But especially in these COVID work-at-home times, it becomes harder to manage a customer service team.

So, that’s why I will show you how can use a Xenioo chatbot to manage a distributed support team. 

Adding and inviting team members

Before we can actually manage a distributed support team, we first need to make one.

Let’s start by creating our support team in Xenioo by inviting our team members. 

You can do this by signing in to your Xenioo account, go to one of your chatbots and click on Settings → Team.

Here, you can fill in the email of the team members, the group they belong to (for example, ‘Sales’ or ‘Support’) and the permission they have:

Once you click on Send invitation, your team members will automatically get an email from Xenioo:

And when they click on Click here to Sign Up or Sign in, they will first need to create an account:

If they made an account, they need to confirm their email (otherwise they won’t show up as “Active” team members):

Eventually, when they log in, they need to select the account they want to work with:

When they have performed all these steps, they will show up as Active members in Xenioo:

Great! Now you got your own team in Xenioo to handle support queries. 

Let’s move further.

Setting up your fallback message

Now we’ve got a team that can handle your support queries, but when are we going to handle them?

This is where the fallback message comes into play.

The fallback message is the message that shows up when your chatbot doesn’t know an answer to a question. 

It is not a problem when the chatbot doesn’t know an answer to a question. But it becomes a problem when you are hanging the user out to dry.

So, we need to make sure that the user has a great experience with your chatbot.

But how can you do this?

By handing over the conversation to a human, who ensures the user has a great experience.

Now, head over to the Build section in Xenioo and look for your Fallback interaction, it looks something like this:

So when the chatbot doesn’t understand something, I like to give the user a choice: Do you need help from a human?

Thus, we need to change the Fallback interaction.

Let’s begin by adding the question.

You can just click on the text in the Fallback interaction and change it to something else:

NOTE: Don’t forget to hit the Save button!

Next, we need to give the user a choice. A choice between choosing between getting help from a human or not. So let’s make two interactions for that.

Just click somewhere in the Flow editor, then on the right-hand side there will be a panel where you can choose for “Add interaction”:

Click on the interaction and name it “Forward to support”:

By the way, I always like to give my interactions a name. It keeps your chatbot flows structured and in a blink of an eye, you understand the whole overview.

We can do the same for the alternative (not forwarding to support), by just clicking on the Tools icon and cloning the existing Interaction:

NOTE: See what I did there? You can just copy different interactions within your chatbot flows. Great feature!

So, now we made these two messages:

But, we need to make a flow, so that if the user answers “Yes” to the question, he will go to “Forward or support”.

Thus, let’s do that! Go to the Fallback interaction, click on the Tools icon and click on Add new action:

Then, under “Content”, choose for the Quick Reply Button:

Here, you can set the Title of the button and under “Go to”, you can choose the interaction it goes to:

We can do the same for the “No” button, so the final flow looks like this:

Assigning a live chat agent to a conversation

Now we got the messages in our flow, we need to assign an agent to the conversation if the user wants to forward it to a support agent.

So, head over the Forward to support interaction, click on Add new action and choose for Set Chat Operator State (Under Flow):

Now, on the right side of your screen, a panel pops up where you can edit the settings of the Set Chat Operator State action:

First, we need to determine which mode we want to use. We can choose between two modes:

1. Request operator
2. Operator take over

With the “Request operator”, a request operator flag is raised for a specific conversation, which looks like this in Xenioo:

But this doesn’t deactivate the chatbot. If you want that any user input is ignored by the chatbot, choose for “Operator take over”. 

And that’s the mode we are going to use!

By the way, there is also a third option called “Chatbot controlled”, but we will not need that in this tutorial

So, if you choose for Operator Take Over, you can also set what kind of operator you want:

• A random operator
• A less busy operator
• Or a specific operator

If you choose for random or less busy, Xenioo will determine the operator for you. But with a specific operator, you can select one person from a dropdown list:

Last but not least, you can also choose for online operators, which is an extremely useful feature:

My recommendation is to go with the following: 

1. Mode: Operator Take Over
2. Assign operator: Less busy
3. Select only online operators

With these settings, you make sure that the chat is handed over from your chatbot to a live chat agent. Besides, you have agents that have the time to respond to your user and are online.

Couldn’t be any better, right?

Assign agent groups to a conversation

So far, we’ve covered how to assign any agent or a specific live chat agent to a conversation.

But, what about agent groups?

Often, there are specific agent groups in companies, such as Support and Sales.

Thus, it would be useful to assign a chat to a specific group of agents. 

And that is possible with Xenioo!

Just head over to the Set Chat Operator State block we already made and under “Operators group”, choose a specific group:

And that’s it! You just assigned a chat to a specific group!

Sharing a conversation URL

We have one last feature to cover: Sharing a conversation URL.

This is one of the best support features that sets Xenioo apart from other chatbot software companies.

Let’s imagine that you are a support agent and you are having trouble giving the right answer to a customer’s question. But, you know that your colleague Dave knows the answer to that specific question.

However, Dave is already done with his shift and doesn’t have his laptop around. So, what do you do?

It would be easy if you could just hand over the conversation to Dave’s mobile phone, right?

That’s where the Sharing a Conversation URL feature comes in.

With Sharing a Conversation URL, you can just send over a URL that will automatically bring you to the conversation. 

And the best part is that you don’t even have to log in to respond. You can just use it in your (mobile) browser. This is perfect if you need to respond to a customer’s question on the go:

So, how do you activate this in Xenioo?

Just head over to the Forward to support block we made before, add another action and choose for Create Conversation URL (Under “Flow”):

Next, you need to set the Validity (how long the link stays valid) and if you want to take over the conversation:

NOTE: It is important to toggle the “Take Over Conversation”, because otherwise you can only see the conversation with the URL, but cannot respond to it.

Up and until now, this is the chatbot flow we created:

But, we are not there yet.

Let’s move on.

Notify the live chat agents

There is still one thing left to do. The user can choose to forward the conversation to support, but how do the live chat agents know this?

They don’t… yet.

But we can notify them in Slack!

Again, head over to the flow builder in Xenoo and add the Call API Service (under Integration) to the Forward to Support interaction:

In the API settings, you can fill in the Service URL, Headers and Payload of the message:

NOTE: If you are not familiar with creating webhooks between systems, you might want a developer to create this.

Once you’ve set this right, every support request will be sent to your live chat agents in Slack!

Awesome, right?

What if the live chat agents are offline?

Unfortunately for our customers, we all have to sleep at some time.

So, this means that a user wants to talk with your chatbot in the middle of the night (especially with a chatbot).

And then, your live chat agents are offline and they cannot ensure a great experience for your users.

Then, you just need to tell them they are not online.

And we can do this by creating a Variable Switch in the Xenioo flow:

This switch checks if the current hour is between 09:00 and 17:00 (standard business hours). Moreover, it checks if the current day is a weekday.

And when the user meets this condition, you can determine which interaction to send next with the Go To action:

By now, I guess you are probably kind of a chatbot wizard, so I won’t explain every step in this flow, but it can end up looking like this:

The only thing I didn’t explain yet (what is in this flow), is how you can send an email from Xenioo. Again, just add an action to an existing interaction, and choose for Email Quick Reply Button (under Content):

Once you selected this, you need to add an operation:

Then, choose for Send Xenioo Mail Message:

And eventually, you can set the sender, subject and content of that email:

Ask for live chat agent after five times

In some cases, you don’t want to trigger the live chat team right away if your chatbot doesn’t know an answer to a question.

Maybe, you first want the customer to try some other phrases that might trigger the chatbot.

In such a case, we can ask for a live chat agent only after five times the fallback happened. 

By the way, you can also set this to 2, 10 or 30. I just use five in this example

We will do this by increasing a variable with 1 every time the fallback interaction occurs.

So, let’s add an action to our Fallback interaction, called Set User Variable (under Profile):

Here, we can just type in the name of the variable and increase it with 1:

Next, we are creating another Variable Switch to check whether the variable ‘fallback_count’ is equal to 1:

I will spare you the details of every step in this flow (because we already covered all the elements we are using for this), but the eventual flow can look something like this:

That’s it

That’s it! That’s how you manage a distributed support team with Xenioo.

Now, let me ask you a question.

How do you currently manage your distributed support team?

And would Xenioo make your life easier?

Join the Facebook group and let us know!

The post How to use a chatbot to manage a distributed support team appeared first on Xenioo.

This time we are going to see exactly this: we will create a very simple chatbot that will act as a group manager and moderator.

Telegram Privacy Mode

When building you chatbot using the BotFather, you will notice multiple configuration options where you can change the name, the avatar and some other settings.

One of these options is /setprivacy and can be used to turn on or off “Group Privacy”. What is it exactly?

• With Bot Privacy OFF, your chatbot will receive every message that is sent to the chat by any user. If you have a hundred thousands users in your group, Xenioo will receive all of the messages and process them.
• With Bot Privacy ON, none of the messages sent by any user will reach Xenioo. Only messages starting with the symbol ‘/’, or direct mentions of your chatbot, will be received.

By default, Bot Privacy is ON and for our example, we will leave it as it is.

As we said, we are going to create a Group Manager and we do not want, for now, to check all users messages.

Reacting to Chat Commands

As explained, with group privacy turned on, we will be receiving only chat messages starting with a ‘/’. A typical use of these commands are /help or /about but you can just handle whatever command you like.

Using Xenioo global bot operations you can handle these commands very easily and make sure that they are always triggered whatever the status of your chatbot.

In our chatbot sample, the /hep command will reply with a very simple bubble proposing two different commands.

Whatever text starts with a ‘/ ‘ symbol inside a Xenioo text will be transformed into a link command inside the Telegram Bubble.

The user can either write the command or just click on the command link inside the bubble to invoke your chatbot again.

Users coming and going

As soon as you add your Xenioo chatbot to a Telegram group you will start receiving events related to every user joining and leaving.

Each event will trigger your chatbot populating specific variables you can use in your flow to react and eventually welcome, or bid farewell to users.

Managing variables and messages have been covered in multiple articles so we will be focusing now only on which variables are available to you whenever your chatbot is invoked in a Telegram Group.

Users can be added massively with a single invite so make sure to always check for the correct number indicated by the telegram_new_user_count variable.

On big groups, it is not uncommon to have tens of users joining altogether. Using Xenioo variable manipulation capabilities you can create a simple loop very easily.

On the other hand, users leaving can be multiple but never massive as removal is immediate and never simultaneous. Variable telegram_user_leaving value is always related to a single user and your flow will be called for each user.

Overseeing users behavior

Another important aspect of managing groups is overseeing users behavior.

If your group runs with specific language policy, for example, a chatbot can be a very effective way of enforcing it and Xenioo gives not only the tools to detect user text but also to kick them from the group.

The first thing to do is turn off group privacy on your bot: this will allow Xenioo to receive and process each and every message that goes in the group.

After this, you can easily create an NLP intent containing all of the expressions that you do not want your users to use.

The expressions can vary from simple, even single word entries to more complex sentences covering different topics. The Xenioo NLP engine will automatically train itself and detect also texts that are different but express the same intent.

Once you’re satisfied with your intent, we can link it to our global chatbot operations and attach it to an interaction.

As you can see from the diagram our approach is to give the user up to 3 warnings before taking on final action.

Each user warning count has its own variable and our chatbot will be able to take note of the count even after months (or you can go ahead and reset counter once in a while using just a broadcast).

Having a high number of users may require a more complex and database oriented approach but for our example, it is going to be just fine.

Your Personal Group Manager

We’ve just seen how building a Telegram Group Manager bot with Xenioo is incredibly easy and flexible.

Want to try it right away? There’s a free template built exactly like this example and ready to be tested in your account.

Do you have any special request or requirement for your Telegram group? Let us know in our community group or just drop a line to our team!

The post Learn How To Create A Telegram Group Chatbot appeared first on Xenioo.

Abbiamo spiegato le basi di come gestire una conversazione singola o di gruppo ed i concetti legati alla privacy del bot, ma non siamo entrati nel dettaglio di come poter gestire un gruppo su Telegram attraverso un chatbot.

L’obiettivo di questo articolo è proprio questo: vi mostreremo come creare un semplice chatbot che funzioni come gestore e moderatore di un gruppo Telegram.

Impostare la privacy di un gruppo Telegram

Nella creazione del chatbot attraverso il BotFather, avrai notato come è possibile configurare una serie di opzioni come il nome, l’avatar e molte altre ancora.

Una di queste opzioni è la /setprivacy e può essere impostata per abilitare o disattivare la “Group Privacy“.

Ma cos’e’ la Group Policy di Tegram?

• con la Group Policy OFF (disabilitata), il chatbot riceverà ogni messaggio inviato dagli utenti. Se il tuo chatbot ha migliaia di utenti nel gruppo, Xenioo riceverà e processerà tutti i messaggi inviati da ciascuno di essi.
• con la Group Policy ON (attivata), nessun messaggio scritto dagli utenti in chat raggiungerà Xenioo. Gli unici messaggi che verranno ricevuti e processati da Xenioo saranno quelli che iniziano con il carattere ‘/’ oppure menzioni dirette.

Per impostazione predefinita, la Group Policy è impostata ad ON ed è quindi attivata.

Per il momento lasceremo l’impostazione della privacy predefinita, in quanto non ci interessa ricevere tutti i messaggi degli utenti per gestire i comandi nel gruppo. Vedremo successivamente come disattivarla quando dovremo configurare il nostro chatbot per funzionare anche da moderatore del gruppo.

Rispondere ai comandi ricevuti in chat

Come descritto nel paragrafo precedente, con la Group Privacy attivata, il chatbot riceverà solo i messaggi che iniziano con il carattere ‘/’. Chiameremo questi messaggi “comandi”.

L’utilizzo tipico di questi comandi è per richiedere aiuto (/help) oppure informazioni aggiuntive (/about), ma è possibile creare e gestire qualsiasi tipo di comando.

In Xenioo è possibile creare i comandi nella sezione Global Bot Operations del chatbot. Infatti, ogni operazione inserita nella Global Bot Operations viene sempre processata indipendentemente dallo stato del chatbot ed in qualsiasi punto della conversazione utente.

Per impostare il comando è sufficiente inserire (/help) nel campo Control Expression di una operazione Text Parse. Questo tipo di operazione cattura l’input dell’utente e reagisce se il testo corrisponde ad una specifica espressione regolare.

Nel nostro caso ci si aspetta che l’utente scriva esattamente il testo /help ed il chatbot risponderà con un semplice messaggio proponendo quello che sono gli altri comandi disponibili.

Inoltre ogni testo che inizia con il carattere ‘/’ viene trasformato da Telegram in un comando cliccabile. L’utente può quindi attivare il comando sia scrivendolo nella chat, sia cliccando direttamente sul link del comando.

Gestire gli utenti in entrata ed uscita dal gruppo

Nel momento in cui si aggiunge un chatbot ad un gruppo Telegram, Xenioo comincerà a ricevere una serie di eventi relativi agli utenti che si iscrivono oppure lasciano il gruppo.

Ognuno di questi eventi viene intercettato dal chatbot e Xenioo valorizza delle specifiche variabili che possono essere poi utilizzate all’interno del flusso, per esempio per dare il benvenuto agli utenti oppure salutarli nel momeno in cui se ne vanno.

Abbiamo già discusso come utilizzare le variabili per gestire il flusso in articoli precedenti, quindi per ora ci limiteremo a vedere nel dettaglio le variabili che sono disponibili quando il chatbot è collegato ad un gruppo Telegram.

Qando si gestisce un gruppo Telegram bisogna tener presente che gli utenti possono essere aggiunti massivamente con un singolo invito. Dal momento che il bot viene chiamato quando uno o più utenti sono stati aggiunti al gruppo, diventa quindi necessario verificare correttamente il numero indicato dalla variabile telegram_new_user_count.

Sfruttando la capacità di Xenioo nel manipolare le variabili, è possibile creare facilmente dei blocchi per gestire questa casistica, come è possibile vedere nell’immagine sottostante.

Al contrario, la rimozione di un utente dal gruppo è immediata e quindi mai si verificheranno rimozioni massive di utenti contemporaneamente. La variabile telegram_user_leaving è sempre relativa ad un singolo utente e il bot verrà chiamato una volta per ogni utente che lascia il gruppo.

Moderare il gruppo

Un aspetto importante nella gestione di un gruppo è la supervisione del comportamento degli utenti. Se per esempio il gruppo adotta delle regole specifiche riguardanti il linguaggio non permesso, il chatbot si presta come una soluzione ideale per verificare che queste vengano fatte rispettare.

Xenioo permette non solo di rilevare e processare ogni testo scritto dagli utenti nel gruppo, ma consente al chatbot di rimuovere automaticamente dal gruppo gli utenti che non rispettino per esempio quelle determinate regole.

La prima cosa da fare per sì che il chatbot funzioni da moderatore del gruppo è quella di disabilitare la Group Policy, disattivandola come abbiamo visto nel paragrafo iniziale. Questo permetterà a Xenioo di ricevere tutti i messaggi inviati dagli utenti nel gruppo.

Il passo successivo è quello di creare una serie di intenti NLP contenenti tutte le espressioni che non si vuole vengano utilizzate all’interno del gruppo (parole volgari, argomenti politici, etc…)

Le espressioni possono variare da una semplice sentenza, anche a singola parola, fino ad arrivare a sentenze complesse che coprono diversi argomenti. Il motore NLP di Xenioo sarà in grado di imparare automaticamente da queste espressioni e quindi capace di individuare anche testi che sono differenti ma esprimono lo stesso intento.

Una volta creati gli intenti, possono essere utilizzati all’interno delle Global Bot Operations collegandoli ad una interazione che si occuperà di gestire la risposta del chatbot.

Come è possibile vedere dall’immagine, l’approccio che abbiamo usato nel chatbot di esempio è quello di dare all’utente 3 avvertimenti prima di essere rimosso dal gruppo. Ogni avvertimento viene gestito con una specifica variabile per utente ed il chatbot sarà in grado di ricordarsi del conteggio anche dopo mesi (oppure si potrebbe implementare un meccanismo per il reset del contatore degli avvisi usando un broadcast).

Se il gruppo da gestire contiene un numero molto alto di utenti, potrebbe essere necessario implementare una soluzione un poco più complessa e basata su database, ma per il nostro chatbot di esempio l’approccio scelto è più che sufficiente.

Ricapitolando…

In questo articolo abbiamo visto come creare un chatbot per gestire e moderare un gruppo Telegram con Xenioo sia estremamente semplice e flessibile.

Vorresti provarlo subito? Questo chatbot è disponibile come Template gratuito all’interno di Xenioo, ti basta entrare nel tuo account per poterlo utilizzare.

Hai delle richieste specifiche per il tuo chatbot Telegram? Non esitare a contattare direttamente il nostro team oppure scrivi alla nostra community Facebook!

The post Come creare un chatbot per moderare un gruppo Telegram appeared first on Xenioo.

Still, sometimes, a user likes to talk to a human being, or your NLP does not yet manage a specific problem.

In a situation where a human being is required to engage the user directly, most tools fall short. You usually end up with something that can create an exceptional chatbot or something that can manage a user-to-operator conversation.

With Xenioo, you get the best of both worlds, and in this post, we’re going to see how.

Enters the Ninja

To get the most out of Xenioo conversation and operator management, we are going to activate the “Pro Team” package.

This additional package, for a mere 39,99€ a month, will not only upgrade some actions but also enable team fine-tuning and operators inside conversations.

This package is also available for free, if you activate a Professional or Agency plan.

After adding our “Pro Team” package, we can immediately head to our chatbot settings menu and see how it has dramatically changed.

In our example, we’re going to add three new team members to our support bot. These users will have different jobs and different purposes so that we can explore how Xenioo lets you fine-tune permissions and conversations.

The first one that we’re calling Andrew is part of the Technical Support group and will only work on customers support on the conversations section.

We will add him to our chatbot team enabling only access to the conversation section and specifically only to conversations that are associated with his group.

He will not be able to check and engage in any conversation unless specifically assigned to him or his group.

Anna, our second team member, is part of the marketing group and will be engaged by marketing questions.

She also needs to check reports now and then so we’re going to give her access to the bot dashboard and bot statistical data.

Mary, our last member, is a Supervisor and she will see all conversations and statistics. Also, she hasn’t developed the chatbot, but by overseeing conversation, she can choose to better train the AI.

For this reason, we’re also giving her access to a read-only view of the chatbot and full editing capabilities of the NLP section.

As you can see, enabling Pro Team opens up all of the necessary permissions that allow you the power to choose what your team members can and cannot do and give them access to your chatbot being sure that they are not going to access information that is not meant for them.

Once we’re done creating our full team and permissions, let’s continue by adding operator management to our chatbot.

Do you want to talk to a human ?

Once your chatbot has done all it could as 1st level support automation, it may be time to move the conversation to a real human.

With Xenioo, you can manage this situation with a very specific action called Set Chat Operator State.

With the Pro Team package, this action becomes even more powerful.

As you can see in the flow above, we manage some chatbot struggle giving the option to talk to an operator. If the user chooses to do so, we redirect to an explanation message and activate take over.

This action will:

• stop the chatbot from replying. Whatever the user writes will not activate any chatbot action until the conversation is handed back over
  
• assign the conversation to the Technical Support group (the Andrew group we’ve just created!)
  
• automatically pick a member of the above group based on three possible rules:
  • Random: a random member of the group is assigned to the conversation
  • Less Busy: Xenioo will automatically pick the team member currently engaged in fewer conversations
  • Specific: you can choose a specific member of the above group

So in a single action, we’ve just managed to create a rule we can use anywhere in our chatbot. Using these options, you can easily create multiple paths that allow your users to talk to Andrew or Anne depending on the flow.

For example, your chatbot could be in the marketing inquiries section and redirect the conversation to the marketing team.

Anne, in our example the marketing operator, will see the conversation popup in her Xenioo dashboard and can then engage with a one to one conversation with the user on any chatbot channel.

Simultaneously, Andrew could be handling multiple conversations with users having tech problems. Once he solves all of the issues, he can then give back control to the chatbot and even redirect the conversation to a specific Behavior or Interaction.

The possibilities are actually endless.

Conversation with users

All of your team is going to access different views of the same chatbot.

Andrew, in our example, is going to see something like in the picture below.

As you see, only the conversation section of your support bot is available and a user, requesting help, is waiting for a takeover.

Andrew sees this conversation because we just configured our chatbot flow to redirect to the technical group the help request. Andrew can take over the conversation and chat with our user in real-time.

The channel is not important: Xenioo will handle all of the multi-protocol communication intricacies for you, and everything will just work.

Once the issue has been solved, Andrew can give back control to Xenioo and, if required, redirect the user to as specific Behavior or Interaction.

For example, he could redirect the user to a section where the chatbot collects some feedback on how the support session went.

Changing Conversation Data

Andrew, as an operator also has a very interesting capability: he can alter the chatbot data by updating run-time variables and tags.

By just clicking on the right panel where all the current conversation data is displayed he can pick specific values and change them as well as adding new tags.

This is very useful whenever helping the user requires not just guiding but also updating previous data that the chatbot may have collected.

Did the user specify a wrong product? Or a wrong id number? Our operator can intervene and change it in real-time. Every change made is immediately reflected by our chatbot live.

Having a Support Supervisor

Sometimes, larger customer care teams may have a supervisor taking care of actually assigning customers requesting for help to specific operators.

Much like you would do with real help-desk tickets. With Xenioo, you can also support this kind of scenario.

Mary, our supervisor example, can access any conversation of our chatbot and has a very specific power: she can assign and transfer a conversation to any operator of any group.

By supervising conversation and managing alerts, she can decide to redirect a troubled user to any other operator.

In our example below, she’s redirecting the conversation to Andrew again.

Take over can happen anytime in the chatbot flow and operators can step in at any point. This is particularly useful when a user is stuck to a question or cannot get over a section, and you want to intervene and help.

As the user may not be expecting the switch to human interaction, Mary also can display a specific alert message.

A complete chatbot based support solution

The Pro Team package is a life changer for everybody working with Customer Care chatbots.

Real-time multi-channel conversation means that you can be always available on Facebook, Web, WhatsApp, Telegram and Slack and have one single entry-point for managing everything.

What do you think? Do you have any specific requirement for your team? Let us know by joining our Facebook group or by contacting us directly: we’re looking forward to your feedback!

The post Managing a Chatbot Customer Service Team With Xenioo appeared first on Xenioo.

You can follow our lesson directly from the video below. At the end of the article you will find a Xenioo bot file that simply restores the example bot into your account for playback and testing. Let’s start!

Splitting the conversation path

During marketing or product testing, it is normal to do a split-test.

A split-test is basically a way to randomly redirecting the user to different content, and verifying which content leads to more conversions, contacts or lead generation.

For example, a chatbot conversation can use this kind of approach to check which questions are answered more frequently by a user, which ones are skipped, and which conversation path leads to a better conversions rate.

Using the Random Split Action

By now, you should know that Xenioo always goes beyond the basics to offer you the best possible result and flexibility. The Random Split Action is a typical example.

With any bot, just click on an interaction where you want to create a split, and then click on “Add Action”. On the “Available Actions” dialog, select the Flow tab,  and then “Random Split”.

As you will see, the Random Split data is only a slider where you can set the split threshold: the true power of this action comes from all the operations you can add to alter your chatbot’s behavior, and later analyze the path taken.

Notice how by default, Xenioo will create a Tag Operation that you can use to set a tag based on the activation of the split and a Go To Interaction Operation that will move the conversation to another interaction if you so wish.

These are as always optional: feel free to delete them and build the split test outcome as you please.

Advanced Split-Testing

Each split you add to an interaction is calculated as a single action. This means that you’re not limited to A-B splits, as you can easily create A-B-C splits or even further complicate your scenario to do multiple cascading split testing.

Also, since the Random Split Actions and Operations just trigger a dynamic set of sub-operations, you can create very complex scenarios with random message picking, or multiple casual paths.

In this tutorial we’ve learned how easy it is to setup a split-test enabled chatbot flow using Xenioo.

As with all our lessons, you can find the chatbot sample in your Xenioo account so that you can import it to further experiment and learn.

The post TUTORIAL #7: Creating a split-test driven conversation appeared first on Xenioo.

You can follow our lesson directly from the video below. At the end of the post you will find a Xenioo bot file that simply restores the example bot into your account for playback and testing. Let’s start!

Splitting the conversation path

During marketing or product testing, it is normal to do a split-test. A split-test is basically, a way or randomly redirecting the user to different content, and verifying which content leads to more conversions, contacts or lead generation. For example, a chatbot conversation can use this kind of approach to check which questions are answered more frequently by a user; which ones are skipped; and which conversation path leads to a better conversions ration.

Using the Random Split Action

By now, you should know that Xenioo always goes beyond the basics to offer you the best possible result and flexibility. The Random Split Action is a typical example.
With any bot, just click on an interaction where you want to create a split, and then click on “Add Action”. On the “Available Actions” dialog, select the Flow tab,  and then “Random Split”. As you will see, the Random Split data is only a slider where you can set the split threshold: the true power of this action comes from all the operations you can add to alter your chatbot’s behavior, and later analyze the path taken.

Notice how by default, Xenioo will create a Tag Operation that you can use to set a tag based on the activation of the split; and a Go To Interaction Operation that will move the conversation to another interaction if you so wish. These are as always optional: feel free to delete them and build the split test outcome as you please.

Advanced Split-Testing

Each split you add to an interaction is calculated as a single action. This means that you’re not limited to A-B splits, as you can easily create A-B-C splits or even further complicate your scenario to do multiple cascading split testing. Also, since the Random Split Actions and Operations just trigger a dynamic set of sub-operations, you can create very complex scenarios with random message picking, or multiple casual paths.

In this tutorial we’ve learned how easy it is to setup a split-test enabled chatbot flow using Xenioo.

You can find this chatbot in the Templates section of your Xenioo account. From there you can easily restore the chabot to try the explained features at will.

The post LEZIONE #7: creare conversazioni dinamiche con lo split-test appeared first on Xenioo.