Work with generative AI Agents

If your team connects MessageMind™ with a knowledge base to fuel its responses, you're using a generative AI Agent. This section contains everything you need to know about how to get your AI Agent up and running.

  • Before you begin
  • Set up your AI Agent's
    knowledge and behavior
  • Integrate MessageMind™ with
    other tools
  • Integrate MessageMind™ with
    Ecommerce platforms
  • Integrate MessageMind™ with
    Booking platforms
  • Manage your AI Agent & Team
  • Deploy MessageMind™
    across channels
  • Measure success
  • Pricing & Billing

Before you begin

Before working on your AI Agent, get some background information on generative content and MessageMind's resolution engine.

When you've used a chatbot in the past, you've probably thought of it as slow or difficult to use. The majority of bots out there aren't great at understanding what your customers want, or knowing how to respond or take actions like a human agent would.

By combining the information in your knowledge base with cutting-edge AI, you don't just have a chatbot with MessageMind™ - you have a generative AI Agent, designed to perform tasks that human agents have previously only been able to do.

This guide will take you through MessageMind™’s technology that we use to make the customer experience with an AI Agent different from any chatbot you've used before.

Understand Large Language Models (LLMs) and Generative AI

The secret behind how your AI Agent both understands and writes messages is in the AI, or artificial intelligence, that MessageMind™ uses behind the scenes. Broadly, AI is a range of complex computer programs designed to solve problems like humans. It can address a variety of situations and incorporate a variety of types of data; in your AI Agent's case, it focuses on analyzing language to connect customers with answers.

When a customer interacts with your AI Agent, your AI Agent uses Large Language Models, or LLMs, which are computer programs trained on large amounts of text, to identify what the customer is asking for. Based on the patterns the LLM identified in the text data, an LLM can analyze a question from a customer and determine the intent behind it. Then, it can analyze information from your knowledge base and determine whether the meaning behind it matches what the customer is looking for.

Generative AI is a type of LLM that uses its analysis of existing content to create new content: it builds sentences word by word, based on which words are most likely to follow the ones it has already chosen. Using generative AI, your AI Agent constructs responses based on pieces of your knowledge base that contain the information the customer is looking for, and phrases them in a natural-sounding and conversational way.

Understand your AI Agent's Content Filters

LLM training data can contain harmful or undesirable content, and generative AI can sometimes generate details that aren't true, which are called hallucinations. To combat these issues, your AI Agent uses an additional set of models to ensure the quality of its responses.

Before sending any generated response to your customer, your AI Agent checks to make sure the response is:

  • Safe: The response doesn't contain any harmful content.
  • Relevant: The response actually answers the customer's question. Even if the information in the response is correct, it has to be the information the customer was looking for in order to give the customer a positive experience.
  • Accurate: The response matches the content in your knowledge base, so your AI Agent can double-check that its response is true.

With these checks in place, you can feel confident that your AI Agent has not only made sound decisions in how to help your customer, but has also sent them high-quality responses.

Understand MessageMind™’s Reasoning Engine

Your AI Agent runs on a sophisticated Reasoning Engine MessageMind™ created to provide customers with the knowledge and solutions they need.

When customers ask your AI Agent a question, it takes into account the following when deciding what to do next:

  • Conversation context: Does the conversation before the current question contain context that would help your AI Agent better answer the question?
  • Knowledge base: Does the knowledge base contain the information the customer is looking for?
  • Business systems: Are there any Actions configured with your AI Agent designed to let it fetch the information the customer is looking for?

From there, it decides how to respond to the customer:

  • Follow-up question: If your AI Agent needs more information to help the customer, it can ask for more information.
  • Knowledge base: If the answer to the customer's inquiry is in the knowledge base, it can obtain that information and use it to write a response.
  • Business systems: If the answer to the customer's inquiry is available using one of the Actions configured in your AI Agent, your AI Agent can fetch that information by making an API call.
  • Handoff: If your AI Agent is otherwise unable to respond to the customer's request, it can hand the customer off to a human agent for further assistance.

Together, the mechanism that makes these complex decisions on how to help the customer is called MessageMind™’s Reasoning Engine. Just like when a human agent makes decisions about how to help a customer based on what they know about what the customer wants, the Reasoning Engine takes into account a variety of information to figure out how to resolve the customer's inquiry as effectively as possible.

Understand How Your AI Agent Prevents Prompt Injections

Many AI chatbots are vulnerable to prompt injections or jailbreaking, which are prompts that get the chatbot to provide information that it shouldn't - for example, information that is confidential or unsafe.

The reasoning engine behind MessageMind™’s AI Agents is structured in such a way as to make adversarial LLM attacks very difficult to succeed. Specifically, it has:

  • A series of AI subsystems interacting together, each of which modifies the context surrounding a customer's message.
  • Several prompt instructions that make the task to be performed very clear, directing the AI Agent to not share inner workings and instructions, and to redirect conversations away from casual chitchat.
  • Models that aim to detect and filter out harmful content in inputs or outputs.

With state-of-the-art generative AI testing prior to new deployments, MessageMind™ ensures a secure and effective customer interaction experience.

When you connect your AI Agent to your knowledge base and start to serve automatically generated content to your customers, it might feel like magic. But it's not! This topic takes you through what happens behind the scenes when you start serving knowledge base content to customers.

How MessageMind™ ingests your knowledge base​

When you link your knowledge base to your AI Agent, your AI Agent copies down all of your knowledge base content, so it can quickly search through it and serve relevant information from it. Here's how it happens:

  1. When you link your AI Agent with your knowledge base, your AI Agent imports all of your knowledge base content.

    Depending on the tools you use to create and host your knowledge base, your knowledge base then updates with different frequencies:

    • If your knowledge base is in Zendesk or Salesforce, your AI Agent checks back for updates every 15 minutes.

      • If your AI Agent hasn't had any conversations, either immediately after you linked it with your knowledge base or in the last 30 days, your AI Agent pauses syncing. To trigger a sync with your knowledge base, have a test conversation with your AI Agent.

    • If your knowledge base is hosted elsewhere, you or your MessageMind™ team have to build an integration to scrape it and upload content to MessageMind's Knowledge API. If this is the case, the frequency of updates depends on the integration.

  2. Your AI Agent splits your articles into chunks, so it doesn't have to search through long articles each time it looks for information - it can just look at the shorter chunks instead.

    While each article can cover a variety of related concepts, each chunk should only cover one key concept. Additionally, your AI Agent includes context for each chunk; each chunk contains the headings that preceded it.

  3. Your AI Agent sends each chunk to a Large Language Model (LLM), which it uses to assign the chunks numerical representations that correspond to the meaning of each chunk. These numerical values are called embeddings, and it saves them into a database.

    The database is then ready to provide information for GPT to put together into natural-sounding responses to customer questions.

How MessageMind™ creates responses from knowledge base content​

After saving your knowledge base content into a database, your AI Agent is ready to provide content from it to answer your customers' questions. Here's how it does that:

  1. Your AI Agent sends the customer's query to the LLM, so it can get an embedding (a numerical value) that corresponds with the information the customer was asking for.

    Before proceeding, the AI Agent sends the content through a moderation check via the LLM to see if the customer's question was inappropriate or toxic. If it was, your AI Agent rejects the query and doesn't continue with the answer generation process.

  2. Your AI Agent then compares embeddings between the customer's question and the chunks in its database, to see if it can find relevant chunks that match the meaning of the customer's question. This process is called retrieval.

    Your AI Agent looks for the best match in meaning in the database to what the customer asked for, which is called semantic similarity, and saves the top three most relevant chunks.

    If the customer's question is a follow-up to a previous question, your AI Agent might get the LLM to rewrite the customer's question to include context to increase the chances of getting relevant chunks. For example, if a customer asks your AI Agent whether your store sells cookies, and your AI Agent says yes, your customer may respond with "how much are they?" That question doesn't have enough information on its own, but a question like "how much are your cookies?" provides enough context to get a meaningful chunk of information back.

    If your AI Agent isn't able to find any relevant matches to the customer's question in the database's chunks at this point, it serves the customer a message asking them to rephrase their question or escalates the query to a human agent, rather than attempting to generate a response and risking serving inaccurate information.

  3. Your AI Agent sends the three chunks from the database that are the most relevant to the customer's question to GPT to stitch together into a response. Then, your AI Agent sends the generated response through three filters:

    1. The Safety filter checks to make sure that the generated response doesn't contain any harmful content.

    2. The Relevance filter checks to make sure that the generated response actually answers the customer's question. Even if the information in the response is correct, it has to be the information the customer was looking for in order to give the customer a positive experience.

    3. The Accuracy filter checks to make sure that the generated response matches the content in your knowledge base, so it can verify that the AI Agent's response is true.

  4. If the generated response passes these three filters, your AI Agent serves it to the customer.

Set up your AI Agent's knowledge and behavior

Connect your knowledge base with your AI Agent, and fine tune its behavior, so it can provide the highest quality responses to your customers.

In this article, you will learn how to train your AI Agent using your website content. You can add multiple websites simultaneously if necessary. This guide covers the process found in Step 2 of the initial setup.

Adding a Website During Setup

  1. Navigate to Basic AI Settings: In Step 2 of the setup process, you will customize your AI's basic settings.
  2. Enter Your Website URL: In the "Enter Your Website" section, type in the address of your website, ensuring it starts with https:// or http://.
  3. Initiate Crawling: Click the Explore Website button. Wait as the system thoroughly crawls and analyzes your website content. The progress bar will indicate the completion status. Once the process is complete, your AI will begin to learn from the imported data.
 

Adding a Hotel During Setup

For hotel businesses, you can search for and add your hotel directly through our platform during the initial setup.

  1. Find Your Hotel: In the "Find Your Hotel" section, enter the name or location of the hotel where you plan to implement the AI agent. This allows us to tailor the analysis specifically to understand and serve your needs better.
  2. Select Your Hotel: Once your hotel appears in the search results, select it to proceed with the crawling and analysis process.
 

Basic AI Settings

In Step 2, you will also configure other basic settings for your AI:

  1. Name Your AI Employee: Create a unique name for your AI assistant to make it recognizable to customers.
  2. Set the Length of Generated Text: Choose how chatty your AI will be—short, medium, or long text.
  3. Tone Settings: Select up to two tones that resonate with your brand's heart. Options include Friendly and Casual, Professional and Formal, Enthusiastic and Energetic, among others.

💡 TIP: Frequent updates and optimizations ensure that your AI Agent remains aligned with the most current and relevant information from your website.

By following these steps, you can effectively train your AI Agent to provide precise and helpful information to your users, whether for general business purposes or tailored specifically for the hospitality industry.

You can train your AI Agent by uploading various types of files. The following guide will help you understand how to add these files to optimize your AI's performance based on your selected category or industry.

Supported File Types

  • PDF
  • Word (*.docx)
  • Excel (*.xlsx)
  • CSV

 

Adding a File to Your AI Agent

  1. Navigate to the AI Training Section: From the dashboard, navigate to AI Settings, then to the AI Training section.
  2. Upload a File: Depending on the specific section (e.g., Products, Additional Information), you will find an option to upload files.
    • For Products, click the Add file option under the "Add Your First Product" section.
    • For other sections with long text boxes, look for the file upload icon.
  3. Select Your Files: Drag and drop your files into the highlighted area or click the upload text to select files from your computer.
  4. Wait for Processing: Once the upload is complete, wait a few seconds for the AI Agent to learn the content of the files.
 

Structuring Your Files for Optimal Training

Different types of files may require specific structures for the best training results:

  • Textual Files (PDF and Word): For these files, it's best to structure the documents with clear paragraph divisions.

    Tip: Lists should be included as FAQs. For example, instead of a long list of company locations, create a FAQ like "What are the locations of XYZ company?" with the locations separated by commas.

  • Tabular Files (Excel and CSV): Ensure the first row contains column names, with subsequent rows containing data entries.

    Note: There is no strict limit on the number of columns, but it's advisable to keep it below 15 for efficiency.

 

Example of File Upload Process

Here’s an example to help you visualize the process:

  1. Navigate to the Products Section:

    • Click on Add Product and select Add file.
    • Upload your product file (e.g., a CSV with product details).

  2. Additional Information:

    • In sections like "Additional/Important Information", click the file upload icon to add relevant files.

💡 TIP: In general, the more compact and structured the information, the better it is for the AI training process.

By following these steps, you can effectively upload and optimize files to enhance your AI Agent's performance, tailored to your specific industry needs.

In this article, you will learn how to customize your AI agent’s behavior to align with your brand's persona and interaction style. These settings are configurable during the initial setup and later through the AI Training section.

 

Initial Setup

During the initial setup process, you can set the basic characteristics of your AI agent.

  1. Navigate to Step 2: Basic Settings:
    • Here, you can customize the name, verbosity, and tone of your AI agent.
  2. Name Your AI Employee:
    • Create a unique name for your AI assistant to make it recognizable to customers.
  3. Adjust AI Verbosity:
    • Choose how chatty your AI will be by selecting Short, Medium, or Long text.
  4. Set Tone Settings:
    • Select up to two tones that reflect your brand. Options include Professional and Formal, Friendly and Casual, Empathetic and Supportive, etc.

Configuring AI Behavior in AI Training Section

After the initial setup, you can further customize your AI agent's behavior by navigating through the dashboard.

  1. Access AI Training:
    • From the dashboard, go to AI Settings and then click on AI Training.
  2. AI Agent Features:
    • Here, you can reconfigure the name, verbosity, and tone settings if needed.
  3. Select AI Identity:
    • Choose whether your AI agent presents itself as a Human or AI to your users.
  4. Adjust Wait Times:
    • Set wait times for inactive and active users to control the responsiveness of your AI agent. You can also toggle wait time adjustments based on response length.

Detailed Steps for Customizing Behavior

  1. Name Your AI Employee:
    • In the AI Agent Features section, you can update the name of your AI employee at any time.
  2. Adjust AI Verbosity:
    • Reconfigure how verbose your AI agent should be—select Short, Medium, or Long text based on the desired interaction length.
  3. Select Tone Settings:
    • You can change the tone settings to reflect different aspects of your brand's personality. Options include:
      • Professional and Formal
      • Friendly and Casual
      • Empathetic and Supportive
      • Concise and Direct
      • Informative and Educational
      • Enthusiastic and Energetic
      • Adaptive and Personalized
      • Humorous and Witty
      • Respectful and Inclusive
      • Reassuring and Confident
  4. Set AI Identity:
    • Decide if your AI agent should be perceived as a Human or AI in interactions.
  5. Adjust Wait Times:
    • Configure the wait times for responses to ensure the interaction pace matches user expectations.

💡 TIP: Regularly review and adjust these settings to ensure your AI agent continues to reflect your brand’s evolving personality and interaction style.

By following these steps, you can effectively manage and tailor your AI agent’s behavior to provide a consistent and engaging user experience with MessageMind™.

In this article, you will learn how to enable and manage multilingual support for your AI agent, enhancing your customer interactions by communicating in their preferred language.

 

Understand Multilingual Content Support

Communicating with your customers in their preferred language makes them feel valued and understood. Use your AI agent's multilingual functionality to provide that personalized experience to each of your customers.

 

Supported Languages

MessageMind™'s multilingual functionality supports the following languages:

  • Albanian
  • Arabic
  • Belarusian
  • Bosnian
  • Bulgarian
  • Burmese
  • Catalan
  • Chinese (Simplified)
  • Chinese (Traditional)
  • Croatian
  • Czech
  • Danish
  • Dutch
  • English
  • Estonian
  • Filipino (Tagalog)
  • Finnish
  • French
  • German
  • Greek
  • Haitian Creole
  • Hebrew
  • Hindi
  • Hungarian
  • Icelandic
  • Indonesian
  • Italian
  • Japanese
  • Kazakh
  • Khmer
  • Korean
  • Latvian
  • Lithuanian
  • Malay
  • Norwegian
  • Polish
  • Portuguese
  • Punjabi
  • Romanian
  • Russian
  • Serbian
  • Slovak
  • Slovenian
  • Spanish
  • Swedish
  • Tamil
  • Thai
  • Turkish
  • Ukrainian
  • Vietnamese

For supported right-to-left languages, the chat is tailored for the best customer experience, including flipped UI components such as settings and loading bars.

 

How Multilingual Support Works

English is the default support language in all MessageMind™ AI agents. Your AI agent will always be able to reply to English-speaking customers. Additionally, your AI agent understands customer questions in any supported language and responds accordingly based on the detected language.

 

Setting the Starting Language

The starting language for your AI agent is determined by the phone number used during the sign-up process, which typically aligns with the location. The AI agent will start interactions in this default language.

 

Automatic Language Detection and Response

With multilingual support enabled, your AI agent can:

  1. Determine the Language:
    • Automatically detect the language the customer is using.
  2. Respond Appropriately:
    • Use the detected language for responses if it is among the supported languages. If the language is not supported, the AI agent will respond in English.

Best Practices for Language Support

  • Enable Only Necessary Languages:
    • Ensure that your support agents can handle the languages enabled to avoid miscommunication.
  • Have Language Experts:
    • Ensure that someone on your team speaks each enabled language to review conversations and gauge the AI agent's performance.

 

Managing Language Preferences

While the AI agent starts in the default language, customers can change the chat language using one of the following methods:

  • Autodetect:
    • If a customer types a message of at least three words and 20 characters in an enabled language, the AI agent will try to identify and switch to that language.
  • Language Name:
    • If a customer types the exact name of an enabled language (e.g., "French" or "Français"), the AI agent will switch to that language.

By following these steps, you can effectively manage and tailor your AI agent’s multilingual support to provide a consistent and engaging user experience with MessageMind™.

Integrate MessageMind™ with other tools

Got other customer support tools you want to use with MessageMind™? No problem - learn all about how our integrations work here.

Expand your AI agent's functionality by configuring API calls through the Actions feature. Depending on the selected category or industry niche, different integrations are available, such as eCommerce platforms, booking platforms, and financial services APIs.

Accessing API Integrations

  1. Navigate to Integrations:
    • From the dashboard, go to AI Settings and then click on Integrations.

Available Integrations

MessageMind™ offers various integrations to enhance your AI agent’s capabilities. Here are some examples:

  • eCommerce Platforms: Connect platforms like Shopify, WooCommerce, etc.
  • Booking Platforms: Integrate with booking services like Google Meet, Zoom, Calendly, etc.
  • Financial Platforms: Link to services like Stripe, Revolut, etc.
  • Hotel Management Platforms: Integrate with hotel booking platforms like Booking.com, Expedia etc...

If you need a specific integration that is not listed, contact us privately, and we will assist with the setup.

Currency Conversion and Package Tracking

Currency conversion and package tracking features are active by default for all eCommerce integrations.

Best Practices for API Integrations

  • Ensure Accuracy:
    • Regularly review and test API calls to ensure they are functioning correctly and returning the expected data.
  • Secure Authentication:
    • Use authentication tokens where necessary to keep your API calls secure.

By following these steps, you can configure API calls with Actions to enhance the functionality of your AI agent, providing precise and context-aware responses to your customers with MessageMind™.

MessageMind™ provides seamless integration with various eCommerce platforms to enhance your online store's functionality through AI-powered messaging. This section will guide you through the steps to connect your eCommerce store with MessageMind™, ensuring smooth operations and enhanced customer interactions.

Getting Started

To get started, log into your MessageMind™ account and navigate to the 'AI Settings' section.

Next, proceed to the 'Integrations' tab where you can manage connections to various eCommerce platforms.

 

Integrating with eCommerce Platforms

To connect your eCommerce platform, there are specific guides and tutorials available below based on your website builder, including Shopify, WooCommerce, Wix, BigCommerce, and Squarespace.

Integrate MessageMind™ with booking platforms to streamline scheduling and offer seamless booking experiences to your customers. Currently, MessageMind™ supports integration with Calendly and Booking.com allowing your AI Agent to manage and offer booking options directly through the chat.

Getting Started

To get started, from your MessageMind dashboard, navigate to the upper menu and click on AI Settings.

Next, within the AI Settings menu, click on Integrations.

Integrating with Booking Platforms

To connect to your booking platform, there are specific guides and tutorials available below based on the desired booking tool, including Calendly and Booking.com.

Integrate MessageMind™ with Ecommerce platforms

Got other customer support tools you want to use with MessageMind™? No problem - learn all about how our integrations work here.

Before connecting your Shopify platform, you will need specific credentials. Below is a guide on how to find the necessary information for each platform, followed by the steps to integrate it with MessageMind™.

Finding Necessary Information

  1. Store Name: This is the name of your Shopify store, usually in the format yourstore-name.
  2. API Key: You can create an API key by navigating to the 'Apps' section in your Shopify admin, then clicking on 'Manage private apps' and creating a new private app. Follow Shopify's guide for detailed steps.

Integration Steps

  1. In the 'Integrations' tab, select 'Shopify'.
  2. Enter your Store Name and API Key.
  3. Click 'Connect' to enable the integration.

By following these steps, you can integrate your Shopify store with MessageMind™ and leverage AI-powered functionalities to streamline order processing, customer service, inventory management, and personalized recommendations. If you encounter any issues or need further assistance, please reach out to our support team via the 'Help' section in your MessageMind™ dashboard.

Before connecting your WooCommerce store, you will need specific credentials. Below is a guide on how to find the necessary information for each platform, followed by the steps to integrate it with MessageMind™.

Finding Necessary Information
  1. Store URL: This is the URL of your WooCommerce store.
  2. Consumer Key and Consumer Secret: You can find these in the WooCommerce settings under 'Advanced' > 'REST API'. Create a new key and copy the credentials. Follow WooCommerce's documentation for detailed steps.
Integration Steps
  1. In the 'Integrations' tab, select 'WooCommerce'.
  2. Enter your Store URL, Consumer Key, and Consumer Secret.
  3. Click 'Connect' to establish the connection.
By following these steps, you can integrate your WooCommerce store with MessageMind™ and leverage AI-powered functionalities to streamline order processing, customer service, inventory management, and personalized recommendations. If you encounter any issues or need further assistance, please reach out to our support team via the 'Help' section in your MessageMind™ dashboard.

Before connecting your Wix store, you will need specific credentials. Below is a guide on how to find the necessary information for each platform, followed by the steps to integrate it with MessageMind™.

Finding Necessary Information

  1. API Key or App ID: You can find this by creating an API key in your Wix Developer dashboard.
  2. API Secret: Generated alongside the API key in the Wix Developer dashboard. Follow Wix's guide for detailed steps.

Integration Steps

  1. In the 'Integrations' tab, select 'Wix eCommerce'.
  2. Enter your API Key or App ID and API Secret.
  3. Click 'Connect' to synchronize your data.
 

BigCommerce

Finding Necessary Information

  1. API Token, Client ID, and Store Hash: These can be found by navigating to the BigCommerce control panel, going to 'Settings' > 'API Accounts', and creating a new API account. Follow BigCommerce's documentation for detailed steps.

Integration Steps

  1. In the 'Integrations' tab, select 'BigCommerce'.
  2. Provide your API Token, Client ID, and Store Hash.
  3. Click 'Connect' to enable the integration.

By following these steps, you can integrate your Wix store with MessageMind™ and leverage AI-powered functionalities to streamline order processing, customer service, inventory management, and personalized recommendations. If you encounter any issues or need further assistance, please reach out to our support team via the 'Help' section in your MessageMind™ dashboard.

Before connecting your Big Commerce store, you will need specific credentials. Below is a guide on how to find the necessary information for each platform, followed by the steps to integrate it with MessageMind™.

Finding Necessary Information

  1. API Token, Client ID, and Store Hash: These can be found by navigating to the BigCommerce control panel, going to 'Settings' > 'API Accounts', and creating a new API account. Follow BigCommerce's documentation for detailed steps.

Integration Steps

  1. In the 'Integrations' tab, select 'BigCommerce'.
  2. Provide your API Token, Client ID, and Store Hash.
  3. Click 'Connect' to enable the integration.

By following these steps, you can integrate your BigCommerce store with MessageMind™ and leverage AI-powered functionalities to streamline order processing, customer service, inventory management, and personalized recommendations. If you encounter any issues or need further assistance, please reach out to our support team via the 'Help' section in your MessageMind™ dashboard.

Before connecting your SquareSpace store, you will need specific credentials. Below is a guide on how to find the necessary information for each platform, followed by the steps to integrate it with MessageMind™.

Finding Necessary Information

  1. Secret API Key: You can generate this in your SquareSpace Developer settings under 'API Keys'. Follow SquareSpace's guide for detailed steps.

Integration Steps

  1. In the 'Integrations' tab, select 'SquareSpace'.
  2. Enter the Secret API Key in the field provided.
  3. Click 'Connect' to link your store.

By following these steps, you can integrate your SquareSpace store with MessageMind™ and leverage AI-powered functionalities to streamline order processing, customer service, inventory management, and personalized recommendations. If you encounter any issues or need further assistance, please reach out to our support team via the 'Help' section in your MessageMind™ dashboard.

Integrate MessageMind™ with Booking platforms

Got other customer support tools you want to use with MessageMind™? No problem - learn all about how our integrations work here.

Follow these steps to connect Calendly to your MessageMind™ AI Agent.

Step-by-Step Guide to Connect Calendly
  1. Access AI Settings: From your MessageMind dashboard, navigate to the upper menu and click on AI Settings.
  2. Go to Integrations: Within the AI Settings menu, click on Integrations.
  3. Find Booking Integrations: Scroll down to the Booking Integrations section.
  4. Connect Calendly: Locate Calendly in the list of booking options and click on it. Click on the Connect Calendly button.
  5. Authorize Calendly: A Calendly pop-up will appear, prompting you to log in to your Calendly account. Enter your credentials and log in.
  6. Select an Event: After logging in, you will be redirected to a page where you can select one event type for your AI Agent to manage and offer to your clients. You can choose from two types of events:
    • Unsupported Events: The AI Agent can manage availability, send booking links, and handle meeting deletions.
    • Supported Events: Includes all the features of unsupported events plus the ability for the AI Agent to book consultations directly for your clients.
  7. Choose an Event Type: Select either an unsupported or supported event type based on your needs.
  8. Save the Integration: After selecting your event type, click Save to confirm your settings.
  9. Integration Complete: Your MessageMind™ AI Agent is now connected to Calendly! It will use the selected event type to offer booking options to your clients seamlessly.

With this integration, your AI Agent can efficiently manage bookings and enhance your customer service by providing direct scheduling options within the chat, reducing the need for manual back-and-forth communication.

Manage your AI Agent

Set your AI Agent up for success! Learn how to customize its look and feel, and to manage your team's access in the dashboard.

Manage Users and Permissions

Add a User

  1. On the MessageMind dashboard, click on your profile name, then select Team.
  2. Click on "Add Team". Enter the new team member's name and email.
  3. Choose a permission level for the user from the options listed.
  4. Click Send Invitation. The team member will receive an invitation email with a signup link.

The new user will now appear in your team member list.

Delete a User

  1. On the MessageMind dashboard, click your profile name, then select Team.
  2. In the user list, click the Delete button beside the user you want to delete.
  3. Confirm the deletion by clicking Delete. The user will be removed from the list.

User Roles and Permissions

  • Admin: Full access, except for editing or deleting team roles.
  • Inbox Manager: Full access to the web inbox, can edit, assign, and transfer chats or agents.
  • Agent: Can read all content but only edit and manage chats assigned to them.
  • Basic Agent: Can only view and manage their own assigned chats.

Only Owners can add or remove team members.

 

ActionAdminInbox ManagerAgentBasic Agent
Insights    
Analytics✔✘✘✘
Conversations✔✔✔✔
Inbox    
Assign Chats✔✔✘✘
View Own Chats✔✔✔✔
View All Chats✔✔✔✘
Reply Own Chats✔✔✔✔
Reply All Chats✔✔✘✘
AI Settings    
Activity Log✔✘✘✘
AI Training✔✘✘✘
Integrations    
Edit Integrations✔✘✘✘
View Integrations✔✘✘✘
Channels    
Manage Channels✔✘✘✘
General Settings    
Edit General Settings✔✘✘✘
Payment & Invoices    
Manage Payments✔✘✘✘
View Invoices✔✘✘✘
Team Management    
View Team Members✔✘✘✘
Edit Team Members✘✘✘✘

Testing allows you to interact with your AI Agent as your customers would, replicating their experiences and observing how your AI Agent handles various inquiries.

Get Started with Testing

Once your knowledge base is connected to your AI Agent, follow these steps to begin testing:

  1. In your MessageMind dashboard, navigate to the upper menu and click AI Settings.

  2. Click on AI Sandbox.

  3. The MessageMind Playground will launch.

  4. Type a message in the chat and press Enter to see how your AI Agent responds.

  5. On the left side of the Playground, you can customize your AI Agent by editing the length of the text, adjusting the tone, and adding specific issues to address. After making your edits, click Save to test the new configurations.

  6. Continue testing by sending various messages and inquiries.

Customize Your AI Agent

On the left side of the Playground, you can customize your AI Agent with the following features:

1. Name of Your AI Employee

Personalize your AI Agent by changing its name to better fit your brand or desired customer interaction style. Enter the new name in the provided text box, and your AI Agent will use this name in all interactions.

2. Text Length

Adjust the response length of your AI Agent to match your needs:

  • Short (Recommended): Provides brief and concise answers, making interactions quick and efficient for users.
  • Medium: Balances detail with brevity, offering clear and engaging responses while maintaining conciseness.
  • Long: Offers more comprehensive and detailed replies for scenarios where in-depth information is needed.

Select the response length that best suits the nature of your inquiries and audience expectations.

3. Tone Settings

Define the tone of your AI Agent to reflect the desired personality and style. You can select up to two tones from the following options:

  • Professional and Formal
  • Friendly and Casual
  • Empathetic and Supportive
  • Concise and Direct
  • Informative and Educational
  • Enthusiastic and Energetic
  • Adaptive and Personalized
  • Humorous and Witty
  • Respectful and Inclusive
  • Reassuring and Confident

Choose tones that align with your brand’s voice and the user experience you want to provide.

4. Have a Specific Issue?

If there are specific issues or adjustments you want to make to your AI Agent’s responses, use the open text box to describe your needs. This feature allows you to:

  • Request specific phrase changes.
  • Address unique customer concerns or scenarios.
  • Provide other customization instructions to refine your AI Agent's behavior.

 

Save and Test Your Changes

After making your edits in each section, click Save to apply the changes. Test the new configurations by continuing to interact with your AI Agent in the chat, ensuring the updates meet your expectations.

Deploy MessageMind™ across channels

Integrate with third-party channels to bring the chat experience everywhere your chatters are.

Expand your AI agent's functionality by configuring API calls through the Actions feature. Depending on the selected category or industry niche, different integrations are available, such as eCommerce platforms, booking platforms, and financial services APIs.

Accessing API Integrations

  1. Navigate to Integrations:
    • From the dashboard, go to AI Settings and then click on Integrations.

Available Integrations

MessageMind™ offers various integrations to enhance your AI agent’s capabilities. Here are some examples:

  • eCommerce Platforms: Connect platforms like Shopify, WooCommerce, etc.
  • Booking Platforms: Integrate with booking services like Google Meet, Zoom, Calendly, etc.
  • Financial Platforms: Link to services like Stripe, Revolut, etc.
  • Hotel Management Platforms: Integrate with hotel booking platforms like Booking.com, Expedia etc...

If you need a specific integration that is not listed, contact us privately, and we will assist with the setup.

Currency Conversion and Package Tracking

Currency conversion and package tracking features are active by default for all eCommerce integrations.

Best Practices for API Integrations

  • Ensure Accuracy:
    • Regularly review and test API calls to ensure they are functioning correctly and returning the expected data.
  • Secure Authentication:
    • Use authentication tokens where necessary to keep your API calls secure.

By following these steps, you can configure API calls with Actions to enhance the functionality of your AI agent, providing precise and context-aware responses to your customers with MessageMind™.

Adding a web chat widget to your WordPress website is a quick and easy process. It does not require any coding skills or technical knowledge.

WordPress Logo

Setting Up for Installation

In order to install a web chat widget on WordPress, you will need the following:

  • Access to your website's WordPress Dashboard.
  • A code snippet for your web chat widget.

If you don't have a code snippet already, you will generate one when creating a messagemind.ai Website Chat Widget.

For successful installation, ensure your website chat widget is activated. Here is how to do so:

Go to messagemind.ai Settings > select Channels > select the Website Chat channel > click Activate Website Chat.

 

Installing on WordPress

Step 1: Log in to WordPress

Navigate to your website’s WordPress Admin Dashboard and log in.

WordPress Log In Page

 

Step 2: Navigate to the Plugins Page

From the left navigation panel, click on Plugins. On the Plugins Page, press the blue Add New button on the top of the page.

WordPress Plugin Page - add new button

 

Step 3: Add New Plugin

Using the search bar, search for the Insert Header and Footers plugin. You will see many options on the search result page that you can use, but we will be using the "Insert Header and Footers" plugin by WPBeginner for this tutorial. Press the Install Now button and make sure you activate the plugin to make use of it.

WordPress Plugin Page - install header & footer

 

Step 4: Open Headers and Footer Console

From the left navigation menu, click on Settings and select the Insert Headers and Footers plugin from the settings submenu.

WordPress Plugin Page - navigating to settings and header & footer

 

Step 5: Add the Live Chat Script

Copy your plugin script from messagemind.ai and paste it into the Script in Header section of the Header and Footer console page.

 

Once you have pasted the script, click on the blue "Save" button at the bottom of the page.

Done!

Open the website and check out the chat plugin. You will find it in the bottom-right corner. Now your website visitors can chat effortlessly with you. If you used the code snippets generated from the messagemind.ai platform, you will be able to manage the conversations and update the appearance of the widget from the Platform.

Adding a web chat widget to your Shopify store is a quick and easy process. It does not require any coding skills or technical knowledge.

Shopify Logo

 

Setting Up for Installation

In order to install a web chat widget on Shopify, you will need the following:

If you don't have a code snippet already, you will generate one when creating a messagemind.ai Website Chat Widget.

For successful installation, ensure your website chat widget is activated. Here is how to do so:

Go to messagemind.ai Settings > select Channels > select the Website Chat channel > click Activate Website Chat.

 

Installing on Shopify

Step 1: Log in to Shopify

Log in to your Shopify account and click on "Online Store" on the navigation bar.

Shopify account online store page

 

Step 2: Click on Edit Code

Navigate to the Themes section. Here, click on the Actions dropdown menu and select the Edit Code option.

Shopify account online store themes page

 

Step 3: Paste the Script

Copy your plugin script from the messagemind.ai platform. On the left panel of the Edit Code Page, click the Sections folder to expand it. Press the header.liquid section and paste the chat plugin script.

Once you have pasted the script into the appropriate section, press the purple Save button on the top left.

 

Done!

Open the website and check out the chat plugin. You will find it in the bottom-right corner. Now your website visitors can chat effortlessly with you. If you used the code snippets generated from the messagemind.ai platform, you will be able to manage the conversations and update the appearance of the widget from the Platform.

Adding a web chat widget to your Wix website is a quick and easy process. It does not require any coding skills or technical knowledge.

Wix logo

 

In order to install a web chat widget on Wix, you will need the following:

  • Access to your Wix account.
  • A code snippet for your web chat widget.

If you don't have a code snippet already, you will generate one when creating a messagemind.ai Website Chat Widget.

For successful installation, ensure your website chat widget is activated. Here is how to do so:

Go to messagemind.ai Settings > select Channels > select the Website Chat channel > click Activate Website Chat.

 

Installing on Wix

Step 1: Sign in to your Wix Account.

Step 2: Navigate to Settings > Advanced Settings > Tracking & Analytics > + New Tool > Custom.

Wix tracking & analytics page

 

Step 3: Add the code snippet generated from the messagemind.ai platform to the paste the code snippet here field.

Wix custom code dialog

 

Step 4: Complete the form as required and click Apply to save the changes.

Adding a web chat widget to your Squarespace website is a quick and easy process. It does not require any coding skills or technical knowledge.

Squarespace logo

 

Setting Up for Installation

In order to install a web chat widget on Squarespace, you will need the following:

If you don't have a code snippet already, you will generate one when creating a messagemind.ai Website Chat Widget.

For successful installation, ensure your website chat widget is activated. Here is how to do so:

Go to messagemind.ai Settings > select Channels > select the Website Chat channel > click Activate Website Chat.

 

Installing on Squarespace

Step 1: Log in to Squarespace

Log in to your Squarespace account. Under the Websites tab, select the website to which you want to add the plugin.

Squarespace dashboard

 

Step 2: Open settings

From the left navigation panel, select Settings.

Squarespace navigate to settings

 

Step 3: Open Advanced Settings

From there, navigate to the Website section and click on Advanced.

Squarespace Navigate to Advanced Settings

 

Step 4: Open the Code Injection Console

From the advanced settings menu, select Code Injection.

Squarespace Navigate to Code injection settings

 

Step 5: Paste the Script

Copy your plugin script from messagemind.a and paste the script into the Header section.

Once you have pasted the code, press Save on the top left.

 

Done!

Open the website and check out the chat plugin. You will find it in the bottom-right corner. Now your website visitors can chat effortlessly with you. If you used the code snippets generated from the messagemind.ai platform, you will be able to manage the conversations and update the appearance of the widget from the Platform.

Measure success

Looking to validate your AI Agent's content? Use these resources to analyze data about chatter interactions for success, so you can be confident in making data-driven decisions.

To continuously improve your AI agent's performance and enhance user satisfaction, it is crucial to analyze past interactions. Reviewing historical conversations allows you to identify patterns, understand user needs, and pinpoint areas where your AI might be falling short. Here’s a guide on how to effectively use past conversations to measure success and make data-driven improvements:

1. Identify Key Performance Metrics

  • Define what success looks like for your AI agent. Common metrics include response accuracy, user satisfaction, completion rates of tasks, and engagement levels.
  • Utilize these metrics to assess how well your AI is performing against your set goals.

2. Analyze Conversation Patterns

  • Review conversations to detect frequent questions, common issues, and areas where the AI excels or struggles.
  • Look for repeated user feedback, especially where users express confusion or dissatisfaction, as these are critical improvement areas.

3. Evaluate Response Accuracy and Relevance

  • Check how accurately and relevantly your AI agent is responding to user queries. Highlight instances where the AI provided incorrect or vague answers.
  • Track instances where the AI failed to understand user intent or required users to rephrase questions multiple times.

4. Monitor User Sentiment

  • Use sentiment analysis tools to gauge the emotional tone of user interactions. Positive sentiment indicates satisfactory experiences, while negative sentiment can highlight areas needing improvement.
  • Focus on improving responses in conversations that had a negative sentiment to enhance the overall user experience.

5. Incorporate Feedback Loops

  • Implement mechanisms for users to provide feedback on the AI’s performance directly within the conversation. This could be through ratings, comments, or specific feedback prompts.
  • Use this feedback to refine the AI’s responses and adjust the training data accordingly.

6. Refine and Retrain Your AI Model

  • Based on the insights gathered, update your AI’s knowledge base and refine the response generation logic.
  • Retrain your AI model periodically using improved datasets derived from past conversations, focusing on areas identified as needing enhancement.

7. Set Up Continuous Monitoring

  • Establish ongoing monitoring of conversations to catch new issues early. This proactive approach ensures that your AI agent evolves along with changing user needs and expectations.
  • Use dashboards or analytics tools to keep track of performance metrics and improvement areas in real-time.

8. Test and Validate Improvements

  • After making changes, validate the improvements by testing the AI with real or simulated conversations. Ensure that the modifications result in better responses without introducing new issues.
  • Continue to iterate based on the outcomes of these tests, refining your AI agent’s capabilities over time.

By regularly reviewing past conversations, you gain valuable insights into your AI agent's performance and areas for improvement. This process not only helps in troubleshooting current issues but also empowers you to proactively enhance your AI’s effectiveness, leading to a better overall user experience and achieving your desired success metrics.

Expand your AI agent's functionality by configuring API calls through the Actions feature. Depending on the selected category or industry niche, different integrations are available, such as eCommerce platforms, booking platforms, and financial services APIs.

Accessing API Integrations

  1. Navigate to Integrations:
    • From the dashboard, go to AI Settings and then click on Integrations.

Available Integrations

MessageMind™ offers various integrations to enhance your AI agent’s capabilities. Here are some examples:

  • eCommerce Platforms: Connect platforms like Shopify, WooCommerce, etc.
  • Booking Platforms: Integrate with booking services like Google Meet, Zoom, Calendly, etc.
  • Financial Platforms: Link to services like Stripe, Revolut, etc.
  • Hotel Management Platforms: Integrate with hotel booking platforms like Booking.com, Expedia etc...

If you need a specific integration that is not listed, contact us privately, and we will assist with the setup.

Currency Conversion and Package Tracking

Currency conversion and package tracking features are active by default for all eCommerce integrations.

Best Practices for API Integrations

  • Ensure Accuracy:
    • Regularly review and test API calls to ensure they are functioning correctly and returning the expected data.
  • Secure Authentication:
    • Use authentication tokens where necessary to keep your API calls secure.

By following these steps, you can configure API calls with Actions to enhance the functionality of your AI agent, providing precise and context-aware responses to your customers with MessageMind™.

Pricing & Billing

Looking to validate your AI Agent's content? Use these resources to analyze data about chatter interactions for success, so you can be confident in making data-driven decisions.

Explore how META's pricing structure works for customer conversations. Instead of charging per message, fees are based on the type and duration of each conversation. Learn more below.

 

Overview

META doesn't charge for individual messages. Instead, you are charged for conversations, which are defined as chats between you and a customer that last for 24 hours.

Categories

Template conversations fall into categories. There are three types:

  • Marketing: When you send messages about promos, updates, or invites.
  • Utility: These help with specific requests, like confirming transactions.
  • Authentication: Used to verify users, like one-time passcodes during login.
 

Customer Service Window

When a customer messages you on WhatsApp, there's a 24-hour timer. While it's running, you can send different types of messages. During this duration, businesses can converse with the customers in any free-form or normal text messages. After 24 hours, you can only send template messages.

Conversation Duration

Most conversations on WhatsApp last 24 hours. If a new conversation starts, it resets the timer.

How Marketing, Utility & Authentication Conversation charged

  • Other than service conversation, all other conversation initiated from the business end needs to be done by sending a template.
  • On sending a template message now, each of the templates opens up a 24-hour window of that type of conversation.
  • Once the message is delivered, the pricing will be charged based on the conversation type window opened.
  • If a customer replies, a business can then send any free-form or normal text message.
 

Free Tier Conversations

You get 1,000 free service conversations every month. They reset at the beginning of each month.

Free Entry Point or Service Conversations

These start when a customer messages via a Click to WhatsApp Ad or a Facebook Page Call-to-Action button. It lasts 72 hours, and you can send any message in that time without extra charges.

 

WhatsApp New Conversation Pricing in USD

Country/RegionMarketingUtilityAuthentication
Argentina0.07110.03910.0422
Brazil0.07190.00920.0362
Chile0.10220.02300.0606
Colombia0.01440.00020.0089
Egypt0.12340.00600.0711
France0.16470.03450.0795
Germany0.15700.06330.0883
India0.01230.00160.0048
Indonesia0.04730.02300.0345
Israel0.04060.00610.0194
Italy0.07950.03450.0435
Malaysia0.09890.01610.0207
Mexico0.05010.01150.0275
Netherlands0.18370.05750.0828
Nigeria0.05930.00770.0330
Pakistan0.05440.00620.0262
Peru0.08080.02300.0434
Russia0.09220.04600.0493
Saudi Arabia0.05230.01320.0260
South Africa0.04360.00870.0207
Spain0.07070.02300.0393
Turkey0.01250.00610.0095
United Arab Emirates0.04420.01810.0205
United Kingdom0.06080.02530.0412
North America0.02880.00460.0155
Rest of Africa0.02590.00700.0166
Rest of Asia Pacific0.08420.01810.0489
Rest of Central & Eastern Europe0.09890.04060.0641
Rest of Latin America0.08510.01300.0512
Rest of Middle East0.03920.01810.0205
Rest of Western Europe0.06810.03450.0435
Other0.06950.00890.0350

 

WhatsApp Conversation Pricing in USD

Country/RegionMarketingUtilityAuthentication
Argentina0.07110.03910.0422
Brazil0.07190.00920.0362
Chile0.10220.02300.0606
Colombia0.01440.00020.0089
Egypt0.12340.00600.0711
France0.16470.03450.0795
Germany0.15700.06330.0883
India0.01140.00160.0048
Indonesia0.04730.02300.0345
Israel0.04060.00610.0194
Italy0.07950.03450.0435
Malaysia0.09890.01610.0207
Mexico0.05010.01150.0275
Netherlands0.18370.05750.0828
Nigeria0.05930.00770.0330
Pakistan0.05440.00620.0262
Peru0.08080.02300.0434
Russia0.09220.04600.0493
Saudi Arabia0.04670.01320.0260
South Africa0.04360.00870.0207
Spain0.07070.02300.0393
Turkey0.01250.00610.0095
United Arab Emirates0.03910.01810.0205
United Kingdom0.08110.02530.0412
North America0.02880.00460.0155
Rest of Africa0.02590.00700.0166
Rest of Asia Pacific0.08420.01810.0489
Rest of Central & Eastern Europe0.09890.04060.0641
Rest of Latin America0.08510.01300.0512
Rest of Middle East0.03920.01810.0205
Rest of Western Europe0.06810.03450.0435
Other0.06950.00890.0350

 

Discover MessageMind's Flexible Pricing Plans to Maximize WhatsApp Automation. Compare features, manage permissions, and access invoices with ease.

 

Choose Your Plan

MessageMind offers flexible pricing plans designed to unlock the full potential of AI Customer Support.

Starter

Perfect for small businesses or solo entrepreneurs. Includes a 30-day free trial, then $99/month.

Professional

Ideal for growing businesses seeking more advanced features and higher capacity.

Enterprise

Designed for large organizations requiring comprehensive, customizable AI solutions.

 

Your Subscription at a Glance

The "Payment" section provides details about your active subscription, including:

  • Plan name
  • Billing frequency
  • Plan start date
  • Plan end date
  • Option to change the plan and payment method

 

Additionally, you have access to your subscription invoices, providing a detailed breakdown of your billing history and payments in the "Invoice" section.

Current Plan

This section displays the name of your current subscription plan and outlines the features and services included.

Update Plan

Explore other subscription plans and switch to one that better suits your needs.

Cancel Plan

Allows you to cancel your subscription if necessary.

Add Payment Method

Provides the option to add or update your payment method.

Invoice History

Access your subscription invoices here. The invoices provide detailed information about your billing history, including:

  • Breakdown of charges
  • Payments
  • Other financial records related to your subscription.