Sinch Community

Ever looked back at your chats with customers and noticed your bot didn't act the way you thought it would? No stress! We're going to explore together how you can figure out why your bot isn't acting as it should.   Let’s start with NLP   Imagine you're talking to a robot that can understand and respond to you just like a human friend. That's what happens when we use NLP, or Natural Language Processing, in chatbot development. 🤖   When you ask your chatbot something, like "What's the weather today?" you're using what we call an "intent" - basically, you're showing your chatbot what you want to know. Behind the scenes, NLP is the magic that helps the chatbot understand your question as if it were a person, even though you're just typing words on a screen. It's like teaching the bot to speak and understand our language!   So, every time your bot seems to "get" what you're saying, remember, it's all thanks to NLP working in the background. Pretty cool, right?   Bot understand vs not understand    For this tutorial, we're going to have some fun with our star of the show, the famous pizza bot!🤖🍕       Now, let's dive into a bit of bot-building basics. We've got one main task for our bot right now, called an "intent." This particular intent is all about ordering pizza. 📝🍕 We teach our bot this intent by showing it different ways customers might say they want to order pizza, like:   "I'd love a large pepperoni, please!" "Can I get a pizza delivered?” “I want to order pizza.”   When your customers first message the bot ✅If the bot gets what your customers saying Imagine you're chatting with a pizza-ordering bot and you say, "I want to order a pizza." The bot understands you want to order pizza because it knows about this kind of request. So, it quickly moves on to ask you, "Which pizza would you like to order?" This happens because the bot has been taught to recognize when someone wants to order pizza and knows exactly what to ask next.       ❌If the bot doesn't get what your customers saying Now, if your customers say something to the bot and it can't figure out what you mean, it always starts with a basic greeting or an introduction message. It's like the bot is saying, "Hello! How can I help you today?" because it didn't understand your request from the start.      When your customers send any message but not answering collect input ✅If the bot gets what your customers saying Again, whenever a customer says they want to order pizza, and the pizza bot has already learned this phrase, it'll know exactly what to do! It'll jump into action. 👇     If the bot doesn't get what your customers saying   Sometimes, the pizza bot might miss the mark and not understand customer’s message. Picture this: your customers ask our pizza bot for recommendations on the best pizza, but if the bot hasn't learned this phrase yet, it might trigger the "not understood" block. 😕     But don't worry! This is totally normal in bot development. Building a bot is like a continuous journey of improvement. If you notice this happening, here's what you can do: Add a New Intent: Teach the bot to recognize new phrases or questions, like "What's the best pizza?" Add More Expressions to Existing Intent: Expand the range of phrases the bot understands within existing topics. Before you release your bot into the wild, it's super important to test it thoroughly with various expressions to ensure it can understand. 😉    When your customers reply to Collect input  When we're building our chatbot, NLP (Natural Language Processing) behaviour is always on by default.       NLP enabled: A double-edged sword With NLP turned on even while collecting user inputs, our chatbot becomes a super listener, ready to act on what it understands. Imagine asking your customer, "To complete your order, what's your name?" 📝   But, if our customer, perhaps distracted by their craving, responds with "I want pizza" instead of their name, our super listener bot will catch that pizza cue and might ask, "Which pizza would you like?" 🍕 Oops, it missed the point but showed off its understanding skills!     NLP disabled   Now, if we turn off NLP for collecting input, our bot wears its "serious hat." 🎩 It won't get swayed by mentions of pizza or anything else when it's asking for specific information. So, if it asks, "To complete your order, what's your name?" and gets "I want pizza" in response, it won't leap into the pizza menu. It'll stay focused on getting the name, keeping the conversation on track.     Disabling NLP can be good but also on the example below it can collect input that that you may not expected. Enabling or disabling NLP behaviour will depend on your bot use case.      ... View more

In your bot's conversation design, each intent represents a unique user goal or action triggering a specific block.   Yet, users might say the same thing at different points in the conversation. For instance, one could expect to trigger a "yes" intent for different reasons. In this type of scenario, you can re-use the same intent (in this example: "yes") in different contexts.   Context acts as a differentiating factor, allowing the bot to understand the specific conditions under which the same intent should be interpreted differently.   For this tutorial, we’re going to use pizza bot where intent yes and no has been used in order_pizza flow and you want to use yes and no intent inside of free dessert flow.   Add context to your bot For this tutorial, we’re going to use a pizza ordering bot where the intents yes and no are used in order_pizza flow. Now, we want to use yes and no intents inside the free dessert flow.   To do so, we need to add an output context to a block, and a required context to an Intent block.   Add an output context to a block To add an output context to your block:  1. Drag and drop a Message block into your flow. 2. Add a Text message.     3. Navigate to the NLP section within the tab bar. 4. Add an output context named free_dessert.   5. Click on Save.   Add a required context to your intent 1. Drag and drop an intent block onto your canvas and select the existing yes intent. 2. Again, head to the NLP section and add a required context. 3. Type free_dessert to match the output context created earlier. Please note that an intent can have multiple required contexts, since it can be re-used at different points in the conversation.    4. Click on Save.   Configure a response based on context Link the yes intent to a message block tailored for users who want the free dessert.   Enhancing flow visualization Creating a clear and understandable bot conversation flow is essential. While direct connection arrows to intent nodes aren't possible, enhancing your flow's clarity through visual connections between message blocks and intents is achievable. This approach visually delineates the conversation's progression and response logic based on user interactions.   To enhance your context visualisation on the canvas, we sugget to use Parent connections. Parent connections are nothing but a visual tool: they do not bear any logic.   To add Parent connections to your blocks with context: 1. Open the block that bears the ouput context. 2. Navigate to the Settings tab.  3. Under Parent dropdown, select the Free_dessert block.   4. Click Save.   See also: Add an intent to your bot Recognize expressions with intents Canvas overview ... View more

Customer properties allow you to gather and store specific information from customer responses. This documentation guides you through the process of adding a new customer property and saving customer responses to it.   🎥 You prefer to watch a quick hands-on tutorial? Check out our new bot builder video tutorial!   👉  Currently, the bot is capable of saving customer properties with the following types: number, word, time, and text. Any customer properties with types not included in this list will not be stored.    Add a New Customer Property Follow these steps to create a new customer property, for example, to store customer IDs: Navigate to the Customers section and select Customer Properties. Click the + button at the top right to add a new property. Fill in the name, label, and type. For this example, leave values and default values empty.    4. Click Create.   Save customer response to customer property Now, configure the chatbot builder to save customer responses to the created customer property: Add a Collect Input block to your chatbot flow. Include a text message asking for the customer's information.     3. In the "Capture user responses as" section, choose @sysnumber under "Check if response matches," assuming the customer ID is numeric.        4. Under Destination Variable, select the previously created customer property.      5. Configure the Go-To block to continue the conversation.     6. Click Save and add a text message for the configured Go-To block. 7. Add text message for the configure go-to block.     8. Publish your bot to make your changes live.    By following these steps, your chatbot will now collect and store customer IDs in the specified customer property, enhancing the efficiency of your interactions with users.   Use customer property response in bot message Enhance your bot's interactions by incorporating customer property responses into your messages. Similarly to using variables, this feature allows you to leverage information stored in customer properties to personalize your bot messages.   To use a customer property inside bot message: Navigate to the desired block containing the bot message. Compose your bot message as usual. Insert the customer property response by clicking on ‘{’ within your message. This opens a menu where you can select the customer properties available for use. For instance, if you have saved the user's nickname as a customer property, you can incorporate it into your message for a more personalized touch.   4. Select the correct customer property by identifying it through the associated user icon. 5. Save your changes, and your bot message will now dynamically incorporate the customer property response during interactions.   Use customer properties with buttons To use customer properties with buttons, you will need to: Create a Conditions block as a Go To after each button.  Open one of these blocks. In the Else option click on + Add variable of type Text. In the following field, add the internal value of the variable using this format: internal.user.properties.Department_1703155477054 and add the value of the button in the third field, like the image below:       Nice to know If you have a customer property and a variable with the same name, this is how you can distinguish them: customer properties are shown with an avatar icon, while variables have the curly brackets icon {}.   ✔️ If your customer property looks like this after you selected it on the bot internal.user.properties.Department_1703155477054 it will work! It contains the name of the customer property   ✖️If it looks like this internal.user.properties.01H7Z6ARP3TYKJ29H9XRXDG8BN, and doesn't show the name of the customer property, it won't work. This happens to customer properties created in the past and we are working to support them soon. If you have the possibility to re-create or create new customer properties, they should work as the case above mentioned.   Working with previously created customer properties and/or customer properties updated with a CSV If you are working with csv files to batch update the customer properties, it will also not work for now. Using customer properties in the bot flow works when they are added/updated through the chatbot conversation.      For these types of customer properties, the indicated way is to make an API call (read more here) to https://rest.messengerpeople.com/docs/v17/#method-5b6ea1729c24ea6c90055e6e359b42e4 As you can see from the image above, you can make a GET request to the endpoint: https://rest.messengerpeople.com/api/v17/user/property informing the user id, which is variable for every conversation and is saved under profile.messenger_id and you need to inform a value, which should be a string. The result of this API call will be saved under the variable that is called apiResult, in this example. Don't forget to put your API key in the Authorization tab 😉. Once a succesfull reqeust is made, this is what the apiResult will look like:         "apiResult": { "data": { "property": { "id": 117533, "channel_id": 72165, "name": "City", "expiration": -1, "label": "City", "default_value": "---", "position": 4, "type": "word", "values": "", "hidden": 0, "agent_visible": 1, "user_visible": 1 }, "user_values": [ { "id": 999001212140221, "value": "Berlin", "last_update": 1703864511 } ] },         So, in order to show the customer property you need, this is the syntax you need to use: {apiResult.data.user_values[0].value}     This is how it will look like in the conversation:     See also:  Variables and properties  Create a customer property [New bot builder] Collect input from your user ... View more

When you add or delete intents or entities, it is crucial to train the bot so that it can learn them and recognize correctly what is said by the user.   🎥You prefer to watch a quick hands-on tutorial? Check out our new bot builder video tutorial!   To train your bot: Go to your bot canvas under Flows. Click the dropdown next to the Publish button. Select the Train button. The training time depends on how much you changed. Bigger changes may take longer for the bot to fully understand and incorporate the modifications.     See also: [New bot builder] Detect entities in expressions [New bot builder] Add an intent to your bot [New bot builder] Enable a chatbot response to a campaign ... View more

This video offers a step-by-step tutorial on building a bot on new Engage bot builder. You will learn the fundamentals of the bot building using the bot canvas.     Happy bot building! 🤖   See also: [New bot builder] Canvas overview [New bot builder] Detect entities in expressions [New bot builder] Organize your flows   ... View more

When creating a bot from scratch, you will see predefined blocks in your General flow.     The predefined blocks are: Start: this marks the beginning of your conversation. Introduction: is the first block send to the user when the conversation is initiated. Not understood: is triggered when your bot doesn't understand the user. For example, if the customer types a pizza type that is not included in your options, the not understood block will be triggered. You can add a message like "I'm sorry, I don't understand. Let me connect you with one of our agents." Error occurred:  is triggered when a technical error occurs. Similar to the Not Understood block, you can add a message like "The bot is currently unavailable due to a technical issue. Let me connect you with an agent." See also: [New bot builder] Bot builder video tutorial [New bot builder] Canvas overview [New bot builder] Navigate your canvas   ... View more

Depending on how your customer responds to your campaign, you can use an intent to trigger a certain flow.    To connect your chatbot to a campaign: Create a campaign. For instance, a campaign where you ask users if they're interested in a promotion. Define an intent that will trigger that campaign. For instance, a 'yes' intent. Connect that intent to your flow. For example, drag and drop the 'yes' intent to the canvas. Connect it to the next block.      4. Train your bot to make sure that the intent is recognized. 5. Test your bot to see the result.       Best practice Try to use a different response, for example, for each campaign. If your customer needs to respond "yes" for a certain deal in one campaign, that means the "Yes" intent should only be used for that specific campaign. An intent can only be triggered once to initiate a flow.   See also: [New bot builder] Add an intent to your bot [New bot builder] Recognize expressions with intents [New bot builder] Train your bot   ... View more

Arrange your chatbot settings from the Bot settings menu that's on the left-hand side of your bot builder.   Bot details In Bot Details you'll be able to see the name of your of bot as well as the primary language.   The option to add additional languages falls under our advanced features. If you're interested in learning more about this capability, don't hesitate to get in touch with us. Similarly, the ability to edit bot access is reserved for advanced features.       For existing bot: the bot's default language is English. However, if you create a conversation flow in German or any other language, the bot will understand and respond accordingly.    Generative AI Here you can decide to switch on or off the AI-powered expression generation feature.     Bot status Click the status slider to temporarily disable your bot.     Maximum message length Chatbots work best with short and concise messages. To avoid that messages that are too long are not understood, a maximum message length can be configured.   Whenever a message is bigger than the characters stated in these settings, the bot will automatically go to a block of your choice. A message with text like: 'I am sorry, I work best with shorter messages. Could you please rephrase that?' is recommended for a good user experience.     Bot behaviour The typing speed, or typing duration, is how fast the bot answers to the user. The higher the typing speed, the longer the user will see that the bot is 'typing' before they receive an answer. The right typing speed can create a positive, more humanlike experience for the user. The default typing speed is 1500ms, but try out different speeds to see what is best for your bot.     Data retention This is include in our advanced features. Please contact us if you want to know more.       Delete bot  You can delete your bot by clicking the Delete this bot button.     See also Conversation design intro [New bot builder] Canvas overview [New bot builder] Blocks and steps ... View more

Comments are a powerful tool for providing feedback and fostering collaboration on your bot canvas.    🎥You prefer to watch a quick hands-on tutorial? Check out our new bot builder video tutorial! Add a comment To add a comment to your canvas: 1.  Enable the comment mode by clicking on the Comment icon in the top right menu of the screen.        2. Choose the specific location on your canvas, then ‘right-click’ on your cursor to add comment. 3. Type your comments in the comment field provided. 4. Press the 'enter' key on your keyboard to submit your comment.       5. You will see the comment in the comment section on the left.     Reply to a comment To reply to a comment: 1. Double click on the comment. 2. Click on the Reply field below the comment. 3. Press the 'enter' key on your keyboard to submit your reply.     Resolve comment To mark your comment as resolved: Double-click the comment to view it. On the left side of the modal, click the checked-mark button. The comment will disappear, indicating that it has been marked as resolved.     Delete a comment To delete a comment: Make sure that you’re in commenting mode by clicking the ‘comment’ icon on the right top menu. Choose the comment that you want to delete by clicking on it. Click the three dots button. Choose Delete comment.     See also: [New bot builder] Canvas overview [New bot builder] Navigate your canvas Chatbot design workflow ... View more

Publishing your bot means that the latest version of your bot will be live on all your channels. Remember that each time you publish your bot, it will overwrite the previously published version.   Please make sure that you train your bot's NLP before publishing it. Otherwise, you will be reminded to do so just before publishing.    To publish your bot: Click Publish bot at the top right corner of your canvas.     2. A little box pops up. In this box, you can write a description for what you're publishing. Yet,  you won't see this description right away anywhere on the UI. This is because it's part of advanced features that let you look back at what you've published before. 3. Click Publish.     3. The button shows a wheel and the text changes into Publishing, meaning that the upload is taking place. When the upload is done, you’ll see the publish button becomes enabled again.      See also: [New bot builder] Train your AI bot [New bot builder] Recognize expressions with intents Channel limitations   ... View more

To check if your bot is doing what you expect, it's good practice to test every new development by using the Test your bot widget on the right side of your canvas.   🎥You prefer to watch a quick hands-on tutorial? Check out our new bot builder video tutorial!     You should see 3 options under Test your bot: WhatsApp Sandbox: enables you to test your bot on a real WhatsApp channel. Debugger: showcases how your bot will behave in a web chat.  Voice: Currently, this is not supported on Engage channel.     WhatsApp Sandbox The WhatsApp Sandbox is for you to test your bot on a WhatsApp environment, without even setting up a WhatsApp channel. It's only there for demonstration purposes.   To test your bot on the WhatsApp Sandbox: On the upper-left corner of your Test your bot widget, select WhatsApp Sandbox. Scan the QR code on the screen with your phone.     2. WhatsApp opens a new conversation with a pre-filled message. Send the pre-filled message. As soon as you send it, your WhatsApp number will be connected to that bot for the next 72h, or until you send 'STOP'.     3. Send a message to trigger it your bot and start chatting!       5. To disconnect from one bot and test another, send "STOP". You will receive a message confirming that your number was disconnected from that bot. You can connect to a different bot by sending another bot ID, for example "join xyz1234".     See also: Create a channel configuration Channel limitations [New bot builder] Add list messages to your WhatsApp bot   ... View more

If you are encountering difficulties when organizing your flows because of all the overlapping path connections and blocks, one way to make your life easier is to structure your canvas in flows: Make smaller, manageable flows that gather a piece of conversation about the same 'topic' Use subflows to break up a large flow into smaller, manageable pieces 🎥You prefer to watch a quick hands-on tutorial? Check out our new bot builder video tutorial!   👉Keep in mind that flows, just like the connections between blocks, are simply a way of organizing your bot. They do not restrict the movement of users across your bot: Users can jump from one flow to another by using intents Bot builders can set-up a next bot dialog to another flow. Bear in mind that an orange representation on the canvas means that your conversation will jump to something that lies in a different flow.   Add flows To add flows: Click the Add flow button at the top left side bar of the canvas. Enter the name of your new flow. Click Create to add your new flow to the canvas.     Add subflows To enhance readability, you have the option to create subflows and break up a large flow into smaller, more manageable parts.    To add a subflow: Click the three dots icon next to your main flow title. Click on Add subflow.       Change the parent flow To change the parent flow: Click the three dots icon next to the subflow title. Choose Edit. Select the desired parent flow. Click Update to save.     Move blocks to another flow If you have a bot with complex flows, you may find it necessary to move certain blocks from one flow to another.   To move blocks to another flow or subflow: Select the blocks that you want to move. You can select multiple dialogs in 2 ways: Holding the CMD key (or CTRL key on Windows) to individually click and select. Or holding the shift key to create a rectangular selection of multiple blocks.  Click on the Move to flow icon in the top left corner of the toolbar. Create or choose the flow or subflow where you want to move the selected blocks. Click Move to complete the process.       See also: [New bot builder] Canvas overview [New bot builder] Blocks and steps [New bot builder] Add buttons to your flow   ... View more

Chances are that you'll need to integrate bot with your back end or third-party services. Sinch Engage allows you to do that using APIs.   How custom integrations work Engage Bot Builder offers a solution to integrate your conversational agent with your backend business logic, APIs, and databases. This integration allows you to create contextual, personalized, and actionable conversational experiences for your users.   The API is available in the Action step to enable you to create chatbot messages based on user-specific information and other external data. Additionally, it allows you to redirect your users to different conversational flows based on your own business logic. You can use this solution on any platform that supports receiving and responding to HTTP requests.         A user types and sends a text message from a conversational agent interface channel like WhatsApp, Webchat, Facebook Messenger, … to Engage bot builder. The received message is going through Engage’s NLP engine to detect the intent and the returned intent combined with user context will be used to retrieve the next bot dialog in the conversation. Engage’s API plugin can be added in a bot dialog to send an API request to your server with different types of static data and/or user session data. Your server can respond with an object with three fields: session: A session object for saving retrieved user session data messages: An array of messages to send back to the interface channel nextDialogstate: A bot dialog state identifier to redirect the user to a next bot dialog state in a conversation flow.   Session data will first be stored in the user session so that you can use this data in messages defined in the array of messages or in messages defined in a dialog state defined as nextDialogstate in the API response. Second, messages will be sent, and afterwards the user is redirected to the nextDialogstate. All fields are optional.   API plugin Engage bot builder provides an API plugin in the list of action plugins which you can configure in dialog state in one of your conversational flows.     Sending the API request The API plugin sends a request to your back end server. It supports different configuration settings: HTTPS method API endpoint url Query parameters Body payload (JSON)   HTTPS method and API endpoint url The plugin supports three HTTPS methods GET POST DELETE PUT PATCH       Query and body payload parameters Add query parameters and/or a body payload by defining key value combinations. Each key can have three possible value types: text: static text variable: a user session variable. The value of the variable will be stored as value for the key. Dot and array notation are supported, for example: users[0].firstname dialogstate: select a dialog state from the dropdown. The dialog state id will be stored as value for the key. This id can be used to redirect the user to a certain dialog state based on your business logic when sending back the API response.   👉You can only define a request body when your request method is POST or DELETE.    In this example, representing a money transfer, we send five keys in the body payload of an HTTPS POST request to our API endpoint.          The amount key will have the value of user session variable transfer_amount (ex: 500). The destination key will have the value of user session variable transfer_destination (ex: Elon Musk). The accountType key will have the value of user session variable card_type (ex: savings_account). The transactionSuccess key will have the dialog state identifier for the ‘successful transaction’ dialog state. This identifier can be used in the response of this API request to redirect the user to a new dialog state. The transactionNoMoney key will have the dialog state identifier for the ‘unsuccessful transaction’ dialog state. This identifier can be used in the response of this API request to redirect the user to a new dialog state. The test key will have a value of ‘5’.   This will result in the following body payload.     { "amount": 500, "destination": "Elon Musk", "accountType": "savings_account", "transactionSuccess": "successful transaction", "transactionNoMoney": "unsuccessful transaction", "test": 5 }       API headers Next to Query and Body parameters, Engage bot builder also supports API Headers in its POST, GET and DELETE requests. Headers can be added using the same combination of Key, Type and Value as the other parameters.     Multi-language If the API response will send agent messages back to the user and the agent supports multiple languages, don’t forget to send the user language in the request. The user language is available in the user session variable ‘locale'. Your back end service can use this language setting to send back the response in the user his preferred language.   Sending the API response You do not need to configure the API plugin to listen for a response. This is done automatically and the API plugin will listen for what your API returns. The API plugin supports 3 types of return variables: session: A session object for saving data in to the user session. The session has two mandatory fields:namespace: a key namespace. The data object will be stored in this namespace key in the user session. You can access this object in Chatlayer.ai by using interpolation: *{namespace.dataKey}*data: an object which will be saved in the user session data in the namespace key. messages: An array of messages to send back to the user interface channel. The structure of different message types such as text, buttons, quick replies, carousels, lists, media, … is available in the chat message structure. action: an object defining an action such as redirecting the user to a next dialog state in the conversation. nextDialogstate: A dialog state identifier to redirect the user to a next dialog state in the conversation flow The above 3 options are executed in the order shown above: session variables are set first, then messages are sent and then you will jump to the next dialog state. You can find an example JSON for these 3 cases in the code snippet below:       const result = { session: { namespace: 'myNamespace', data: { variable: 'test123' }, }, messages: [{ type: 'text', config: { textMessages: [{ text: 'random message 1' }] } }], action: { nextDialogstate: 'dialogstate-123-abc', }, };       👉Make sure you include the correct content t ype in the header: content-type: application/json;   Example This example demonstrates one API endpoint for transferring an amount of money from an account type (regular or savings) to someone. We will redirected the user to a certain dialog state based on the transaction result.     app.post('/transaction', function (req, res) { let nextDialogstate; const { amount, destination, accountType, transactionSuccess, transactionNoMoney = req.body;         // get account type (regular - savings account) const account = account_synonyms[accountType];         if( accounts[account].amount + accounts[accounthlimit — amount < ) { nextDialogstate = transactionNoMoney } else { // transfer amount accounts[account].amount —= amount; nextDialogstate = transactionSuccess; }         res.json({ action: { nextDialogstate, }, session: { namespace: 'account', data: { limit: accounts[account].limit, amount: accounts[account].amount } }, }) });       We receive the body payload object as defined in the API plugin. If the user doesn’t have a sufficient amount of money on his account we set the next dialog state to ‘transactionNoMoney’. Else we subtract the desired amount and set the next dialog state to ‘transactionSuccess'.   As a response for the request we send the next dialogs state to redirect the user to that state and we save the amount of money and the limit of his account in his session data under the namespace account. This data can be used in that next dialog state.     As an alternative solution you could also send that chat message as a response of the API plugin requests by using the messages key.   👉 For more API documentation, please check our API documentation here.   See also: [New bot builder] Make a channel router flow [New bot builder] Variables and properties [New bot builder] Channel limitations ... View more

System entities are pre-defined Engage entities that can be automatically extracted from the user's messages. This means that you don't need to create them: they are already part of the system.   Please note that you should never overwrite System Entities yourself – they are automatically overwritten by the last detected value (if any values are detected). So instead, copy the System Entity variable to a variable of your own choosing outside the sys or internal namespaces.   Supported system entities   Engage bot builder supports the following system entity types:     Variable name Example input by user Example result in session sys.email "ilovebots@chatlayer.ai" sys: {email: 'ilovebots@chatlayer.ai'} sys.phone_number "+32 487 23 02 03" sys: {phone_number: '(+32) 487230203'} sys.ordinal "5th" sys: {ordinal: '5'} sys.amount_of_money "5 euro" sys: {amount_of money: '5', amount_of_money_currency: 'EUR'} sys.distance "5 kilometers" sys: {distance: '5', distance_unit: 'kilometre'} sys.number "eighty eight" sys: {number: '88'} sys.quantity "3 liters" sys: {quantity: '3', quantity_unit: 'litre'} sys.temperature "80C" sys: {temperature '80', temperature_unit: 'celsius' sys.time "3 pm tomorrow" sys: {time: '2020-12-25T15:00:00.000+00:00', time_grain: 'hour'} sys.url "https://www.chatlayer.ai/jobs" sys: {url: 'www.chatlayer.ai/jobs', url_domain: 'chatlayer.ai'} sys.duration "3 hours" sys: {duration: '3', duration_unit: 'hour', duration_normalized: '10800', duration_normalized_unit: 'second'}   @sys.email @sys.email checks if the given user input has the format of an email address. If the given input is not an email address, the bot will show the 'When user response does not match' messages, at the bottom of the input validation. If the response is a valid email address, you can see that the email address will be saved correctly under the given variable name in the debugger.    @sys.phone_number '@sys.phone_number' will accept numbers with more than 6 and fewer than 17 numbers in them.   @sys.number Any number in the bot is immediately recognized as '@sys.number'. However, seeing you could ask for multiple number in different input validations, it is important to give them a unique name. So, when you choose '@sys.number' in 'Check if response matches', you will get the option to give this variable a unique name.    @sys.url '@sys.url' checks if the given input is a URL. Accepted formats can be with www (www.engage.sinch.com) or without (engage.sinch.com). Just the domain 'sinch engage' will not be accepted.   See also: [New bot builder] Detect entities in expressions [New bot builder] Recognize expressions with intents [New bot builder] Add an intent to your bot ... View more

Match entities are entities detected only when the user uses a string that matches a pre-defined string.    Create a match entity There are 2 possibilities for detecting a match entity: match text match pattern To create a match entity: Go to the Entities page and click on Match entities. To add new entity, click Add match entity. Here, you can choose between the 2 options: Match text: for example, the different values of a @product entity.   Match pattern: this one uses RegEx expressions to match a particular format, like a customer ID for example. For instance, if you have @customer_ID as a match entity, and have provided the following regex pattern: [a-z]{5}[0-9]{2}. This means that when a users says "My customer ID is terwf33" – which consists of 5 letters and 2 numbers – it is saved as the match entity @customer_ID with the value "terwf33".    3. Make sure to train your NLP.     4. Test your bot. Imagine building an FAQ bot. One of the things it can do for the user, is trace their lost package. For the bot to be able to find this lost package, it needs the package number. To get this number, the conversation would look like this:   The bot now recognises the package number without asking for it.     See also: [New bot builder] Detect entities in expressions [New bot builder] Recognize expressions with intents [New bot builder] Add an intent to your bot ... View more