Skip to main content

How to ask an AI model. Please?

six good techniques for prompt engineering

“Prompt engineering,” or the art of asking the right question in the right way, is somewhat like being a manager and asking your subordinates to work. For example, if you’re working with a Generative Artificial Intelligence model and you want it to write a cover letter for a job, you don’t just tell it to “write something.” You give it a well-constructed prompt, showing your resume and describing the job you’re applying for. Prompt engineering is about how to provide information to a model, and how to ask for results. But it’s not an abstract art: just a few years after the emergence of generative models, hundreds of scientific articles have already been written on the subject. Fortunately, on February 5, 2024, an excellent review of these articles was published. It is about 8 pages long, easy to read, but we realize it’s not for everyone! So, we thought of extracting the 6 most important techniques and adding some examples.

1. Zero-Shot Prompting: The most immediate use. It’s a bit like walking into a room where there’s an intern and asking them a point-blank question. You present the model with a task it has never seen before, without any examples, and it uses what it already knows to make a guess. For instance, you could ask an AI: “What is the best cold brew coffee on the market?” without ever having taught the model anything about coffee, extraction methods, and how humans appreciate good flavors.

2. Few-Shot Prompting: This is like giving the AI a little help. Instead of sending it blindly into the task, you provide some examples to help it understand what you’re looking for. Say you’re teaching the AI animal sounds. You might say: “A dog goes ‘woof,’ a cat goes ‘meow,’ what does a cow do?” With these few examples, the AI grasps the concept and can respond: “A cow goes ‘moo’.” This technique is, in our opinion, essential. Providing examples to the model infinitely improves the responses.

3. Chain of Thought Prompting (CoT): Sometimes, problems require a bit of step-by-step reflection. CoT is like encouraging the AI to think out loud as it solves a problem. Imagine a complex math problem like: “If you have 5 apples and you give away 2, how many do you have left?” You wouldn’t believe it, but adding “Break down the problem and reason step by step” allows the model to perform calculations it otherwise wouldn’t.

4. Retrieval-Augmented Generation (RAG): It’s not exactly prompt engineering, but we can’t help but mention it. Have you ever used a cheat sheet during a test? That’s RAG for AI. Faced with a question, the AI pulls in extra information from a vast database to enrich its answer. So, if you ask: “Who was the first person on the moon?” the AI might pull in extra details about the Apollo 11 mission to give you a more comprehensive answer.

5. Self-Consistency: This technique is like double-checking your work in a test to make sure the answers are consistent. You tell the model to generate multiple answers to a problem, and then compare them to find the most coherent solution. So, if it’s solving a riddle, it might propose several hypotheses and then focus on the one that makes the most sense based on what it knows.

6. Be kind: This means you should always say “Please” when asking and “Thank you. Could you now…” when re-asking. This technique actually is not in the review—it comes from my gramma. But, believe it or not, we noticed that it works also with GPTs, not just people!

Happy prompting everyone!

AI and Us

Have you ever noticed how quickly our world has changed with technology? One day we were talking with Nokia phones, the next everyone was posting on Instagram and the like. And the next big change might just be AI, or Artificial Intelligence.

The question is: should we be happy that AI is entering our lives, or should we eye it suspiciously from across the room?

AI is certainly the ideal helper when it comes to chatting and sharing interesting things. It can hold onto a mountain of information and find what we need in a few moments. Generative AI can now even read and digest for us. That’s why in the book The Amazing Journey of Reason, written by Mario Alemi, the co-founder of MrCall, we find the idea that human society is increasingly transforming into a network of brains connected by digital synapses. We as a species as a whole are becoming smarter because we are getting better at saving a trace of what we know and sharing it, just like neurons do in our brain, and proteins in our cells.

But there’s a problem – AI doesn’t intimately understand being human. It doesn’t understand, for example, our jokes, our dreams, or why so many people love kitten videos (we don’t understand that either…). That’s why we need to treat AI as a team project: involve thinkers, artists, and emotional people – not just technicians – to ensure that AI doesn’t become a party crasher. Otherwise, AI could become like an autoimmune disease, mistakenly attacking the very entity that produced it and was designed to protect it. This metaphor serves as a reminder to align AI’s capabilities with humanity’s wellbeing rather than its potential harm.

Let’s say AI should be like our right hand, not the other way around. It shouldn’t be humans “training” algorithms with “likes” and “dislikes” to teach them which image sells more (it’s always the kittens in the end).

Otherwise, we risk ending up chatting with bots instead of other humans. AI is like any other powerful tool – to be handled with care.

So, what’s the situation? It’s really up to us to decide – AI is like a river. Channeled correctly, rivers have nourished civilizations, empowered communities, and created pathways to unexplored knowledge. But if left unchecked, rivers can flood and irreparably damage the very city they made great.

It should be our hands, and not just those invisible ones of the market, guiding the development of such powerful technologies. Nuclear energy has brought well-being where it has been used well, but disasters where it has been used poorly. And missed wealth where it has been rejected.

From Fire to Generative Artificial Intelligence

From the time our ancestors discovered fire to today’s solar and nuclear power plants, we have witnessed energy revolutions that have fueled human progress. But that’s not all: there have also been information revolutions – from the birth of language to writing, from printing to telephony, and, of course, the internet.

Now here we are, in the midst of the web era, overwhelmed as if by a raging river. Our daily life, our species, our society, everything has changed. It hasn’t even been two decades, and we’ve gone from not knowing whether it was summer or winter in Brazil to being constantly informed about what’s happening on the other side of the world. In the end, we feel it close, as if it were right next to us. The world has become small, and perhaps a little better, despite everything. Yes, with ups and downs…

But there’s more. Illiteracy is becoming a thing of the past, and with it, population growth is slowing down. Women are studying, working, and the world, step by step, seems to be moving towards a slightly more sustainable future.

But there’s something that’s growing and getting worse: digital bureaucracy. Yes, that dark forest of rules, numbers, documents, and interfaces that seem to come out of a Kafkaesque nightmare. Who hasn’t cursed the municipal website while trying to pay a fine, right? Worse than the fine itself!

The realm of the absurd: we, the sapiens, with two million years of linguistic evolution behind us, after writing the Odyssey, now find ourselves pressing buttons on glossy screens like neurotic monkeys at the zoo. But, we believe, things are about to change: thanks to Generative Artificial Intelligence.

Did you think Generative Artificial Intelligence would only serve to make us laugh and cry with online content? That too. But the real magic lies in its power to change the way we interact with the digital world. Imagine being able to talk to a database as if it were an old friend. “Give me the addresses of the customers?” Done. And in the blink of an eye, without needing to know SQL.

An agent with Generative Artificial Intelligence could even navigate that awful municipal website for you. No matter how complicated it is: it doesn’t give up in front of a bad interface (but you still have to pay the fine).

And now, the million-dollar question (or rather, billion-dollar): how much is this technology worth? Look at OpenAI: from zero to 90 billion in no time. And Nvidia, with its microchips that run these software, is approaching a capitalization of almost a thousand billion.

A bubble? Maybe. But it might be not. If we think about the astronomical increases in market capitalizations in past years, who can say where we will arrive in a not-too-distant future? OpenAI, Nvidia, or some unknown new player – someone will scale these new heights. And we will be here, perhaps more neurotic, perhaps less, but certainly more connected to our digital world.

Artificial Intelligence and the Interface

As (almost) everyone knows, the first artificial intelligence program was created by Herbert Simon in the 1950s, who won the Nobel Prize for… economics about twenty years later!

In his book “The Sciences of the Artificial,” Simon writes:

An artifact [the artificial] can be thought of as a meeting point—an “interface” in today’s terms— between an “inner” environment … and an “outer” environment …

Considering that the software he wrote with others in 1956, the Logic Theorist, proved theorems of logic, this seems strange. Yet today more than ever, it is clear how right Simon was.

More than ever today, with arrival of generative artificial intelligence, the technology behind ChatGPT and company. Have a look at the latest article of your favourite influencer and…. GPT is so intelligent! So much more than just an interface, it understands!

Yes, it behaves intelligently—but so does a car that accelerates and brakes on its own. Nonetheless, we don’t call the miracle, nor the sapiens-machine singularity.

The intelligence we see in AI today is not really its own – AI is more like a puppet that shows the cunning of those who pull the strings. Those hundreds of millions of dollars spent by OpenAI for ChatGPT? They were used to pay 1000s people to teach it how to behave intelligently. Basically, GPT-4 on its own is just very good at playing with words, but it doesn’t really understand them.

This brings us back to Simon and the artificial seen as an interface between its internal world (the digital) and ours (the analog). Think of generative AI as a fantastic gadget that sits between us and our technological tools. If used well, it will do an excellent job in helping us use digital tools.

Generative Artificial Intelligence, in our opinion, will explode as an intermediary between the Sapiens and the digital world. Put a bit technically, to translate requests made in natural language into programmatic languages and vice versa. For software, understanding “I would like to come on November 9th at 10:15” is not trivial. On the contrary, for a language model like GPT, it is easy—as it is easy for it to translate it into a “computer format,” i.e., asking for the year (which it does not know) and generating 2024-11-09T10:15:00+02, which means the same thing but every developer can easily use in their own software code. This is the interface!

For now, we use models like GPT in this way. We take them for what they know best: interpret language. The result? Useful software. Which doesn’t get lost in chatter but tries to solve the problem in the best possible way.

Trustworthy Artificial Intelligence—Our Vision

The fascinating world of data analysis has progressed leaps and bounds, with every bit of the digital sphere becoming a potential goldmine of insights. In politics, it has re-written the rules of engagement and redrawing the battle lines in many instances.

Two prominent examples, Brexit and the election of Donald Trump, exemplify the profound implications that the intersection of Artificial Intelligence, social media, and politics can bring about.

To begin with, the case of Brexit provides an enlightening illustration. The decision of the UK to exit the European Union was a significant political and economic event with global repercussions. It may seem that the vote was purely a democratic expression of the will of the British people. However, the exploitation of data produced by social media platforms in this saga is a factor that can’t be underestimated.

Algorithms trawled through enormous amounts of data to identify patterns. These algorithms were the product of a specialised field that combines computer science with psychology, economics, and sociology. Using this information, as Cambridge Analitica proudly touted to every one (they defined themselves a “global election management agency“), political strategists were able to target users with tailored content that played upon their fears, aspirations, and biases.

This gave birth to the phenomenon of Fake News. People were targeted with skewed or outright false narratives about the European Union, designed to fuel Euroscepticism. These messages were cleverly designed to resonate with individuals’ existing views and fears, making them more likely to vote ‘Leave.’

Similar tactics were witnessed during the 2016 U.S. presidential elections, which led to the victory of Donald Trump. Here, the plot thickened with the alleged involvement of foreign powers. Accusations were made about an army of social media bots, created and controlled by foreign entities, designed to flood American social media platforms with propaganda and disinformation. These bots exploited the divisions in American society, sowing confusion, discord, and distrust.

The episode serves as a warning about the potential abuse of artificial intelligence and social media in political contexts.

These cases point to a potential danger that looms in the future: the prospect of an Artificial Intelligence agent with the capability to influence each voter individually. Imagine a software so advanced that it could craft the perfect argument to sway every single voter. Such an AI could manipulate voters into supporting a candidate not on the basis of their policies or merits but based on its capacity to tap into their fears and desires.

This raises the spectre of a potential ‘strong (wo)man’ figure, reminiscent of past fascist dictators such as Mussolini or Hitler. Such an individual could potentially exploit this AI capability to manipulate public opinion on an unprecedented scale. They could bend the will of the masses to their liking, undermining the very basis of democratic decision-making. In essence, democracy could be hijacked by a powerful AI tool and its unscrupulous handlers.

The idea of a manipulative AI is not purely speculative anymore. The leaps in technological advancements we are witnessing and the existing examples of technology’s role in manipulating public opinion make it a possibility that we can’t afford to ignore.

Unregulated Artificial Intelligence shown its ability to manipulate public sentiment and influence democratic outcomes, as seen in the Brexit referendum and the 2016 U.S. Presidential election. They have demonstrated their capacity to be used as vectors for misinformation and propaganda.

While the World Wide Web promised more informed and engaged citizens,  its conubium with Artificial Intelligence and free-style capitalism gave birth to a three-head Cerberus leading our global society into a dystopian society where a non-sentient (sorry Google Bart) machine will, in the end, control us.

In the face of such threats, it’s crucial to cultivate a digital ecosystem that champions truth, transparency, and integrity. This includes regulations on the use of personal data, stringent fact-checking mechanisms to combat misinformation, and public education on digital literacy. Technological advances in AI must be matched with equal progress in ethical guidelines and accountability mechanisms to prevent misuse.

The digital revolution which started more than 50 years ago with the creation of a network of computers, the Internet, still holds vast potential to enhance democratic processes. However, without appropriate checks and balances, these same tools can become threats to the very ideals they promise to uphold. As we move further into this new frontier, our challenge lies in harnessing the power of these technologies while safeguarding the principles of democracy.

This isn’t just the responsibility of policymakers: first and foremost, it’s the responsibility of people, like us, who are developing products based on Artificial Intelligence.

MrCall—The Many Features of an AI Answering System

We built MrCall as a truly innovative Artificial Intelligence (AI) Answering System. And for us, an intelligent system must learn alone, this is why the service works immediately, without the need for complicated configurations. MrCall is smart enough to go to the internet and learn about your business. Nonetheless, if you want to personalise the assistant a bit more… well, you can personalise practically everything!

No need to thank us, it’s all included in the package.

Basic configurations

Which sector does the activity belong to?

First of all, let’s establish which branch you are operating in—the sector of your activity. You could choose “Health”, for example, if your practice is dental or veterinary, or “Property Management”. Of course, you can opt for the “General Business” category, but specifying the sector allows MrCall to understand if it should expect requests such as “I want to cancel an appointment” (for studios) or “I want to book a room” (for hotels). After all, accuracy is the courtesy of masters.

The assistant’s voice

You can then decide whether you want a male or female voice. It doesn’t matter if it’s a man or a woman answering your requests, the important thing is that the assistant always behaves impeccably. So take all the time you need to reflect on this difficult decision.

Welcome messages

First interaction…

MrCall is not the usual boring answering machine that reads the same standard message. No—that’s why we call it an AI answering system! MrCall creates a personalised welcome message based on the situation it finds itself in.

First of all, MrCall knows that you can’t go wrong with greetings. So, depending on the time of the day, it will give you the “Good morning”, “Good afternoon” or “Good evening” you deserve.

But it doesn’t end there: if someone call to find out if you are open or closed, MrCall checks Google My Business for you and responds accordingly. And to loyal customers, those who always call, MrCall recognises them by name and can’t resist saying, “Nice to hear from you again!”.

Don’t think there are only automatisms: you can choose how to present your business and decide on the closure of the welcome message. In addition, MrCall knows how to provide the right information at the right time.

But wait, there’s more! If the mysterious type with a hidden number calls you, MrCall won’t judge, but will kindly inform them that if they want to be contacted again, they will have to leave a phone number.

Who wouldn’t want MrCall as their answering machine? It’s like having your own personal assistant!

… successive interactions

If the interlocutor is kind enough to leave a message, MrCall is ready to act impeccably.

If they want to be called back, MrCall will immediately communicate that the request will be forwarded to the appropriate person. If instead the caller wants to schedule an appointment, no worries, MrCall will do everything necessary to assist them.

In addition, if the caller wants to speak with an operator, and MrCall is authorised to do so, MrCall will promptly and kindly inform them that they will be transferred to a professional who can assist them. But if the caller is in too much of a hurry to wait, MrCall will do their best to gather all the necessary information and send it to the appropriate department.

And if the caller asks to speak with a human being, but MrCall cannot forward the call, no problem! MrCall is always ready to respond with an elegant and personalised answer to let the caller know that the request cannot be fulfilled.

In short, MrCall is a true telephone professional, ready to listen, answer, and solve any problem. After the second message, MrCall will always respond appropriately and with a virtual smile, promptly greeting the customer.

Sync Your Contacts

What a magnificent world it would be if we could synchronise our contacts with MrCall through the MrCall iOS or MrCall Android app. Well, it’s just like that! On the main screen of the app, just click on Sync Contacts. MrCall will take care of them like WhatsApp or any other similar application. And if MrCall finds a person’s name in the “First Name” or “Last Name” fields, then he will use it! But what happens if I want MrCall to address my magnificent notary with a particular title like… well, like “Magnificent Notary”? No worries, just enter it in the “Nickname” field – edit the contact on your phone and click on “Add field”. What a brilliant solution, isn’t it?

Does MrCall call my contacts by name?

MrCall responds personally only on two occasions: when his interlocutor introduces themselves for the second time and has previously provided their name to our attentive assistant (regarding calls from fixed lines, which can sometimes be shared by multiple individuals, it will be our responsibility to advise MrCall not to take note of the names of the callers); or when the contacts have been synchronised with the mobile app, as described above.

How to activate my AI Answering System?

Thanks to MrCall, you can have a public phone number and allow people to talk to him when you are not available, or maybe you just want an assistant to handle your calls… Here are three options to choose from:

If you have a landline and want MrCall to act as an “advanced answering machine,” you can activate call forwarding from your number to the assistant’s number in case you don’t answer. It’s as simple as drinking a glass of water (or a cold brew if you’re more sophisticated).

Are you a professional with a VoIP switchboard? Then you can connect MrCall to an extension in your switchboard, so you have maximum control over the incoming calls. You can decide to forward calls only during closing hours or only to certain extensions. With providers like 3CX, all this is possible: just contact support and they will tell you how to do it.

If you want your customers to call MrCall directly because you have assigned him a toll-free number or migrated your old number, there is nothing to activate. Just advertise the assistant’s number and you’re done. If your switchboard does not allow you to connect MrCall to a network extension, no problem! You can tell the assistant that the calling number is hidden and configure it so that it extracts the number from the message: Extract the phone number from the message. If it has received the first message without a phone number, MrCall reminds the caller of the importance of providing a contact number to be called back.

Unparalleled kindness and courtesy, but also common sense.

Information on managed calls

Have you ever wanted to know who is calling you without answering the phone? MrCall offers a notification service that not only sends you the call recording but also a formatted transcription to meet your needs. Imagine being a restaurant and receiving a reservation. Here’s the notification:

New booking from Anna:
📅 June 14th 🕰 8:45 pm, 👥 2

A little old-fashioned but clear, right?

Notifications can be received via the MrCall Mobile App for iOS and Android, via email, WhatsApp, or SMS. The mobile app is secure and economical, but if you prefer email notifications, you can use this option to send notifications to multiple people or third-party systems. WhatsApp notifications, on the other hand, are very convenient because they do not require the installation of the app by collaborators and allow you to reach a wider audience than emails, which are often ignored. The SMS option, on the other hand, is activated only on request and is rarely used.

Both through the mobile app and via email, you will see a message with a link that will allow you to send a message to the person who called you via WhatsApp. If you have the app or WhatsApp Web, clicking on the link will open the app and you can send a pre-populated message Send Whatsapp Message to Caller, which you can customize as you like. In short, thanks to MrCall, you will never miss an important call again and you can manage your notifications intelligently.

Having calls forwarded by MrCall

What kind of assistant would MrCall be if he didn’t forward calls? Surely we could not call it an AI answering system… Well, he does, and in a decidedly intelligent way too! Just access the Enable Call Transfer section. You can ask MrCall to forward calls only during opening hours, always, or only if requested. During closing hours, like a true professional, he could simply say that he is not authorised.

MrCall will take care of adding the customary phrases: “If you stay on the line after leaving a message, I will put you in touch with an operator,” and then “Please hold the line…”.

The forwarding can be done through two channels: you can choose between a telephone number or VoIP (the only supported operator is MrCall, as you can imagine). And if you opt for VoIP, not only can you make calls from your assistant’s number, but you can also forward calls to multiple people simultaneously. How? Simply by installing an app that acts as a SIP client and receiving the call, with the first one to answer winning.

Any SIP app will do, for now, we have tried Zopier (Android, iOS, Windows, Mac, Linux) or SessionTalk (Windows, iOS, Android), and they both seem to work perfectly. Just make an appointment with MrCall customer service, and you will receive the credentials to register.

How the AI Answering System Interacts with Your Customers

Of course, knowing who called you is important. But it’s just as important for the person who called you to know that they didn’t leave a secret message in the cosmic void. That’s why MrCall’s mission is to build a communication bridge between you and your customers so that information can flow freely in both directions!

To accomplish this noble mission, MrCall is ready to assist you in communicating with your customers and anyone else who has contacted you in any possible way…

SMS and WhatsApp messages to callers Messages to the caller can be sent through WhatsApp or SMS, and soon through MrCall itself: yes, if the person who called you has MrCall, why not use MrCall 🙂?

And not only that: you can choose between two types of messages. One for those who have interacted with the assistant and another for those who interrupted the call when the assistant started talking. For example, a caller who left a message could receive a message like: “Thank you for leaving a message. We will contact you soon. Remember that you can schedule or change appointments on our fantastic website”. But if they didn’t interact with the assistant, they could receive a message like: “Thank you for calling. If you want to be contacted again, leave a message for the assistant, and we will get back to you as soon as possible”. (Yes, some people are too popular to be able to call everyone back…)

There is a third type of message for those who have made an appointment or reservation. In that case, MrCall sends a message with all the information you need. It’s practically like having a personal assistant always at your disposal!

Oh, one last thing: if you decide to use WhatsApp, you can choose between Meta’s official APIs (more expensive, less flexible but secure) or unofficial ones (more convenient, but at the risk of the number being blocked if notifications become too frequent). The choice is yours!

Integration with third-party systems

If you are eager to let your customer management systems know that they have just received a call – who can blame you? Here are some ways to go about it:

If the system supports REST calls (and if it doesn’t but you don’t know what it is, search for “Developer API” on the provider’s website), then you can send all the information about the call through MrCall’s Web-hook Integration option. Easy.

If, on the other hand, the system already has a Zapier connection (which, for those who don’t know, is a platform that facilitates the connection between two systems that use REST APIs), then you’re in luck. You can connect MrCall to the system in no time.

Finally, if you think that integrating MrCall with your system could be useful to others as well, then you can make an appointment with MrCall customer service and discuss it. How elegant.

The long, hot summer of MrCall

A new user of ours told us on the first phone call: “But where were you? I’ve been looking for you for years…”

Those are heart-warming statements, 🙂

For seaside resorts and water parks, summer is a time of business, but a source of stress: many centres easily exceed 50 calls a day, often reaching 100. The telephone in practice becomes the victim of its own success: the operators of the centre either work or answer the phone. But the conundrum is: if you don’t answer the phone you risk alienating potential customers, and if you answer and don’t work, you alienate actual customers.

The solution is in human psychology. As people in the sector say: often people call to ask the most senseless questions, and to answer 90% of the calls a responder with a pre-recorded message would be enough. But the remaining 10%? Do we want to throw the baby with the bathwater?

No, and that is why many centres use MrCall!

Here’s how summer camps using MrCall set up their assistant:

  1. The calls are all immediately forwarded to MrCall, who welcomes you with a fairly long message, explaining the center’s rules as much as possible, and announcing that a Whatsapp message has been sent to the caller with further explanations and links for various bookings
  2. MrCall notifies the center only when the caller has said something to MrCall. Given the length of the greeting message, typically we are talking about 10% of callers. And the good news is that MrCall only counts calls with messages for the subscription!
  3. MrCall then sends a Whatsapp message to the caller, different depending on whether or not the caller has interacted with him/her (the service costs €4.88 per month with an unlimited number of messages)

That’s all. Of the approximately 1,000 calls a month, only about a hundred pass the filter and are processed by the centre’s administration—an average of 3 a month, in short, more than acceptable.

MrCall goes to the Gym

At MrCall, we’re not just here to sip cold brew coffee (although that is a perk of the job). We’re problem solvers, and we’ll chat with you over coffee to make sure our solution fits your needs. Just ask Alessio Rinelli, owner of Reverbia Personal Trainer Milan..

Reverbia is a growing business with six centers in Milan. The trainers and clients stay connected through smartphones, but sometimes calls go unanswered, leaving potential customers hanging. And that’s not cool.

But fear not! We’ve got a clever trick up our sleeves. The phones in all six centers have a “conditional” call forwarding to the same MrCall assistant. If no one picks up, the call goes straight to us.

We’ve also got an online call log that tracks every call, even the missed ones. The caller can leave a message and wait on the line to speak with an operator. If they’re just canceling a reservation, they’ll say their piece and hang up. But if they’re a potential customer, they’ll give us their name and wait to talk to an operator.

The operator jots down what happened in the call log, so we can keep track of every lead. And just like that, missed calls turn into leads, which can turn into new customers. We call that a win-win.

MrCall loves restaurants

Ah, restaurants! They may only account for a mere 10% of our MrCall users, but they’re a vital sector to us nonetheless. After all, without them, where would we stuff our mouth with delicious food?

Our close collaborator, the Carbonara reservation system, can attest to our dedication to the HoReCa sector. And as if that weren’t enough, we even have some first-hand experience dealing with the trials and tribulations of restaurant operators. We’ve seen the long hours, the finicky customers, and the stress that comes with it all.

So we’ve gone ahead and studied how different restaurants make use of MrCall. Yes, you heard that right—we actually did some research. And what did we find, you ask? Well, keep reading and you shall see.

MrCall “reservation clerk”

In 50% of the restaurants under our umbrella, this life-changing assistant is nothing short of a real person answering the phone to take reservations. Brace yourselves for this highly complex, multi-step process:

Firstly, the caller will be greeted by MrCall’s soothing voice and given the option to either leave a message or confirm their booking. Should they choose the latter, MrCall will diligently take note of all the important details such as date, time and the number of people attending.

Next, MrCall will notify the restaurant through a variety of high-tech channels, such as the MrCall app (available on Android or iOS for free!), email (also free!) or if you’re feeling fancy, WhatsApp (for only €3.66 per month).

But wait, there’s more! For a small additional fee of €4.88 per month, MrCall can even send a WhatsApp message to the caller with the booking details, kindly reminding them that the booking is not yet confirmed.

Finally, the ball is back in the restaurant’s court to either call the customer back or send a pre-compiled message (that’s right, they don’t even have to type out the confirmation message themselves!) via the email/app notification. So easy, a caveman could do it!

Thank you, MrCall, for revolutionising the way we make restaurant reservations.

MrCall, the Lead Generator

Ah, the joys of missed calls – we’ve all been there. But fear not, dear restaurateurs! Enter MrCall, your trusty sidekick for lead generation. No longer shall those precious contacts be lost in the abyss of unanswered phone calls.

With MrCall, customers can leave a message to be relayed to the restaurant, along with a friendly reminder that reservations are preferred on the website. And for those technologically-challenged customers (shoutout to the 80-year-old lady who still calls to book a table), MrCall’s got your back – they’ll transcribe and send everything to the restaurant on your behalf.

And the best part? MrCall sends notifications to the restaurant via app, email, and Whatsapp, ensuring not a single lead slips through the cracks. And as the cherry on top, they even send the customer a Whatsapp with all the necessary instructions on how to make that coveted reservation.

So sit back, relax, and let MrCall do the heavy lifting for you. After all, why waste time and energy answering calls when you could be cooking up a storm in the kitchen?

MrCall, the Call Center Operator”

Ah, the remaining users of MrCall—those restaurant chains and customer service-centric eateries. They’re quite fancy, really. They have their own person just for answering the phone! How quaint.

MrCall, always the polite one, offers a warm welcome message asking for the caller’s name and reason for ringing up. During the receptionist’s shifts, MrCall even kindly gives a heads up that the call is about to be passed along to an actual human being. Fancy, fancy.

And of course, the call is added to a log file—who doesn’t love a good spreadsheet? The receptionist can mark down the outcome of the conversation and others can check in on it.

Now, when it comes to outside of working hours, MrCall doesn’t just sit there twiddling his virtual thumbs. No, no. He interacts with the caller like the polite AI he (or she) is and sends out notifications and WhatsApp messages as usual. Eventually, he’ll mark everything down in the call log for future reference. All in a day’s work for MrCall.


Hot off the press: MrCall is expanding its linguistic horizons with English and Spanish! Claro que  sí compañer@, you read that right!

MrCall, the non-stop phone answering machine, is always at your service, whether you’re too busy or too important to take the call yourself.

Need a helping hand with your business hours? MrCall can greet your callers with a cheery “open for business” or a stoic “closed for the day”. And if your caller is curious about the time, MrCall can whip out their Google My Business skills and report it back in a jiffy.

With their super-sleuthing capabilities, MrCall can tell if you’re a fresh newbie or a seasoned regular, and dish out the appropriate deets.

And if you’re feeling like old-school texting, don’t worry, MrCall’s got your back! It will shoot your caller an SMS

MrCall and VoIP Switchboards

Many companies contact us because they want to use a VoIP PBX, and they are right! At the moment MrCall does not offer VoIP PBXs, but it can be integrated without problems with third-party PBXs.

If you are a company with more than 2-3 people, or even if you are alone, our advice is not to use your mobile phone for work, but to activate one of the many cloud switchboards available, for example 3CX.

With a switchboard at your disposal, plus MrCall, here’s what you can do:

  1. Give your employees a VoIP app. 3CX has their own, while with others you can use Zoiper, which is free.
  2. With the VoIP app, your employees receive calls on an extension of your line, and not on their personal phone number
  3. MrCall can however act as a “first line assistant”: it always answers, asks the reason for the call and records all the information in a file like this. This way you keep track of who is calling and why
  4. After taking the information, MrCall routes the call as you want. That is
    • if you like, it will not forward to anyone during certain hours (i.e. closing hours) but instead just interact and say goodbye
    • send back to the PBX which will try to probe the availability of the various operators in cascade
  5. MrCall can also simply answer only when no one answers, i.e. act as an emergency assistant who takes charge of the call and then sends notifications with the transcript to whoever you want
  6. In addition, MrCall can send the call data to any system that provides APIs (if you have a CRM: for example all calls can create a deal on Pipedrive)
  7. Dulcis in fundo, you can send personalised messages to those who call you via SMS or Whatsapp

PS We’ll let you in on a secret: MrCall is also a PBX. If you call your assistant’s number, the call goes to one of our switchboards (heavily customised with the help of our partner Centralix) which transforms the call, a 120-year-old technology, into an IP audio stream, where IP stands for Internet Protocol, a technology born 50 years ago but, we can say, still quite in vogue 🙂