends the selected contact and configured context to a Managed Agent that has the Invoked from a workflow trigger. The agent follows its existing instructions, uses its configured tools and CRM capabilities as needed, and returns a response that can be used by later Workflow actions.

Managed Agents are part of HighLevel’s Agent Studio experience and can combine AI reasoning with Knowledge 

Bases, CRM information, triggers, and CRM actions.

Key Benefits of Invoke Managed Agent

Adding a Managed Agent to a Workflow allows deterministic automation and AI-driven reasoning to work together. This is especially useful when the next automation step depends on understanding, summarizing, evaluating, or generating information instead of following only fixed rules.

• AI reasoning inside Workflows: Add a Managed Agent at the exact point where your automation needs interpretation, analysis, or content generation.
  
  

• Context-aware execution: Send contact information and Workflow data to the agent so its task can reflect the current automation context.
  
  

• Dynamic instructions: Include dynamic values in the instruction sent to the Managed Agent to personalize each execution.
  
  

• Attachment support: Pass attachments to the agent when files are part of the context it needs to complete the task.
  
  

• Reusable agent configuration: Use a separately configured Managed Agent instead of rebuilding its instructions and capabilities inside every Workflow.
  
  

• Downstream automation: Use the agent’s response in later Workflow steps to update records, branch the automation, or send messages.
  
  

• CRM-enabled execution: Allow the Managed Agent to use the instructions, tools, and CRM capabilities already configured for that agent.

How Invoke Managed Agent Works

The Invoke Managed Agent action creates a handoff between two automation layers: the Workflow controls when the task occurs, while the Managed Agent determines how to complete the assigned task based on its configuration. 

Understanding this relationship helps you decide which responsibilities belong in the Workflow and which should be delegated to the agent.

The basic execution flow is:

1. A contact enters or progresses through a Workflow.
   
   

2. The contact reaches the Invoke Managed Agent action.
   
   

3. HighLevel sends the contact, configured Workflow context, dynamic data, and any included attachments to the selected Managed Agent.
   
   

4. The Managed Agent processes the instruction using its published configuration, tools, and CRM capabilities.
   
   

5. The agent returns its response.
   
   

6. The Workflow continues and can use that response in later actions.

This approach allows you to keep predictable steps—such as triggers, waits, messages, and branching—inside the Workflow while delegating tasks that benefit from AI reasoning to the Managed Agent.

Managed Agent Requirements

Only appropriately configured Managed Agents can be used by the Invoke Managed Agent action. Preparing the agent first ensures it can be selected from the Workflow Builder and is ready to handle live Workflow executions.

Before adding the action to a Workflow:

• Open the Managed Agent in AI Agents → Agent Studio → Managed Agents.
  
  

• Add the Invoked from a workflow trigger.
  
  

• Confirm the agent has the instructions, tools, Knowledge Base access, and CRM capabilities required for the task.
  
  

• Test the Managed Agent before using it in a live automation.
  
  

• Publish the Managed Agent.

HighLevel’s existing Managed Agent documentation confirms that Managed Agents follow a draft, testing, and publishing lifecycle and can be configured with CRM actions and Knowledge Base access.

Passing Context to the Managed Agent

The quality of the agent’s result depends on the context it receives. Providing the information needed to complete the task helps the Managed Agent reason about the correct contact, understand what has already happened in the Workflow, and produce an output that later steps can use.

The Invoke Managed Agent action can send:

• Contact information.
  
  

• Workflow data.
  
  

• Dynamic values available when the action runs.
  
  

• Instructions describing the task the agent should complete.
  
  

• Attachments that the agent needs as context.

Dynamic data can be included directly in the instruction. This allows the same Workflow action to send different information for each contact instead of relying on a fixed prompt.

For example, an instruction could ask the agent to review a contact’s current information and return the most appropriate follow-up based on the data available when the Workflow reaches the action.

When writing the instruction:

• Clearly state the task the agent should complete.
  
  

• Include only the context that is relevant to the decision or output.
  
  

• Describe the result you expect from the agent.
  
  

• Use dynamic values when the instruction should change based on the contact or Workflow execution.
  
  

• Include attachments when the agent needs to review a file as part of the task.

Using the Managed Agent Response in Later Workflow Steps

The agent response becomes most useful when it influences what the Workflow does next. Passing that result downstream allows the automation to combine AI reasoning with standard Workflow actions without requiring the entire process to be handled by the agent.

After the Managed Agent completes its task, its response can be used in later Workflow steps. Depending on your automation, you can use the returned information to:

• Update CRM records.
  
  

• Determine which branch of the Workflow should run next.
  
  

• Populate content for a later communication.
  
  

• Pass information into another automation step.
  
  

• Continue processing based on the result produced by the agent.

For example, a Managed Agent could evaluate the available context and return information that a later Workflow step uses to update a record or determine an appropriate branch.

Invoke Managed Agent vs. Other Workflow AI Options

HighLevel provides multiple ways to add AI to automation, and each option serves a different configuration model. Choosing the correct action helps prevent duplicated setup and makes it easier to maintain your automation over time.

Invoke Managed Agent is designed for a Managed Agent that is created and maintained separately from the Workflow. The Workflow invokes the published agent when it reaches the appropriate step.

HighLevel also currently documents two adjacent options:

• AI Agent: Configured directly inside the Workflow action. You define its instructions, model, tools, memory, and output behavior from the Workflow Builder.
  
  

• Invoke Agent Studio Agent: Calls an eligible published flow-based Agent Studio agent from a Workflow. HighLevel documents this separately from the new Managed Agent workflow invocation experience.

Use the option that matches where your AI logic is maintained:

HighLevel currently recommends Managed Agents for creating new autonomous agents, while Agent Studio remains available for maintaining flow-based agents.

Common Use Cases for Invoke Managed Agent

Managed Agent invocation is useful when a Workflow reaches a point where fixed automation rules are not enough to handle the available context. Keeping that reasoning inside a reusable Managed Agent can simplify the Workflow while allowing the surrounding automation to remain structured.

Common examples include:

• Contact analysis: Review available contact or CRM information and return a useful summary or classification.
  
  

• Workflow branching: Evaluate context and provide a response that determines which Workflow path should run next.
  
  

• Personalized content: Generate context-aware text that a later Workflow step can use in a message or record.
  
  

• Record processing: Interpret information before a later action updates fields, notes, or other CRM records.
  
  

• Attachment review: Process an attachment that was made available to the Workflow and return information needed for subsequent steps.
  
  

• Complex task handoff: Delegate a task requiring multiple reasoning steps to a Managed Agent while keeping the rest of the process inside the Workflow.

How To Setup Invoke Managed Agent

Proper setup begins with the Managed Agent because the Workflow can only invoke an agent that has been prepared for workflow-based execution. Configure and publish the agent first, then connect it to the Workflow and define the task and context it should receive.

Step 1: Configure the Managed Agent

1. Navigate to AI Agents → Agent Studio.
   
   

2. Open the Managed Agents tab.
   
   

3. Create a new Managed Agent or open the agent you want to use.
   
   

4. Configure the agent’s instructions, tools, Knowledge Base access, and CRM capabilities based on the task it should perform.
   
   

5. Open the agent’s trigger configuration.
   
   

6. Add the Invoked from a workflow trigger.
   
   
   

7. Test the Managed Agent to confirm that it behaves as expected.
   
   

8. Publish the agent.

HighLevel’s Managed Agent documentation recommends testing an agent before publishing it to live triggers.

Step 2: Add Invoke Managed Agent to the Workflow

1. Navigate to Automation → Workflows.
   
   

2. Create a Workflow or open an existing Workflow.
   
   

3. Navigate to the point where the Managed Agent should run.
   
   

4. Click + Add Action.
   
   

5. Select Invoke Managed Agent.
   
   
   

6. Select the published Managed Agent you configured in Step 1.

If the Managed Agent does not appear, confirm that the correct agent has the Invoked from a workflow trigger and has been published.

Step 3: Write the Agent Instruction

1. Enter the instruction that describes what the Managed Agent should do.
   
   

2. Add dynamic contact or Workflow data where the task requires information that changes between executions.
   
   

3. Include enough context for the agent to understand the desired outcome.
   
   

4. Add attachment context when the agent needs to work with a file provided through the Workflow.
   
   

5. Review the instruction for clarity before saving the action.

A useful instruction should identify the task, relevant context, and expected result rather than relying on a vague request.

Example instruction:

Review the available contact information and recent context provided by this Workflow. Determine the most relevant next action for this contact and return a concise explanation that can be used by the following Workflow steps.

Step 4: Use the Response in Later Actions

1. Add the Workflow action that should run after the Managed Agent.
   
   

2. Open the dynamic-value selector where applicable.
   
   

3. Select the available response from the Invoke Managed Agent step.
   
   

4. Use the response in the downstream action as needed.
   
   

5. Add branching or record-update logic if the result should influence the remainder of the Workflow.

Possible downstream actions include updating a record, branching based on the result, or using the returned content in a message.

Step 5: Save, Test, and Publish the Workflow

1. Save the Invoke Managed Agent action.
   
   

2. Review the complete Workflow sequence.
   
   

3. Test the Workflow with representative contact data and context.
   
   

4. Confirm that the Managed Agent receives the expected information.
   
   

5. Verify that later actions use the returned response correctly.
   
   

6. Publish the Workflow when testing is complete.

Testing both the Managed Agent and the surrounding Workflow helps ensure the AI task and deterministic automation work together as intended.

Frequently Asked Questions

Q: Why does my Managed Agent not appear in the Workflow action?
Confirm that the Managed Agent has the Invoked from a workflow trigger and is published. The release makes workflow invocation available to eligible published Managed Agents configured with this trigger.

Q: Is Invoke Managed Agent the same as Invoke Agent Studio Agent?
They are documented as separate experiences. Invoke Managed Agent is designed for Managed Agents configured with the Invoked from a workflow trigger. HighLevel’s existing Invoke Agent Studio Agent documentation applies to flow-based Agent Studio agents and uses its own workflow-trigger configuration.

Q: Does Invoke Managed Agent replace normal Workflow actions?
No. It is designed to work inside a Workflow alongside standard automation actions. Use the Managed Agent where reasoning or flexible task execution is useful, then continue with normal Workflow actions afterward.

Q: Can the Managed Agent make CRM changes when a Workflow invokes it?
The agent can use the CRM capabilities and tools that are configured for it. Managed Agents can be configured to work with CRM information and perform supported CRM actions, so review the agent’s permissions and instructions carefully before publishing.

Q: Should the Workflow or the Managed Agent handle the business rules?
Keep predictable sequencing and fixed conditions in the Workflow when possible. Use the Managed Agent for tasks that require interpretation, reasoning, generation, or flexible action based on context.

Q: How detailed should the Workflow instruction be?
Provide enough information for the agent to understand the immediate task, relevant context, and expected result. The agent’s permanent role and capabilities should remain in its Managed Agent configuration so you do not have to recreate the full agent definition in every Workflow.

Q: Can the same Managed Agent still use other triggers?
HighLevel supports multiple triggers on Managed Agents. The Invoked from a workflow trigger gives the Workflow an additional way to start the agent; other supported triggers can remain part of the agent’s configuration where appropriate. HighLevel’s Managed Agent documentation confirms that one Managed Agent can use multiple supported triggers.

Related Articles

• Setup and Use Managed Agents in Agent Studio — View article
  
  

• Workflow Action – Invoke Agent Studio Agent — View article
  
  

• Workflow Action – AI Agent — View article
  
  

• AI Tools in HighLevel — View article
  
  

• Agent Studio – Setting Up Triggers for Flow Agents — View article