ARTIFICIAL INTELLIGENCE
Human Takeover
The human takeover happens in these cases:
When a human agent replies to a user's message.
When the Settings > Artificial Intelligence > Human takeover option is active. It is triggered automatically when the chatbot fails to understand a user's message or it can be requested manually by the user explicitly asking to contact a human agent.
General information
When the human takeover is activated the chatbot is automatically disabled for as long as the last human agent that replied to the conversation is online. If no agents have responded to the conversation yet, the chatbot will remain active. After that, the chatbot is activated again but no default fallback messages will be sent within 10 days of human takeover if the chatbot doesn't know the answer to the user's question in the same conversation. You can force a Dialogflow message to be always sent by adding to the Intent the custom Payload value "force-message": true.
The chatbot is fully activated again when the conversation is archived or deleted.
If you're using Slack, no messages will be sent if the chatbot knows the answer. Once the human takeover is active all conversation's messages are sent to Slack.
When a human agent reply to a user the human takeover is activated automatically.
The human takeover feature is compatible with OpenAI and will continue to function even if the Dialogflow chatbot is deactivated.
To fully disable the chatbot on human takeover, check the option Human takeover > Disable chatbot.
If the human takeover is already active, it will not be activated again, and the human takeover message will not be sent. The Fallback message will be sent instead.
Human takeover option
When the option Human takeover is active the following happens:
If enabled, the request is sent only if the message sent by the user is longer than 3 chars and contains at least two words. This optimization prevents mistaken requests.
The conversations to which the chatbot was able to answer correctly, are marked as read and moved at the bottom of the Inbox list.
When the user confirms the human takeover, or if it is automatic, the following happens:
The conversation is marked as unread and moved on top of the Inbox.
Any future user messages in the same conversation sent within 10 days of the human takeover, and without an answer from the chatbot, will trigger agent notifications.
If agents email notifications are active, an email notification is sent to the agent assigned to the conversation, or, if the user's conversation is assigned to a department, to the agents assigned to that department, otherwise it is sent to all offline agents.
If Push notifications are active, a push notification is sent to the agent assigned to the conversation, or, if the user's conversation is assigned to a department, to the agents assigned to that department, otherwise it is sent to all offline agents.
If text message notifications are active, a text message is sent to the agent assigned to the conversation, or, if the user's conversation is assigned to a department, to the agents assigned to that department, otherwise it is sent to all offline agents.
No human takeover requests within 10 days of the human takeover will be sent in the same conversation.
The follow-up message, offline message, and subscribe message are activated.
If queue settings are active, the queue or routing is activated.
Open AI
The settings below are related to the Artificial Intelligence app.
Synchronization
Automatic sync mode
The automatic sync mode is ready-to-use and does not require any additional settings.
If you want to activate the chatbot, check Settings > Artificial Intelligence > OpenAI > Chatbot.
You need to purchase credits to use this option.
Manual sync mode
The OpenAI (ChatGPT) integration gives your chatbot the ability to answer general questions about almost anything you can imagine. To start using it, follow the steps below.
Register at https://beta.openai.com/signup.
Get an API key from https://beta.openai.com/account/api-keys and paste it into Settings > Artificial Intelligence > OpenAI > API key
Enable the chatbot from Settings > Artificial Intelligence > OpenAI > Chatbot.
Information
If you want to send only the latest user message and prevent all previous conversation messages from being sent to OpenAI, you can select the option Omit previous messages. If OpenAI is unable to reply after a few user messages, you can try checking this option and attempting again.
If Dialogflow is active, the OpenAI query is performed only if the chatbot does not know the answer to the user's question and if the length of the user's message is greater than 4 characters.
The following settings are compatible with OpenAI: Smart reply, Human takeover, Disable for the tickets area, Disable during office hours, Bot response delay, Reply to user emails, Reply to user text messages.
The following Google settings are compatible with OpenAI: Multilingual, Multilingual via translation, Automatic translation, Language detection
If a human takes control, the OpenAI chatbot is deactivated, and is remains deactivated also if the agent goes offline. The Dialogflow chatbot continues to function whenever necessary.
The default model is gpt-3.5-turbo.
OpenAI supports the use of voice messages through speech recognition.
Settings
See information about most OpenAI settings here.
Chatbot mode
This feature is related to the Settings > Artificial Intelligence > OpenAI > Chatbot mode option. It allows you to configure the information OpenAI will use to respond to user messages.
Only general questions OpenAI will respond only to general questions and questions related to previous user messages in the same conversation, without using any information you provide. This is the default setting.
Only questions related to your sources OpenAI will only respond to questions related to the information you provide. The user messages will be ignored. You have to first train the chatbot with your sources.
All questions OpenAI will only to questions related to the information you provide, to general questions, and to questions related to previous user messages in the same conversation. You have to first train the chatbot with your sources. This is the recommended mode.
Assistant Use this mode if you are using an OpenAI Assistant.
Assistant
This features allow you to use your own Assistants created at https://platform.openai.com/assistants.
You have to set Settings > Artificial Intelligence > OpenAI > Sync mode to Manual and use your own API key.
You can use multiple assistants by adding their IDs in Settings > Artificial Intelligence > OpenAI Assistants - Department linking and selecting Assistant in Settings > Artificial Intelligence > OpenAI > Chatbot mode. To activate an assistant, both the assistant and the conversations must be assigned to a department.
The assistant is used only for the chatbot, and smart replies, not for the message rewriting and other features.
Chatbot
The OpenAI chatbot feature functions similarly to Dialogflow, providing automated responses to user messages. Select the Chatbot mode setting to specify the questions that the chatbot is capable of responding to. Utilize the human takeover feature to enable the chatbot to redirect the chat to a human agent as necessary.
Fallback message
The fallback message is sent when OpenAI is unable to understand the user question. If the Dialogflow chatbot is enabled, the fallback message will be turned off and the Dialogflow chatbot's fallback message will be utilized instead.
Prompt
The prompt instructs OpenAI on how to respond by providing relevant information that can be utilized to answer user inquiries. To comprehend the process, refer to the example prompts listed below.
If you choose to activate the human takeover feature, you need to tell OpenAI to respond with I don't know if it is unable to provide an answer to the user's question. You should always include the following text in the prompt: Respond "I don't know", if not sure about the answer.
Prompt - Message rewriting
This prompt instructs OpenAI on how to rewrite a message when the Message rewrite button is active. This prompt should be in English. Dialog Fusion automatically add the following text when required: and use the user langauge, add greetings.
Replies from the training sources can be utilized with the prompt feature as they are compatible.
Spelling correction
This feature automatically fix any spelling mistakes in the agent's message.
Smart reply
This feature allow to enable the Smart Reply feature also if the chatbot is not active. If the chatbot is active the Smart Reply feature will use OpenAI automatically.
Dialogflow spelling correction
In the case where Dialogflow is unable to find the appropriate response to the user's message, this function verifies if there are any spelling errors. If any such errors exist, Dialogflow is prompted again with the correctly spelled version of the message for an accurate response. Although it has a higher priority, this feature can still work together with the Google Search spelling correction feature.
Message rewrite button
This feature adds a button to the text field of the conversation area, click on it to rewrite your message and make it more friendly and professional. Greetings will be added automatically if there is no previous agent messages. If your language is not English, you have to edit your agent/admin profile and set the correct language.
Speech recognition
When this option is active, audio messages will be converted to written text.
You do not need to activate this feature for the chatbot to understand audio messages. The speech recognition feature of the chatbot is always enabled.
For this feature to work better, the user language should be know. To automatically detect the user's language, you can enable the language detection feature.
The text will be displayed alongside the audio player.
The generated text is compatible with the translation features.
Source links
When this option is active, the response will automatically include the links to the sources and training data used for generating the answer. To include articles as sources you have first to set the articles page in Settings > Articles > Articles page URL.
Note data scraping
When this option is active, you will see a menu in the notes panel. The menu enables the automatic extraction of specific information from the user's messages.
OpenAI parameters
Dialog Fusion allows you to adjust various OpenAI parameters such as temperature and logit_bias, for more details visit https://platform.openai.com/docs/api-reference/completions/create. Don't set any values if you don't know what these parameters do or OpenAI may stop working.
Logit bias
The Logit bias parameter must be JSON string and the keys must be strings, for example: {"2435":-100, "640":-100}.
Generate user expressions - Option
When this option is active, OpenAI will generate new user expressions in real time when you open the chatbot training window.
Generate user expressions - Button
When you click the button Generate user expressions, openAI will update your Dialogflow agent and generate new user expressions for each Intent.
Make a backup of your Dialogflow agent first.
This task can take several minutes or even hours if your chatbot has a lot of Intents. Since the operation takes a long time, your server may interrupt the operation (operation timeout) before it finishes, in which case you need to click the button again. You can verify if the operation is interrupted by checking the browser console for errors.
This task is performed only once per Intent. Previously processed Intents will be ignored.
This task checks existing user expressions and does not create duplicates.
The first 5 user expressions will be used to generate new user expressions.
Since this is an automated process, we strongly recommend reviewing your Intents after the task has been completed.
Training
With this feature, your chatbot can undergo training using your website, texts, PDF documents and more. Once the training is successfully completed, the chatbot will be able to answer questions related to your contents. To access this feature, navigate to Chatbot > Training.
To initiate the chatbot training, enter the chatbot area. It is possible to enter URLs for websites, text or PDF files, or XML sitemaps.
Once the sources are set, click the Train chatbot button and await completion of the training process.
Information
You can add and manage personalized question and answers from Chatbot > Training > Q&A and from the chatbot training window.
It is only possible to upload files in PDF and TXT formats.
If you retrain the same website, you must first delete the previous website's training data; otherwise, only new URLs will be trained.
You can provide the website URL and all child URLs will be included and crawled, but with large websites, it is more efficient and less prone to errors and infinite link loops to utilize an XML sitemap instead of relying on the website URL. You can create it with a service like https://www.xml-sitemaps.com.
If you want to train your chatbot using specific pages from your website instead of all of them, you can make use of an XML sitemap. Create one using a tool like https://www.xml-sitemaps.com, and then remove the pages you do not wish to include by editing the file in a text editor. To use the XML sitemap, you need to upload it either onto your server or an external online location. Afterward, add the URL of the sitemap in Chatbot > Training > Website. If your sitemap contains more than 1000 URLs, it's advisable to split it into multiple files and train the chatbot with one file at a time to prevent server crashes.
You can upload large files and your XML sitemap with a service like https://tmpfiles.org.
As soon as the training is completed, the uploaded files are removed.
To add new training sources, simply train the chatbot again. The previous training sources will not be lost, and only the new sources will be added.
The Dialog Fusion articles are used as training sources automatically.
The Dialog Fusion conversations are used as training sources automatically. The training is done via cron job every 24 hours. Only user and agent messages are used, chatbot messages are ignored.
The embedding model is essential for training your chatbot and handling all user messages. We currently use the text-embedding-3-small model. It is necessary for these scenarios and cannot be disabled or changed. You can find pricing information at https://openai.com/pricing. Check out the pricing for the text-embedding-3-small model in the Embedding models section.
The responses generated by OpenAI have the feature to include in the reply a link to the corresponding website page where the answer was sourced.
Go to Chatbot > Training > Information, and click the Delete all training data button to remove all previous training data for the chatbot.
The embeddings are stored as JSON files in the Dialog Fusion uploads folder and are secured using the password-by-filename approach.
Multilingual training
If your user base is multilingual, you can train the chatbot with content in multiple languages and limit the chatbot to retrieve answers only from the sources in the user's language. To activate this feature, check the Settings > Artificial Intelligence > OpenAI > Multilingual Training Sources option.
Files Files currently support only one language.
Websites The language of the website is detected automatically. For Dialog Fusion to comprehend the language of your web pages, the <html> must contain the attribute lang.
Q&A Q&A currently support only one language.
Articles All article languages are used automatically.
Conversations If automatic translation is active, only messages in the agent's language will be used.
Q&A
The information below is related to the Question and Answers section of the chatbot training area. Add questions and answers to the chatbot to improve its performance. The chatbot will use this information to respond to user inquiries.
Function calling
Function calling allows you to connect the chatbot to external tools and systems. The chatbot will query your server and return the information from your server to the user. Our support doesn't include assistance with this feature, as it is for advanced users and requires custom code on your server.
Parameters
URL: Enter the URL of the API endpoint that will supply the necessary values for the function.
Headers: Enter key-value header parameters, separated by commas. E.g. apikey:123345, json:true.
Properties: Enter values that the user must provide to the chatbot. For example a city, a tracking number, etc. The chatbot will ask the user for these values. If you already know all the possible values, you can enter them in the Allowed values field.
Response from your server
Your server must returns a JSON array with the values required by the chatbot. E.g. ["order_status" => "Delivered 2 hours and 25 minutes ago"].
Set data
Set the specified user values when the question is asked. You will see such values in the user details panel. You can also use this feature to assign a department, an agent, and tags to the conversation.
Flows
The information below is related to the chatbot flows area. Flows allows you to esely create conversation flows powered by the chatbot. Use them to guide the user toward a specific goal with a series of pre-defined messages.
Start: Use the start block to set when the flows should start. It can be everytime the user start a new conversation or when it sends a specific message. If you set conditions, the flow will only start when all conditions are met.
Send message: Send a message to the user.
Send button list: Send a list of buttons to the user.
Send video: Send a video to the user.
Get user details: Get the user details and store them in Dialog Fusion. You will see such values in the user details panel. You can leave the description field empty for default details, but it's required if using custom user fields.
Set data: Set the specified user values when the block is executed. You will see such values in the user details panel.
Actions: Execute the specified actions when the block is executed.
Conditions: Use it to create different branches in the flow. If the conditions are met, the flow will follow the branch set as true, otherwise the one set as false.
The settings below are related to the Artificial Intelligence app.
Synchronization
To start using the Google AI services and Dialogflow follow the steps below.
Automatic sync mode
Click Synchronize now and complete the procedure.
If you want to activate the Dialogflow chatbot, check Settings > Artificial Intelligence > Google > Dialogflow chatbot. Also, you have to enter your chatbot Project ID or Agent Name.
You need to purchase credits to use this option.
Manual sync mode
Enable the setting Dialog Fusion > Settings > Artificial Intelligence > Google > Dialogflow Chatbot and save the changes.
Go to console.cloud.google.com and sign in.
Select or create a project by clicking the Select a project button on top-left. Name the project as you want.
Activate the Dialogflow API by entering Dialogflow API on the top search bar. Click Dialogflow API and then click Enable.
Select the project and the go to Left menu > APIs and services > OAuth consent screen. Select External and click Create. In App name enter what you want, in User support email and Developer contact information enter your email. Click Save and continue.
In the scopes area, click Add or remove scopes, scroll bottom and into the Manually add scopes area enter https://www.googleapis.com/auth/dialogflow,https://www.googleapis.com/auth/cloud-language,https://www.googleapis.com/auth/cloud-translation. Click Add to table and then Update and Save and continue.
In the test users area, click Add users and add your Google email, use the same email as the currently logged in account. Click Save and continue.
Go to Left menu > APIs and services > Credentials and click Create credentials, select OAuth client ID. As Application type select Web application. Enter any name you want. In Authorised redirect URI enter the redirect URL, get it from Dialog Fusion > Settings > Artificial Intelligence > Google > Authorised redirect URI. Click Create.
Copy Client ID and Client Secret and paste them into Dialog Fusion > Settings > Artificial Intelligence > Dialogflow. Save the settings.
In Settings > APIs & Services > OAuth Consent Screen click PUBLISH APP. There is no need to complete the review process, leave it in the pending review state.
Click Dialog Fusion > Settings > Artificial Intelligence > Google > Synchronize. Login with the same Google account you have used till now. On the next screen click Continue. On the next screen select all scopes and click Continue.
Copy the Refresh token and paste it into Dialog Fusion > Settings > Artificial Intelligence > Google > Refresh token.
You are done! If you want to activate the Dialogflow chatbot, check Settings > Artificial Intelligence > Google > Dialogflow chatbot. Also, you have to enter your chatbot Project ID or Agent Name, to get it follow the steps below. Note that the app does not need to be approved by Google.
If you are a Google Workspace user, go to https://admin.google.com/ and click Google Cloud Session control. Set Re-authentication policy to Never require re-authentication.
Dialogflow
The information provided below is relevant to Dialogflow. Warning! We will stop supporting Dialogflow by the end of 2025. All its features will be available in Dialog Fusion through OpenAI.
Get Project ID
Log in to the Dialogflow ES console by going to dialogflow.cloud.google.com. You must sign in with the same Google account used during the synchronization.
Click the gear icon at the top left, near the chatbot name, and open the settings area. . If you haven't created a chatbot yet, follow the instructions below to create your first bot.
Copy the Project ID .
Make sure to choose US / GLOBAL on the top left of the Dialogflow dashboard. Please note that our system does not support mega agents. .
Get Dialogflow CX Agent Name
Log in to the Dialogflow CX console by going to https://dialogflow.cloud.google.com/cx/.
Select the project of the desidered agent and go to the agents page. You can enter the agents page by selecting the agent and by clicking the top button Agents > View all agents .
Click the options menu for the desiderate agent in click Copy name .
More details at https://cloud.google.com/dialogflow/cx/docs/quick/api#detect-intent-drest.
Location
Set the location or region of your Dialogflow agent. This setting is optional if your agent location is set to global.
Welcome Intent
Trigger the Dialogflow Welcome Intent for new visitors. The option Settings > Messages > Welcome message must be active.
Send the user details
Send the user details of the registration form and email rich messages to Dialogflow.
Add Intents to saved replies
Include the Dialogflow Intents into the saved replies. To access the saved replies option, go to Settings > Admin > Saved replies.
Create a basic chatbot
If you haven't created a chatbot yet, follow the instructions below to create your first one. The creation and management of your Dialogflow chatbot is handled entirely by Dialogflow. There are a lot of tutorials online that can help you create and configure your Dialogflow bot.
To create your first chatbot enter the Dialogflow console and create an agent. As Google project select the same project used during the synchronization.
Add a new Intent from the left menu and open it.
In the Training phrases area adds the user's question you want the chatbot to reply to, add as many variants are you can. For example, if you want to the chatbot to reply to users asking for your business address, add variants like "what is your address", "address", "where are you".
In the Responses area adds the chatbot answer as a text response. If you want to add buttons, cards, etc., you can use the rich messages.
You have created your first question and answer! Test if from the right area or from the Dialog Fusion chat. Add new Intents to populate your chatbot with the questions and answers you want. You can include basic pre-built questions and answers by enabling the Small Talk feature from the left menu.
Here are some great resources to help you build a more complex chatbot:
Dialogflow Information
OpenAI
If OpenAI is enabled, Dialogflow takes priority over it. The OpenAI API will only be used if Dialogflow cannot answer the user's question.
Chatbot training and optimization
It will require some time for your chatbot to consistently provide correct answers to all questions. To improve its performance, you and your human agents should continuously train the chatbot by incorporating new question variations and Intents. This approach will effectively enhance the capabilities of your chatbot.
Agents can add new Intents and chatbot responses, and add new training phrases to existing intents on the fly from the admin area by moving the mouse cursor over a message and clicking the Dialogflow Intent icon. Enable Settings > Artificial Intelligence > OpenAI > Generate user expressions to automatically add variations of the question and to rewrite the answer. New Intents will contain also the responses, while the update of existing intents will add new training phrases only, but not new chatbot responses. If you're using Dialogflow CX, the chatbot responses will be added to the latest flow used in the conversation if any, otherwise to the start flow.
If the chatbot is replying with the wrong intents, go to Dialogflow Console > chatbot Settings > ML Settings, and set the ML CLASSIFICATION THRESHOLD to a larger number, such as 0.6. Also check the Intent detection confidence.
Dialogflow Intent detection confidence
When searching for a matching intent, Dialogflow scores potential matches with an intent detection confidence, also known as the confidence score. These values range from 0.0 (completely uncertain) to 1.0 (completely certain). Specify a value ranging from 0.1 to 1.0. Any answer provided by Dialogflow that is less than this value will not be considered. If you are utilizing Dialogflow alongside your OpenAI chatbot that is trained using your resources, it is recommended to configure the value as 0.81.
Knowledge Base
Knowledge Base are automatically enabled. Knowledge Base is a feature that gives your chatbot the ability to search within documents (such as a PDF) or web pages to find an answer. To create your first Knowledge Base, go to cloud.google.com/dialogflow/docs/knowledge-connectors
Dialogflow response
The full Dialogflow JSON response is automatically saved in the database, sb_messages, column payload.
Ignore an Intent if it doesn't fit the provided keywords
Sometimes Dialogflow gives incorrect answers due to similar questions with different subjects. To solve this, you can instruct Dialog Fusion to ignore an Intent if specific keywords are not present in the user's message. Here's how you can do it:
Enter Dialogflow and edit the Intent.
For each training phrase, select the keywords you want to be required and link them to a new Entity, or an existing one.
Under Actions and parameters check Required and add a new Prompt with value skip-intent
Multilingual Chatbot
The feature Artificial Intelligence > Google > Multilingual checks if there is a Dialogflow agent in the user's language and activate it.
For this feature to work the user language must be know. The user language is based on the language user detail of the user if set, otherwise on the user browser language. The language can also be detected with the language detection feature.
Make sure to activate this setting even if your OpenAI sources consist of multiple languages.
Automatic Translation
The automatic translation feature automatically translates user messages into agent language and agent messages into user language. To enable it check the option Settings > Artificial Intelligence > Automatic translation. Artificial Intelligence > Google > Sync mode is set to Automatic, the multilingual features will work automatically. Otherwise you have to complete the synchronization and the setup below. The multilingual via translation and language detection features also require these steps.
Setup
Log in to https://console.cloud.google.com with your Google account and select the project of your Dialogflow Agent.
On the top search bar type cloud translation, select the Cloud Translation API service and enable it. Please note that this is a paid service with a free tier, additional charges may occur.
Enable the billing by clicking Left menu > Billing and by enabling a billing account with a valid payment method.
Information
The user messages in the admin area are translated automatically in real-time to match the agent language.
The agent messages are translated automatically in real-time to match the user language.
Agents can view the original message by opening the message menu and by clicking View original message.
The agent language is based on the language user detail of the agent if set, otherwise on the browser language, or admin area language.
The user language is based on the language user detail, if set, otherwise on chat language, if set, otherwise on the browser language. The language can also be detected with the language detection feature.
The notifications are also translated.
To avoid translating a string, enclose it with the characters ` or ```.
Multilingual via translation
The feature at Settings > Artificial Intelligence > Multilingual via translation automatically translates user messages into the default language of Dialogflow or OpenAI, and translates Dialogflow or OpenAI messages into the language spoken by the user. Additionally, this feature translates all text displayed within the chat, such as the chatbot's rich messages, articles, registration forms, and pop-up notifications. To enhance performance and minimize translation costs, the translations are automatically integrated into the translation files. Combine this feature with the language detection feature for optimal results.
The original texts must be in English.
Language detection
Detect the language of the user' messages and change the user language and Dialogflow agent language accordingly, if available, otherwise, show a fallback message. You can use the following merge fields in the message: {language_name}.
The user message must be at least 2 words long.
Language detection is executed only for the first 2 user messages of a conversation.
As long as the OpenAI chatbot is operational and programmed to respond to generic inquiries, the fallback message will never be dispatched, since OpenAI will consistently provide answers to any use message.
Google search
The Google search features give your chatbot the ability to search for answers on Google and your website and automatically correct misspelled user questions. To start using it, follow the steps below.
Register at https://programmablesearchengine.google.com/.
Create a search and setup it is as you want. We recommend to add only your website and Wikipedia if you want your chatbot to reply to general questions, leave disabled the option Search the entire web. Use the setting Entities to exclude invalid results.
Go to Edit search engine > Setup > Basic and copy the Search engine ID value, paste it in Dialog Fusion.
To get the API key visit https://developers.google.com/custom-search/v1/overview and click Get a key.
Spelling correction
In the case where Dialogflow is unable to find the appropriate response to the user's message, this function verifies if there are any spelling errors. If any such errors exist, Dialogflow is prompted again with the correctly spelled version of the message for an accurate response. Although it has a lower priority, this feature can still work together with the OpenAI Dialogflow spelling correction feature.
Entities
The Entities setting analyze the user's message and recognize and extract entities like cities, events, dates, and more. Use it to exclude invalid results returned by Google search. To enable this setting follow the steps below.
Log in to https://console.cloud.google.com with your Google account and select the project of your Dialogflow Agent.
Enter Cloud Natural Language API in the search bar at the top, select Cloud Natural Language API and enable the API .
Enable the billing by clicking Left menu > Billing and by enabling a billing account with a valid payment method. Enable billing for the project of your Dialogflow agent.
Information
The Google search is performed only if the chatbot does not know the answer to the user's question and if the length of the user's message is greater than 4 characters.
If the Google search returns a result, the Dialogflow context google-search is automatically activated. The context contains the attribute link which is the website's link of the Google search result. Use the context to create a new intent that provides the link, if the user sends a message like tell me more or I want to know more.
Google Search is not required to activate the spelling correction. You can disable Google Search and activate only spelling correction.
If Google Search is active, it will have priority over OpenAI.
The settings below are related to the WhatsApp app.
To install the app see the apps installation section.
WhatsApp Cloud API Setup - Automatic sync mode
Click Synchronize now and complete the procedure.
To add new numbers, visit https://business.facebook.com/wa/manage/phone-numbers/. If you add new numbers after the sync process, you will need to sync them again. All numbers will be automatically synchronized. If you wish to disable specific numbers, you can delete them from Settings > WhatsApp > Cloud API numbers.
If you sync again with the same phone number and do not receive the verification SMS or call, you can enter the latest PIN you received and it will work.
If you do not receive the messages sent to your WhatsApp number in Dialog Fusion, please check the following:
Click Reconnect and complete the procedure.
Go to the Meta Business Suite and add a payment method.
WhatsApp Cloud API Setup - Manual sync mode
Create a new account at https://developers.facebook.com or login with your existing account.
Create a new app and choose Other as the app type. Then select Business. Enter a name for the app and select the Business Account used for WhatsApp.
In Dialog Fusion > Settings > WhatsApp > Cloud API settings > Secret key enter a random string then go to https://developers.facebook.com/apps and select your app. Click Add product and add WhatsApp, then go to WhatsApp > Configuration and in Webhook URL enter the URL you get from Dialog Fusion > Settings > WhatsApp > Cloud API > Configuration URL. In Verify token enter the secret key you previously entered in Dialog Fusion. Click Verify and save, click Webhook fields > Manage, enable the following Webhook fields: messages.
To verify the integration, simply go to https://developers.facebook.com and select your app. From there, click on "WhatsApp" in the left menu and then select "API Setup". Copy the Phone number ID and paste it into Dialog Fusion > Settings > WhatsApp > Cloud API numbers > Phone number ID. Enter the desired phone number in the "To" field, such as your personal WhatsApp number, and send a test message. Check your WhatsApp account and send a reply, which should then appear in Dialog Fusion. To reply to the test number from Dialog Fusion, copy the "Temporary access token" and paste it in Dialog Fusion > Settings > WhatsApp > Cloud API numbers > Token.
To activate the WhatsApp integration for all phone numbers and add a live phone number, refer to the following guidelines.
In Dialog Fusion > Settings > WhatsApp > Cloud API numbers > Token enter the permanent access token, follow the instructions below for getting it.Visit https://business.facebook.com and go to Left menu > Settings > Business settings, then go to Users > System Users to view your admin system user, or create a new one. Open the user and click Add Assets, then select the app used for the WhatsApp API integration and check Develop App, or Full control. The system user needs to be an admin. If you do not see the option, click Business settings.
Click Left menu > Account > Apps. Select your app or add it. Make sure the system user is there and has full control. If not, click Add user, select the system user, click Full control, and click Assign.
Click Left menu > Apps and under Select Assets and choose your app, enable Develop App, or Full control and save.
From Users > System Users select the user you just creted and click Generate New Token, click Apps and select the app used for the WhatsApp API integration, set the Token expiration to Never, enable the following permissions: whatsapp_business_management, whatsapp_business_messaging, business_management. Click Generate Token and save. Paste the token in Dialog Fusion > Settings > WhatsApp > Cloud API numbers > Token.
To add additional phone numbers, you can do so by visiting https://developers.facebook.com, selecting your app, and navigating to Left menu > WhatsApp > API Setup. To get started, click on Add phone number at the bottom and follow the instructions provided. Please keep in mind that if you use your current WhatsApp business number in Dialog Fusion, it will no longer be usable with your WhatsApp Business app, and you will need to migrate it following these instructions. After activating the number, copy the Phone number ID and paste it into Dialog Fusion > Settings > WhatsApp > Cloud API numbers > Phone number ID.
360dialog Account Setup
Go to https://www.360dialog.com/ and create a new account.
Enter your dashboard and from Left menu > WhatsApp Accounts generate the API key and copy and paste it in Dialog Fusion > Settings > WhatsApp > 360dialog settings.
Click Dialog Fusion > Settings > WhatsApp > 360dialog settings > Synchronize now.
Done! Dialog Fusion should start receiving the WhatsApp messages sent to your number, and you can reply to those messages from Dialog Fusion.
Note that you can also use the free sandbox account for testing, more details at https://docs.360dialog.com/whatsapp-api/whatsapp-api/sandbox. The sandbox account has limitations and some features, such as media attachments, will not work.
Twilio Account Setup
Go to https://www.twilio.com and create a new account.
Verify your phone number.
Complete the form and choose WhatsApp, Alerts & Notifications, With no code at all, 3rd party integrations.
From the Twilio console copy ACCOUNT SID and AUTH TOKEN and paste them into Dialog Fusion > Settings > WhatsApp > Twilio settings, save the changes.
You will now set up a free test account to run some tests and make sure the integration works with Dialog Fusion. From the left menu click Messaging > Settings > WhatsApp sandbox settings and enter into WHEN A MESSAGE COMES IN and STATUS CALLBACK URL the URL of Dialog Fusion , get it from Dialog Fusion > Settings > WhatsApp > Twilio settings > Get configuration URL. Mind that localhost will not work, you need a public URL and a live server.
From the left menu click Messaging > Try it out > Send a WhatsApp message. Follow the instructions and send the message with the code to the WhatApp number provided. Click the next buttons until the configuration is complete.
Done! Dialog Fusion should start receiving the WhatsApp messages sent to the sandbox account, and you can reply to those messages from the Dialog Fusion.
To publicly use the WhatsApp integration with your customers you need also to complete the steps below:
Update your account and enable billing, you can do that here.
Purchase a Twilio number, which will be the phone number of your official WhatsApp Business account. More details here. You cannot use the phone number of your existing WhatsApp Business account, you must use a Twilio number. More details here.
From the Twilio console go to Messaging > Services and create a new Messaging Service. Click Add Senders, select WhatsApp Number as the sender type, and add the Twilio number you purchased. Copy the Service SID and paste it into Dialog Fusion > Settings > WhatsApp > Twilio settings > Sender.
Templates
As for WhatsApp Business Policy, you cannot send outbound marketing and solicitation messages to end users. End user users must reach out to you first. You have 24 hours from when the end user's message was sent from WhatsApp to reply to the message. To communicate with a user who has not contacted you before or has not been in touch for more than 24 hours, you must opt for the text message fallback or the WhatsApp message template.
To send message templates you have to add a payment method to your WhatsApp Business Account. You can do it from https://business.facebook.com/billing_hub/.
To send a specific message template to a group of users, use the direct messages feature.
Text message fallback
To enable the text message fallback you must set up the SMS in Settings > Notifications > Text message notifications.
WhatsApp message templates
A WhatsApp message template is a message format that you can use over and over again to message users once they have opted-in and given your app permission to send them messages. You can not Enter the original message into the template, you must use it to notify the user of a new message and instruct him on how to view it, for example by providing a link to your website where the chat is shown.
WhatsApp Cloud API
To get the Template name and manage the templates visit https://business.facebook.com and go to Left menu > Settings > More system settings, then go to Accounts > WhatsApp accounts > Settings and click WhatsApp Manager.
In Template languages enter all the language codes supported by your template, separated by commas. (copy only the language code, e.g. it, es, en_US). If you use a template that supports multiple languages, the matching language for the user will be automatically selected. Otherwise, the default template language will be used.
In Header variables and Body variables enter the supported merge fields separated by commas, e.g. {recipient_name}, {conversation_url_parameter}. The number of parameters entered here must match the number of parameters of the template. Use this feature if your template uses dynamic values. Order is important, the first merge field will be used as the first template parameter.
In Button variables enter the link of your custom buttons, or the text of the quick replies with prefix quick_reply_, e.g. quick_reply_abcde. Each value must be separated by a comma.
Template fallback
Set the WhatsApp template sent as fallback from Settings > WhatsApp > Cloud API template fallback.
Send template messages to a user who has not contacted you before
In Settings > WhatsApp > Cloud API settings > Business Account ID enter you Business Account ID. Provide your Business Account ID, which can be obtained from https://developers.facebook.com. Choose your app and go to Left menu > WhatsApp > API Setup.
To send the template to specific users, go to the Dialog Fusion Users section and choose the intended recipients. Then, click on the WhatsApp icon located at the top right corner.
If you are using the WhatsApp Cloud API with a template that supports multiple languages, the matching language for the user will be automatically selected. Otherwise, the default template language will be used.
If you are using Twilio and have parameters in your template, input the parameter values separated by commas in the Body section.
Twilio
Enter the Template SID and the template attributes separated by commas into Dialog Fusion > Settings > Twilio template.
360dialog
Get the Namespace value from Left menu > WhatsApp accounts > Details.
Get Template name and Template default language from your 360dialog templates area.
In Custom parameters Enter the supported merge fields separated by commas, example: {recipient_name}, {conversation_url_parameter}. Use this feature if your template uses dynamic values. Order is important, the first merge field will be used as the first template dynamic value.
Dialog Fusion will try to use the template with the same language as the user, if it is not available, it will use the template with the default language. The following template languages are not compatible: en_GB(use en_US), pt_PT(use pt_BR), zh_HK and zh_TW(use zh_CN), es_AR and es_MX(use es_ES).
WhatsApp Flows
For more details about the WhatsApp Flows click here.
Built-in flows
The Support Board automatically generates and sends the following flow. To regenerate a flow, click the Settings > WhatsApp > Clear flows button.
Registraton - This flow is sent when a new user sends their first message to the WhatsApp number, and the Settings > Users > Require registration option is enabled.
Follow-up - This flow is sent if the Settings > Messages > Follow-up message option is active and the user does not have an email address.
Subscribe - This flow is sent if the Settings > Messages > Subscribe message option is active and the user does not have an email address.
More information
You cannot send a WhatsApp message to a user who has sent you a message more than 24 hours ago or has never messaged you before. WhatsApp prohibits this action. Instead, you must use a WhatsApp template or send an text message. If you encounter an "Error message: Re-engagement," it indicates this situation.
If you does not receive WhatsApp messages make sure you are not assigning the WhatsApp conversations to a department and that the WhatsApp number used for testing is not a phone number of a Dialog Fusion admin or agent. Also, make sure you setup correctly the WhatsApp webhook URL.
If you can not send messages, an error should appear in the admin area when you try to send a message to the user.
We cannot provide support for Twilio or 360dialog configuration, including all related issues.
We cannot provide support in getting your WhatsApp account or WhatsApp message template approved.
WhatsApp conversations and messages are compatible with queue and routing.
If you are testing with the sandbox and after 72 hours you can no longer send messages to your phone number you must link again your phone number to your sandbox.
You can send rich messages to WhatsApp. If you send chips, buttons or select rich messages, with more than 3 options, you can use the whatsapp="Your menu text" shortcode attribute to set the text of the WhatsApp message menu.
The follow-up message is supported, but the message is always sent, also if an agent replies.
The offline message is supported, but the timetable is not sent.
The chatbot is supported. The human takeover feature is also supported. To enable the Dialogflow chatbot support for audio messages, activate Settings > Artificial Intelligence > OpenAI > Speech recognition
The supported AI features include language detetction, spelling correction, multilingual via translation, Google search.
Twilio and 360dialog has many limitations. For example, Twilio does not support messages longer than 1600 characters. We strongly recommend to use the Official WhatsApp API.
Facebook & Instagram
The settings below are related to the Facebook & Instagram Messenger app.
Installation
Automatic sync mode
Complete the synchronization by choosing at least 1 Facebook page and enter the returned information in Settings > Messenger > Facebook pages.
You're done. All messages sent to the Facebook pages and Instagram accounts you selected will appear in the conversation admin area of Dialog Fusion. Mind that only new messages will be synchronized, the old ones will not be imported.
Manual sync mode
Create a new account at https://developers.facebook.com/ or login with your existing account.
Create a new app and choose Other as the app type. Then select Business. Enter a name for the app and skip selecting any Business portfolios.
From the menu on the left side, click on Add product. Choose Messenger.
Under the Configure webhooks section, click on Configure.
Retrieve the Callback URL from Settings > Messenger > Messenger and Instagram settings > Get configuration URL.
Set the Verification Token in Settings > Messenger > Messenger and Instagram settings > Secret key and save the changes, then use it to verify the webhook.
In Webhook Fields select the following: inbox_labels, message_deliveries, message_echoes, message_reactions, message_reads, messages, messaging_account_linking, messaging_handovers, messaging_optins, messaging_policy_enforcement, messaging_postbacks, messaging_referrals.
In the Generate access tokens section, click on Connect. Select the pages you want to sync and complete the process.
Under the Webhook Subscription column, click on Add Subscriptions. Choose the scopes you want: messages, messaging_postbacks, messaging_optins, message_reads, and message_echoes.
In the Tokens column, click on Generate. Copy the access token provided and paste it into Settings > Messenger > Facebook pages.
Copy the Page ID and Page Name and paste them into Settings > Messenger > Facebook pages.
Repeat these steps for all pages.
Save the changes and you're done. The final step is to put the app in Live mode.
If you want to sync Instagram as well, follow these steps:
From the menu on the left side, click Messenger > Instagram settings.
In the Configure webhooks area, click on Configure. Repeat the same step you previously took for Messenger.
Under the Webhook Subscription area, click on Add Subscriptions. Select the following scopes: messages, messaging_postbacks, messaging_optins, messaging_seen.
Enter your Instagram ID in Settings > Messenger > Facebook pages > Instagram ID. To get it, open your web browser and enter the following URL: https://graph.facebook.com/FACEBOOK-PAGE-ID/?access_token=ACCESS-TOKEN&fields=instagram_business_account. Replace FACEBOOK-PAGE-ID and ACCESS-TOKEN with the corresponding Page ID and access token from the Facebook page linked to Instagram.
Save the changes and you're done. The final step is to put the app in Live mode.
Your app must be in Live mode. To do that, your app must be submitted for review and approved by Meta. You can use the text at this for the review process. Please note this process is not covered by our support. If you require assistance, you can hire us.
To link Instagram to your Facebook page and Dialog Fusion follow the steps below.
Enter the Settings area of your Facebook Page and click Left Menu > Instagram (https://www.facebook.com/YOUR-PAGE-SLUG/settings/).
Click Connect account and complete the setup.
Sync Messenger with Dialog Fusion again and you're done. Mind that only new messages will be synchronized, the old ones will not be imported.
More information
If you don't receive Instagram messages:
Make sure to enable Settings > Privacy > Messages > Connected tools - Allow access from your Instagram mobile app.
Make sure your Instagram account is not setup as a professional account, it must be a business account.
Go to Meta Business Suite, select your account, and go to Users > People. Under Instagram account click Manage and make sure to enable all the permissions.
If you don't receive Facebook Messenger messages, make sure that the Facebook page does not send automated replies, such as the welcome message.
In case you encounter duplicated messages or an ongoing chat cycle between the chatbot and Instagram messages, you are facing a problem due to the presence of two Dialog Fusion installations or Dialog Fusion Cloud accounts that are both synchronized with the same Instagram account. To resolve this, access the second Dialog Fusion admin area, navigate to Settings > Messenger > Facebook pages, remove the Instagram ID value and save the changes. Try also to click the Unsubscribe button.
The Unsubscribe button remove the webhook subscription from all of your Facebook pages, it is useful if you want to stop receiving messages from a Facebook page.
Every Dialog Fusion user has only 1 Facebook conversation and 1 Instagram conversation.
Dialog Fusion rich messages are automatically converted to Facebook rich messages when possible, some part of the rich message could be removed or changed.
Only private Facebook messages will get sent to your team inbox. If someone posts a Facebook message on your wall it won't appear in your team inbox.
When someone sends a message to your company Facebook page or Instagram account they will get designated as a lead in Dialog Fusion. You'll only be able to see the user's Facebook or Instagram name and profile picture.
Messenger conversations and messages are compatible with queue and routing.
The chatbot is supported. The human takeover feature is supported.
The supported AI features include language detetction, spelling correction, multilingual via translation, Google search.
If the chatbot is enabled, it is necessary to deactivate any automatic replies on Facebook Messenger, such as the welcome message.
The follow-up message is supported, but the message is always sent, also if an agent replies.
The offline message is supported, but the timetable is not sent.
Only 1 Facebook account can be synchronized, to link pages from multiple Facebook accounts, the account synchronized in Dialog Fusion must be an admin of all Facebook pages of the other Facebook accounts.
Using this integration of Instagram and Facebook Messenger comes at no additional cost.
If the message exceeds 1000 characters, only the initial 1000 characters will be transmitted due to the character limit.
Only new messages, sent after the synchronization, will be synchronized, the old ones will not be imported.
Credits
Credits are used by the following functions, only in Automatic sync mode. The Manual sync mode doesn't use credits. If you do not want to use credits, you can use the Manual sync mode and your API keys.
Artificial Intelligence > Google > Dialogflow chatbot and Automatic Translations, Language detection, Multilingual via translation.
Artificial Intelligence > OpenAI > Chatbot and Spelling correction, Message rewrite button, Speech recognition.
Pricing
Credits must be purchased from https://app.dialogfusion.com/account?tab=membership. Here are the costs of functions that use credits.
Dialogflow ES $0.004 per request.
Dialogflow CX $0.014 per request.
Dialogflow ES Audio Message $0.000866 per second of audio.
Dialogflow CX Audio Message $0.002 per second of audio.
Google Translations $0.00004 per char.
OpenAI gpt-3.5-turbo-instruct $0.000004 per token.
OpenAI gpt-3.5-turbo $0.000004 per token.
OpenAI gpt-4 $0.00012 per token.
OpenAI gpt-4-32k $0.00024 per token.
OpenAI text-embedding-3-small $0.00000004 per token.
OpenAI audio-to-text whisper $0.0002 per second of audio.
Information
When your credits run out, if the automatic recharge is not enabled, you will be notified via email. You will receive a maximum of two email notifications. Activate the automatic recharge to prevent running out of credits.
When automatic recharge is enabled, the credit will be recharged once it falls below 1.