6

Automations & AI Agents

Last Update 5 dagen geleden

How to Build and Manage AI Agents in myCRMSIM myCRMSIM Automations Guide AI Agent Troubleshooting Guide Link Clicked Trigger Guide Setup (myCRMSIM) Create an Advanced Missed Call Text Back Automation in myCRMSIM

How to use myCRMSIM AI Agents with HighLevel

Overview

This guide explains how to create, configure, test, and manage a myCRMSIM AI Agent connected to HL. It also explains how to assign the correct contact tag, test the AI Agent through an SMS, iMessage, WhatsApp and RCS conversation, and manage appointments through the AI Agent. All booking, cancellation, and rescheduling actions must be initiated through the AI Agent conversation and then verified in the HL Calendar.
Important: Always select the correct HL agency or location before making changes. Using the wrong location may update the wrong contacts, workflows, conversations, or calendar.
1. Open the AI Agents Dashboard
1. Login to myCRMSIM Dashboard.
2. From the left sidebar, select AI Dashboard.
3. The AI Agents Dashboard is the central workspace for managing AI Agents.
2. Confirm the OpenAI API Key or OpenRouter API Key
Before creating an AI Agent, make sure the API key for your selected AI provider is already configured in the system.

When you click on Create New AI Agent, the system requires a valid API key to continue the AI Agent setup. You can use either an OpenAI API Key or an OpenRouter API Key, depending on the AI provider you want to use.

Please ensure the appropriate API key is configured before starting the AI Agent creation process. Without a valid API key, the AI Agent may not be created or may not work properly.
3. Create a New AI Agent
To create a new AI Agent, visit the Ai Dashboard from side menu and click the blue button named as:
       + Create New AI Agent
You can see it at the top right of the AI Agents Dashboard.
After clicking this button, a popup will appear titled:
         Choose Your Path
This popup allows you to select how you want to create your AI Agent.
4. Choose Your Path

When creating a new AI Agent, you will see three options:

Create New
Select Create New if you want to build a new AI Agent from scratch.
Use this option when you want to manually create the agent’s:
1. Instructions
2. Conversation 
3. Configurations
4. Knowledge
5. Workflows

6. Review

This is the best option when setting up a completely new AI Agent.
Import Strategy
Select Import Strategy if you already have an exported AI Agent strategy file.
This option allows you to upload a .json file and recreate an existing strategy.
Use this option for importing a backup, reusing a previous strategy, moving an agent setup from another workspace, or restoring a saved configuration.
Creating an Agent with Simi
For users who prefer a guided setup, myCRMSIM offers “Simi,” an AI assistant designed to help
you build your agent conversationaly.

1. Click + Create New AI Agent.
2. Select Create with Simi and click Next.
3. Click the Start with Simi button.
4. A chat interface will open where you can describe what you want the agent to do. 

For example, you can ask, “how can i create an agent?” and Simi will guide you through the required parameters
5. AI Agent Builder Steps
After selecting the creation method, the AI Agent Builder will guide you through the setup process.
The builder includes five main steps:
Step 1: Instructions
Step 2: Conversation
Step 3: Configurations
Step 4: Knowledge
Step 5: Tasks
Each step controls a different part of how the AI Agent works.
Step 1 — Instructions
The Instructions step is where you define who the AI Agent is, what role it should perform, how it should speak, and which AI model it should use.
This is one of the most important steps because it defines the identity and behavior of the agent.
Strategy Name
The Strategy Name is the internal name of your AI Agent.
Use a clear name that explains the purpose of the agent.
Agent Role
The Agent Role defines what the AI Agent should act as during the conversation.
Contact Tag
The Contact Tag is used to apply a specific tag to contacts connected with this AI Agent.
Tags are important because they help organize contacts inside your CRM.
Example tags:
qualified_sales_lead
plant_lead
Using the correct tag helps you filter contacts, trigger workflows, and track lead status properly.
Tone
The Tone controls how the AI Agent communicates with customers.
Choose a tone that matches your business and the type of conversation.
Common tone options include:
  • Professional and Formal
  • Friendly and Casual
  • Enthusiastic and Energetic
  • Empathetic and Supportive
  • Instructive and Informative
  • Persuasive and Convincing
  • Calm and Reassuring
Choose the AI Model
The AI Model section allows you to select which AI model will power the agent.
Different models may vary in quality, speed, reasoning ability, and cost.
Available model options may include:
  • GPT-4o mini
  • GPT-4.1 mini
  • GPT-4.1
  • GPT-5 mini
  • GPT-5
  • GPT-5.1
Prompt Builder
Navigate to the Strategy Builder page within your myCRMSIM dashboard. On the right side of the screen, look for the panel that says "No prompt yet" and click the Build My Prompt button to open the builder.
  1. Define the AI's Role
  2. Set the Objective
  3. Provide Context
  4. Establish Conversation Rules
  5. Add Example Conversations (Optional)
  6. Save and Compile
Once you have completed all the sections, click the Save Compilation button at the bottom right of the modal.
The Prompt Builder will close, and you will be returned to the Strategy Builder page. Your newly created, fully structured prompt will now be displayed in the Prompt Editor panel, ready to be used by your AI agent! You can always click "Edit Instructions" if you need to make changes later.
Advanced Settings
The Advanced Settings section is optional and allows you to control how the AI agent responds during conversations.
Click on Advanced Settings to expand this section. Inside this section, you can configure the following options:
Initial Message Delay
The Initial Message Delay controls how long the AI waits before sending the first message.
Options may include:
Instant
30 seconds – 1 minute
1 – 5 minutes
5 – 15 minutes
15 – 30 minutes
You can also set custom minimum and maximum delay values.
This makes the AI feel more natural instead of responding instantly every time.
Response Delay
The Response Delay controls how long the AI waits before replying after the customer sends a message.
Options may include:
Instant
5 – 15 seconds
15 – 30 seconds
30 – 60 seconds
1 – 2 minutes
A small response delay can make the conversation feel more human and realistic.
Objection Handling
The Objection Handling setting controls how the AI responds when a customer hesitates, says no, asks difficult questions, or gives an objection.
The behavior may be adjusted between:
Passive
Persuasive
Confident
Assertive
For sales agents, a persuasive or confident style is usually helpful.
For support agents, a calm and supportive style is usually better.
Qualification Priority
The Qualification Priority setting controls how strictly the AI qualifies a lead before moving the conversation forward.
The behavior may be adjusted between:
Light
Balanced
Strict
Use Light when you want the AI to keep the conversation going and avoid being too strict.
Use Balanced for normal lead qualification.
Use Strict when only serious and qualified leads should continue.
Creativity
The Creativity setting controls how freely the AI responds during the conversation.
The behavior may be adjusted between:
Scripted
Adaptive
Freeform
Use Scripted when you want the AI to stay close to the prompt.
Use Adaptive when you want natural but controlled replies.
Use Freeform when you want the AI to respond more flexibly and creatively.
Step 2 — Conversation
The Conversation step is used to build the AI Agent’s complete message flow. In this step, you can set the first message, add qualification questions, create follow-ups, use templates, and add conditional logic.
This step helps the AI guide the customer in a structured way and qualify the lead properly.
Conversation 
The Conversation section provides two different views: Script and Map.

We are using Script in this guide.

Initial Message
The Initial Message is the first message the AI Agent sends when the conversation starts.
This message should be short, clear, and relevant to the customer.
 Example: 
Hi, thanks for reaching out. How can I help you today?
Spintext
The Spintext option allows you to add multiple variations of the initial message.
You can add up to 5 variations, and the AI will rotate between them for new leads.
This helps the AI sound more natural and prevents every customer from receiving the exact same message.
 Example variations: 
Variation 1:
Hi, thanks for reaching out. How can I help you today?
Variation 2:
Hello, I’m here to help. What are you looking for?
Variation 3:
Hi, welcome. Are you interested in learning more or booking an appointment?
Using Spintext makes the conversation feel less robotic and more personalized.
Qualification Enabled Toggle
The Qualification toggle controls whether the AI should qualify the lead during the conversation.
When qualification is enabled, you can add questions that help the AI understand the customer’s interest, need, budget, or intent.
This is useful for sales, appointment booking, and lead filtering.
Add Question
Use Add Question to add qualification questions into the conversation flow.
Each question appears as a separate node in the flow.

 Example questions: 
  1. Are you mainly looking to get new leads, keep current clients engaged, or both?
  2. Are you currently running any marketing campaigns?
  3. What does your ideal customer look like?
Conditional Logic
Conditional Logic allows you to create different conversation paths based on the customer’s answer.

 For example: 
If the customer answers yes, the AI can move to the next question or skip to another step.
If the customer answers no, the AI can send a different message or continue with another question.
Use Add Condition to define these rules.
Conditional logic helps make the conversation smarter and more relevant to the customer’s reply.
Add Follow-up
Use Add Follow-up to add a follow-up message after a question or conversation step.
Follow-ups are useful when the customer does not reply or when you want to remind them after some time.
You can set the follow-up message and delay time using:
  • Days
  • Hours
  • Minutes
 Example: 
Send a follow-up after 1 day if the customer does not respond.
Follow-up Spintext
The Follow-up Spintext option allows you to add variations of a follow-up message.
This helps the AI avoid sending the same follow-up every time.
It makes follow-up messages feel more natural and less repetitive.
Step 3 — Configurations
The Configurations step allows you to control how the AI Agent sends messages, what goal it should work toward, how it should handle unqualified leads, and when it is allowed to message contacts.
This step is important because it helps the AI Agent follow your business rules.
Messaging
The Messaging section controls how the AI formats its replies.
Multiple Messages
The Multiple Messages option allows the AI to split long responses into shorter sequential messages.
When this option is turned ON, the AI may send a longer response as multiple shorter messages.
This can make conversations easier to read and more natural for the customer.
When this option is turned OFF, the AI will usually send replies as a single message.
End Goal
The End Goal section defines the main outcome the AI Agent should try to achieve during the conversation.
This tells the AI what it should guide the customer toward.
Available goal types may include:
Call to Action
Book Appointment
Send Booking Link
Book Appointment
Select Book Appointment when you want the AI to book an appointment directly on your GHL calendar.
After selecting this option, choose the calendar provider and select the connected calendar.
Example: 
Calendar Provider: GHL Calendar
Select Calendar: Your connected calendar account
This option is useful when the AI should qualify the lead and then schedule a meeting, consultation, demo, or appointment.
Lead Management

The Lead Management section controls what should happen if a customer is not qualified or does not want to continue.

Disqualification Trigger
The Disqualification Trigger field is used to add words or phrases that mark a lead as lost, unqualified, or not interested.
If the customer sends any of these words or phrases, the AI can understand that the lead should not continue in the normal sales flow.
Execution Window
The Execution Window section controls when the AI Agent is allowed to message contacts.
This is useful if you only want the AI to send messages during business hours.
Timezone
Select the correct timezone for your business.
Example: 
Karachi (GMT+5)
Choosing the correct timezone is important because all start and end times follow this timezone.
Start and End Time
Set the time window during which the AI Agent is allowed to send messages.
Example: 
Start: 09:00 AM
End: 05:00 PM
This means the AI Agent will only send messages during this selected time window.
Skip Weekends
Enable Skip Weekends if you do not want the AI Agent to message contacts on Saturday and Sunday.
This is useful for businesses that operate from Monday to Friday.
Outside the Window
The Outside the Window option controls what happens if a message needs to be sent outside the allowed time.
Example: 
Queue until next window Do not Send
If this option is selected, messages will wait and send when the next allowed time window starts.
This helps avoid sending messages too early, too late, or outside business hours.
Also Apply to AI Replies
The Also apply to AI replies option controls whether the execution window should also apply to AI replies.
If this option is turned ON, the AI will only reply during the selected business hours.
If this option is turned OFF, some replies may still be sent outside the selected window depending on the setup.
For strict business-hour control, this option should be enabled.
Step 4 — Knowledge
The Knowledge step is where you provide business information to the AI Agent.
This helps the AI understand your company, products, services, pricing, policies, and common customer questions.
The better the knowledge you provide, the better and more accurate the AI responses will be.
Company Information
The Company Information section is used to give the AI general context about your business.
You can add information such as what your company does, what products or services you offer, your value proposition, target customers, pricing details, business location, delivery or service areas, and important policies.
 Example: 
Our company is a plant seller company in Australia. We provide indoor plants, outdoor plants, low-maintenance plants, and plant care guidance for homes and offices.
This information helps the AI answer general customer questions correctly.
FAQs
The FAQs section is used to add common questions and answers that the AI can reuse during conversations.
Click Add FAQ to add a new FAQ.
Each FAQ includes:
Question
The customer question or objection.
Answer
The response the AI should give.
Step 5 — Workfows
The Tasks step is optional inside the AI Agent Builder.
This step is used to define what should happen after the AI reaches its goal or when a specific action is required.
However, for AI Agents, advanced workflow actions should be created from the main Automations page.
Important: Only workflows that are created using an AI Trigger and have an Active/Live status will appear in the Add Workflow dropdown. If you cannot see any created workflows in the Add to Workflow dropdown, follow the steps below to create a workflow.
Create Appointment Management Workflows
To allow the AI Agent to manage appointments, create three separate workflows in Automations:
  1. Book Appointment
  2. Cancel Appointment
  3. Reschedule Appointment
Each workflow should use the appropriate AI Trigger and appointment action or other actions.
Workflow 1: Book Appointment
  1. Go to Automations.
  2. Click Create Workflow.
  3. Add the AI Trigger.
  4. Configure the trigger with the instruction:
    When the user wants to book an appointment.
  5. Add the Book Appointment action.
  6. Click Save.
This workflow will allow the AI Agent to trigger the Book Appointment action when a user requests to book an appointment.
Workflow 2: Cancel Appointment

  1. Go to Automations.
  2. Click Create Workflow.
  3. Add the AI Trigger.
  4. Configure the trigger with the instruction:
    When the user wants to cancel an appointment.
  5. Add the Cancel Appointment action.
  6. Click Save.
This workflow will allow the AI Agent to trigger the Cancel Appointment action when a user requests to cancel an existing appointment.
Workflow 3: Reschedule Appointment
  1. Go to Automations.
  2. Click Create Workflow.
  3. Add the AI Trigger.
  4. Configure the trigger with the instruction:
    When the user wants to reschedule an appointment.
  5. Add the Reschedule Appointment action.
  6. Click Save.
This workflow will allow the AI Agent to trigger the Reschedule Appointment action when a user wants to change their existing appointment.
Important Note About Automations
AI Agent conversations are created inside the AI Agent Builder, but workflow actions should be created from the Automations page.
After creating the AI Agent, go to:
Automations → Add Workflow
From there, you can build automation flows connected with your AI Agent.
The AI Agent handles the conversation.
The Automations page handles the backend workflow actions.
What Can Be Created in Automations
From the Automations page, you can create workflows for an AI Agent by using the AI Trigger, such as:
  • Create contact
  • Add tag
  • Book Appointment
  • Cancel Appointment
  • Reschedule Appointment
  • Move contact to pipeline
  • Send follow-up message
  • Notify team member
  • Trigger appointment workflow
  • Mark lead as qualified
  • Handle disqualified leads
  • Pause AI for a contact
  • Continue AI after a condition
  • Send internal notification
Step 6: Review Your AI Agent
The Review page gives you a complete overview of your AI Agent setup before launching it. You can review and edit the Identity, Prompt, Conversation, Goal, Knowledge, and Workflow settings, check your setup progress, and complete any missing required configurations. Once everything is ready, click Launch Agent to activate your AI Agent.
Launch the AI Agent
Save the AI Agent regularly to prevent loss of work.
Use Save Draft when the agent is not ready to go live, when the conversation flow is incomplete, when more knowledge must be added, when approval is pending, or when you plan to continue editing later.
Before activation, review the instructions, contact tag, conversation flow, calendar configuration, knowledge, tasks, and execution window.
Select the Correct Agency or Location in HL
  1. Open GHL.
  2. Click the Agency/Location selector.
  3. Select the correct Sub-account or Location where you want to use the AI Agent.
Important: Ensure you are working in the same location connected to your myCRMSIM setup.
Identify the AI Agent Tag
The AI Agent uses a specific tag to identify which contacts should be handled by the Agent.
  1. Go to Contacts in GHL.
  2. Open a contact already configured for the AI Agent, if available.
  3. Check the Tags section.
  4. Note the exact AI Agent tag name.
Important: Always use the exact AI Agent tag.
Step 5: Add the AI Agent Tag to a Contact (Important)
  1. Go to Contacts.
  2. Search for the contact using their name or phone number.
  3. Open the contact record.
  4. Locate the Tags section.
  5. Click Add Tag.
  6. Select the correct AI Agent tag.
  7. Save the changes.
The contact is now configured to interact with the AI Agent.
Use the AI Agent Through HL
Test an Incoming Message
  1. Send an SMS from the tagged contact's registered phone number.
  2. Go to Conversations in GHL.
  3. Open the conversation for that contact.
  4. Wait for the AI Agent to process the message.
  5. Verify that the AI Agent sends a response.
Make sure the response:
  • Appears in the correct conversation.
  • Is sent to the correct contact.
  • Follows the configured AI Agent instructions.
Book an Appointment Through the AI Agent
  1. Open the customer's conversation in GHL Conversations.
  2. Send a message such as:
I would like to book an appointment.
  1. Allow the AI Agent to request the required information.
  2. Provide the requested details, such as your preferred date and time.
  3. Confirm the appointment when prompted.
  4. Wait for the AI Agent to confirm the booking.
  5. Go to Calendars in GHL.
  6. Find the appointment using the customer's name or phone number.
  7. Verify the appointment details.
Make sure the correct date, time, time zone, service, and appointment status are shown.
Cancel an Appointment Through the AI Agent
  1. Open the customer's conversation.
  2. Send a message such as:
Please cancel my appointment.
  1. Provide appointment details if requested.
  2. Confirm the cancellation when prompted.
  3. Wait for the AI Agent's confirmation.
  4. Go to Calendars.
  5. Find the customer's appointment.
  6. Confirm that the appointment is marked as Cancelled or is no longer active.
Reschedule an Appointment Through the AI Agent
  1. Open the customer's conversation.
  2. Send a message such as:
Please reschedule my appointment.
  1. Provide the original appointment details if requested.
  2. Provide the preferred new date and time.
  3. Review and confirm the new appointment slot.
  4. Wait for the AI Agent's confirmation.
  5. Go to Calendars.
  6. Find the customer's appointment.
  7. Verify the updated appointment details.
Make sure the new appointment is correct and that the previous appointment is no longer incorrectly active.
Final Verification Checklist

Verification item

Expected result

Correct agency/location

All actions occur in the intended GHL sub-account

Correct contact

Name and phone number match the intended customer

Exact AI Agent tag

The configured tag appears on the contact record

SMS test

The AI Agent replies in the correct conversation thread

Booking request

The customer requests booking through the AI Agent chat

Booking verification

The booked appointment appears correctly in HL Calendar

Cancellation request

The customer requests cancellation through the AI Agent chat

Cancellation verification

The correct appointment is marked Cancelled or inactive

Rescheduling request

The customer requests a new date/time through the AI Agent chat

Rescheduling verification

The new appointment is correct and only one active appointment exists

Duplicate check

No duplicate appointment remains active

Confirmation

AI Agent and Calendar details match

Was this article helpful?

0 out of 0 liked this article

Still need help? Message Us