Back to blog

How Much Does It Cost To Build A Chatbot In 2019?

I used to be asked about it several times a week by clients who want to understand the business of chatbot creation. The price really depends on the effort required to build the bot, as we don’t sell pre-made chatbot templates.

Spoiler alert: it will take between $200 USD to $15k USD to build a single chatbot. If we’re building the chatbot platform, or self-made data science is required, the price could be even higher.

So, let’s take a look at the key drivers impacting the price for custom chatbot development.

  The first one is the channel in which the bot should function. I mean where the bot will actually do its work. Is it a website, SMS, some of the existing messaging platforms? The cheapest ones are FB, Telegram, Viber, Web and others when it’s possible to use the platform UI components to make rule-based conversations. There are even plenty of FREE FB chatbots templates. Here’s an example https://templates.botstar.com/. In reality, it will be required to customize such a template a little, so that’s why the minimum price for a chatbot is about 200 bucks.  More complexity comes when the bot for WhatsApp or SMS is required to be built. It means that there are no UI controls and additional effort will be required to train the bot and fix all possible flows of the conversation. Such bots are starting from around $1000 USD.

The next point that has to be considered is the complexity of the conversation. That relates to  a) the number of branches in the conversation tree as well as b) the number of questions that have to be addressed by the chatbot (in case of FAQ chatbot) and c) the need to support the unstructured dialog with the end user. Training the bot to support several hundred FAQs will require an additional thousand USD. Free based conversations will also add about 500 USD to the price list. While structured conversations will not impact the chatbot cost significantly. Some bots could have a specific task related to the use of Artificial Intelligence. We’ve had requests to understand dreams and automate confession. That’s a separate task which requires corresponding data sets and the training of machine learning models. It’s hard to estimate the price here, but that kind of bot will cost from $10k USD and more. On the other hand, the bot could be made more intelligent while enriching with sentiment analysis, which does not require being built from scratch and is available via API (that is an additional 500 for projects)

Bots are rarely working in isolation, so in most of cases, integration with back-end systems is required. Typically, chatbots are integrated with a CRM, ticketing, live agent solutions or some other business specific solution. You would need to account for $1k-2k USD for each such integration.

Bots are very language sensitive, everything is pretty much in English. It’s widely supported by all the vendors. It’s also fine with the major European languages such as French, German and Spanish. But what about others, and even non-European languages? That’s a more complicated story. If one of the trusted providers has the support of your language, then it makes sense to invest in custom bot development. Otherwise, I would not even recommend doing that if your bot requires any bit of an AI component.

 

I would also recommend that you look at my blogpost related to the total cost of ownership for a chatbot solution and the criteria for selecting a chatbot development provider.  

Back to blog

6 Types for Chatbots: Know Which One Brings Value to Your Business

In 2019, chatbots have a variety of capabilities and more than just one type just might be suitable for you.

It’s good practice to define what is the role of your bot, measure the value and compare it with existing services before the chatbot launches in the business. If the chatbot could solve the issues, set up better customer engagement or improve internal communication. It’s the right decision to begin its development.

We identified 6 possible business roles for a chatbot, depending on which function they serve:

  • Sales
  • Lead generator
  • Interface
  • Informant
  • Helper
  • Psychologist

As mentioned above, each bot could take on several business roles, so we are using this classification just to create a common language and definitions of chatbot practitioners.

A chatbot increases sales and cross-selling

Sales Chatbot is responsible for increasing sales. It has several ways of functioning. The chatbot could choose the right service or good, create the invoice, make a payment (need to be connected to appropriate API), track orders, push notification about payment status, and conduct cross-selling. Sounds kind of like this chatbot could help to grow your biz, eh?

A chatbot generates leads for your CRM system

The main purpose of this chatbot is to gather together the target audience in one channel and convert them all into the clients. It could work in combination with an informant role, for example. How does the chatbot behave? The chatbots can provide the following services: make an appointment, creating a loyalty card (discounts, special offers, coupons, promo codes, and more).

On the vendor side, the chatbot gathers all the appropriate information useful for creating advertising campaigns or special offers. Also, the chatbot can maintain the communities with content to keep a particular audience interested in the services.

A chatbot acts as an interface for engagement with clients

Chatbot interface gives access to other system functions. It accepts and processes the information, integrates with the company services through the API and passes a long the collected information.

If needs be, the chatbot authorizes the user by itself. Following engagement with the website services, the chatbot distributes the processed results.

A chatbot informs the customer of the available services

Informant makes the data search quickly and easily. The Chatbot could aggregate information from different sources and conduct push notifications to the user about changes in the interested services. It’s one of the most attractive options for your business.

A chatbot helps the customer

The Informant makes a data search quick and easy. The Chatbot could aggregate information from different sources and conduct push notifications to the user about changes in the interested services.

A chatbot acts as a psychologist

A Psychologist chatbot’s main value is a conversation with the user. It recognizes the user’s mood, problem and offers methods (probably yours) to avoid the stress, suicide, offers appropriate specialist, and play as a lead generator – bringing a new client to a psychologist.

Experience shows,  the right chatbot is one of the main values you can offer your clients, making them satisfied, so you get a chance to make a quick profit.

 

If you have doubts as to choosing the right chatbot, check out its possibilities in a variety of industries (click button “I don’t know what kind of bot you need”).

If you want to have a full list of chatbot values, customized for your business, contact us and we will describe all the ways on how to bring value with a chatbot!

Back to blog

Chatbots in 2019: Predictions and Major Trends for Business

AI chatbots were everywhere if one were going by all the hype in 2016. Everyone who is involved in technology wants to be in on the know for what to expect next year and how chatbots will change the world.

Ever curious, I peeked into my crystal ball and checked out the current trends for chatbot development and business implementation, noticed that there are no significant changes expected in Artificial Intelligence. However, we will observe new landmarks that will change some aspects of chatbot development and business implementation. Without further ado, let’s consider the major new trends for the upcoming year!

Raising automated chatbot testing

Chatbots’ complexity is growing more and more each year. Full stop.

The real example being that bots are getting ever more intense. Now, it is not surprising to build a project which has about 100 intents and the complexity of conversation itself is 100s of decisions and condition points in the dialog.

You always should maintain a real case scenario to have to keep your bot updated. Also add new intents, new synonyms, branches in the conversation to save bot smart and usable. So the key question is: how do you ensure that everything is working in tip-top shape?.

We predict the rise of automated bots solutions. This you will enable you to automatically test a bot’s dialog and NLP.

The rise of bots for internal use for enterprises

Enterprise clients will be the major driver of growth of the chatbot development market. In many cases, the companies failed to onboard customers for their bots which are working out of these organizations. But the enterprises have a power for employees to use bots for internal purposes. That will be the key driver for market goals next year.

The main scenarios for enterprise bots would be the cases for sales personnel, HR interactions. But the question arose, “What is the main reason for using bots for automation business processes and instructions for enterprises?” The key driver is the cheaper cost of bots development comparing with mobile app development. That will cause the intensive growth of bots in the enterprises.

NLP and bot constructors will become the commodity

In ChatbotSummit, I recently saw dozen of solutions which actually do the same thing: NLP, NLU, building conversations in an easy way, integrating with any messaging platform and etc. Mentioned services become a commodity. Every provider seems to be able to provide the same and it becomes a just minimum required standard. There is no significant difference between DialogFlow, IBM Watson, Smooch, Rasa. So it seems many many startups do the same solutions.

The Ice Age of Facebook and WhatsApp will remain

We don’t expect significant changes to happen with Facebook and WhatsApp messengers. We would call it the Ice Age of FB and WA. In 2016 actually, Facebook raised such a huge amount of chatbots and now keeps silent.

My feeling, now it is very busy with solving own privacy security issues rather than development of the messenger platforms. It is major chatbot development companies keep focus for both website bots, SMS bots, mobile apps. In the upcoming year, we will see huge demand in such area comparing to initially expected Facebook messengers.

Data privacy: the doubts of reliability will dispel

Security or data privacy will become more and more relevant for big enterprises. There will be a big concern about letting large players like Google, Amazon or Microsoft own their conversational data.

It means in 2019, will appear more and more solutions to provide on-premise bot building solutions that guarantees data privacy for big companies that are concerned about it.

Most user download zero apps per month — that will drive to build more bots

The key methods for customer engagement are chatbots and mobile applications. Next year we will see that engagement via apps will fail. Actually, no one downloads the apps. No one wants to use up phone memory.

Instead of that, end-customers will engage with your system or buy goods/services via chatbot. Why? Besides the usual services that chatbot provides (push notifications, direct communication), it is a simple way to start/stop engagement without additional actions. It will be a motivation into the next year.

The User support platform includes engines for chatbot or holds the integration

Despite the personal data gathered from applications or bots, it has become the security. So the gathered data is used for improvement and learning AI assistance.

In 2019, people will more and more use an AI chatbot to communicate internal team, arrange own calendars, events, order food, plan vacations etc. It is obvious, the service becomes useful as they learn our habits, speech and in each case can offer a better and better solution.

Back to blog

WhatsApp Business API: Common Questions for Chatbot Implementation

WhatsApp is on everybody’s A-list. It’s nothing new that WhatsApp is on the hype and most companies want to implement the bot into for business. Statistic says, that today messenger has 1.6 Billion monthly active users across 170+ Countries and 80% of messages sent to WhatsApp are seen within 5 minutes compared to the traditional SMS. Looks impressive but there are still a lot of uncovered questions that go on and on.

So, I gathered the most important for development and implementation questions that cover WhatsApp Business API. In the course of creating the article, I also checked Quora questions I’ve previously answered related to the topic. Please check the following list and write the questions you want to know.

WhatsApp bot

 

What is a WhatsApp bot?

For now, the WhatsApp bot seems like a simple AI solution. The bot for this messenger communicates only through text chat and images. Buttons and additional tools are not possible like on other messengers.

How safe are WhatsApp bots?

WhatsApp bots are very safe. Compared with other platforms, WhatsApp bots really encrypt messages. Messages to the WhatsApp server come via encrypted format. Check WhatsApp Availability and Scaling to understand how the service architecture provides this.

How do I build a simple Whatsapp bot?

To create a simple bot for WhatsApp without any additional help you can use the Twilio API that allows one start building and prototyping in a sandbox. Visit Twilio API for WhatsApp to understand how it works.

Is it possible to integrate a chatbot in Whatsapp which replies to my messages?

As mentioned previously, you can already build a bot for WhatsApp. First of all, install and set up the WhatsApp server. Then you will get access to the API that gives the opportunity for a bot to start working.

Warning: the bot will start working if it is created with programming languages but not with cloud platforms.

You can probably integrate a chatbot with WhatsApp but you’ll need to create an integration by yourself.

Launch the following services:

Getting Started — Quick outline of how to get started and next steps

Network Requirements — Network requirements necessary for the WhatsApp Business API client to connect to WhatsApp servers

Phone Number — Verify and register your business’s phone number

Verified Name — Display your business’s name when talking to your customers

Volumes — Securely store WhatsApp data while using Docker

Installation and Upgrading — Installation scripts and guide to get the WhatsApp Business API client running

HTTPS Setup — Set up and use HTTPS endpoints

Users endpoint — Create, manage, and use access tokens and user accounts for additional security

Backup and Restore Settings — How to backup and restore your WhatsApp Business API client

Deploying WhatsApp on AWS — Create an Amazon Web Services cloud to run the WhatsApp Business API client

Rate Limits — WhatsApp Business API endpoint rate limits scenarios

Understanding How to Get Opt-in for WhatsApp — How to present your users with an opt-in for messaging

Postman Collection — Import our WAE Developer Collection into Postman to quickly test the WhatsApp Business API

Then create an integration code with AI WA. Check out API Reference to understand how to build that. Here you find information regarding WhatsApp Business API Root Nodes and example of WhatsApp Business API format uses the contacts node.

How do I create a computer bot that can automatically reply to all our Facebook and Whatsapp messages?

As far as I know, one of the solutions is to use the Twillio API for WhatsApp using a simple REST API. The Twilio API for WhatsApp allows developers to start building and prototyping in a sandbox. In order to launch apps in production, you can request access to enable WhatsApp on your Twilio number. WhatsApp is currently opening up access in a Limited Availability program, where WhatsApp approval is required for all customers who wish to create their own profiles. Check out this link to start work with Twiliio API.

Other platforms, for example, Clare.AI and Hubtype, are still in beta testing. You can use these ones if you have the time when it will be launched.
For now, start learning how to make your bot for WhatsApp using WhatsApp Business API. So, the solution is to learn guidelines and tutorial and develop bot by yourself or pass the work to agencies.

How can I connect a WhatsApp group with a Telegram Group using a bot?

As of now, there isn’t any opportunity to work with groups in WhatsApp, unfortunately. As far as I know, only p2p communication is possible.

How accessible is the WhatsApp API?

WhatsApp API is accessible after branching on servers. Check this Installation and Upgrading to understand how it works in coding.

How can I get Whatsapp API?

First of all, install and update the WhatsApp Business API Client using Docker Compose. Follow all the steps and then you will get the WhatsApp API as you need it.

Make sure you have gotten approval for your business’s phone number and have a Verified Name certificate before attempting installation.

Initial Setup

Before continuing, please read through the other WhatsApp Business API guides.

This guide requires Docker, a container platform that lets you run the WhatsApp Business API Client. Docker Compose is also required. Docker Compose is bundled with Docker for macOS and Windows but requires a separate installation on Linux.

1. Install Docker on your system.
2. If Docker Compose is not bundled with your Docker installation, install it.
3. Download the docker-compose.yml and db.env configuration files: -WhatsApp_Configuration_Files.zip (find it here)
4. Open a console and navigate to the directory where you saved the downloaded files.
5. If you have a MySQL installation running, change the values in the db.env file to reflect your MySQL configuration. If you do not have MySQL installed, the docker-compose.yml and db.env files have a default configuration to bring up an instance in a local container.
6. Run the following command in the console:

docker-compose up

You will get some output, while the script downloads the Docker images and sets everything up. To run the containers in the background, use the -d parameter:

docker-compose up -d

Once you have completed these steps, ensure that the containers are running with the following command:

docker-compose ps

By default, the Web app container will be running on port 9090.

You can download and configure our Postman Collection to easily interact with the WhatsApp Business API.

Refer to the Registration documentation for next steps.

 

Please note that the list could be supplemented by other related questions. If you have anything to add, please share it with us and we’ll include it in the existing list. So, follow me and stay on top of WhatsApp chatbots novelties.

Back to blog

Top Chatbot Benefits: How Bots Make Advertising Campaigns Cheaper

Previously Chatbots.Studio was considering how a bot helps business grow — optimizing information management and automating the work process.

So hold onto your hats, because this article is about how a bot can help decrease the costs of advertising campaigns and how it benefits businesses.

One of the lowest-cost ways of communication with the customer is a bot. Also, marketers increase productivity and save time. The main benefit of using a chatbot has to be the low-cost communication with a customer. Compared with other ways of communications, we can make a serious case that the bot is faster than emailing and smoke signals and cheaper than SMS, which costs about one cent per message in sunny Ukraine. Also, bots provide two-way engagement, mostly without a live agent.

To measure if chatbot implementation provides a cost reduction for an advertising campaign, identify a single metric — the cost of client acquisition.

 

Scenarios for automation advertising campaigns with bot:

  • Bot defines and segments target auditory using ‘ask & answer’ method. The bot asks the customer about preferences and offers the appropriate goods or services;
  • Sends advertising campaigns to customers via a messenger. The Marketer creates articles and the bot takes to sending routine messages on a massive scale to prospects.

 

Let’s consider an example of the first scenario to better understand how it works in real business cases.

The Sephora bot was developed for the beauty industry to help customers find the appropriate goods and let them know about cosmetic novelties. The chatbot handles natural language, asking customers about preferences regarding beauty goods. To decrease the cost of promotion, the bot acts in the following way:

  • Makes quiz — asks questions to gather information and makes suggestions (e.g. age, makeup brand preferences);
  • Scans an image, object or face of a celebrity, for example, and presents a list of matchings lipsticks;
  • Provides ‘how-to’ content. The chatbot showcases life hacks for makeup using their own supplies.

 

The results of chatbot implementation is an 11% higher conversion rate versus any other channel for booking in-store makeover appointments.

Does your chatbot reduce the costs of advertising campaigns and company service promotion as well as the Sephora bot does?

 

Another example of this sort of scenario is the M chatbot that advertises and promotes anything customers need. There is no necessity here to buy expensive tools for email marketing. Just hand the advertising content to the bot.

chatbot M
According to the previous intent, the chatbot M offers goods within the confines advertising

 

To promote goods and services quickly and affordably the bot acts in the following way:

  • Sends messages with ad content automatically and free or cheap;
  • Reaches the target audience directly via a messenger that increases conversion;
  • Offers the goods or services without aggressive advertisement. The customer will get an ad right after he realizes he needs the goods.

The aforementioned chatbot sends messages automatically and free. The B2B customer pays only for bot development.

 

With all that said, chatbots are a complete necessity for the smart business to explore new leads without massive cash outpouring. In the meantime, make them customer make sending offers and keep them loyal to the services you provide.

Back to blog

Top Chatbot Benefits: How Chatbots Automate the Working Process

Chatbots are in high demand because of all the new opportunities for business and customer service. Previously Chatbots.Studio considered the first benefit for businesses, which provides cost reducing — information management optimization. Let’s talk about chatbot efficiency on the automation of working processes.

automation of working processes
Source: https://bit.ly/2CezDTd

 

It is a great chance for entrepreneurs to save money by transferring work tasks over to chatbot and let existing staff concentrate on other important work. A wide range of staff isn’t all that necessary as the work becomes automated. Therefore company profits margins continue to increase with smart team.

I’d like to point out that chatbots aren’t the only way to automate a work routine. Lots of information systems provide the same and sometimes better work automation. However, we will consider how chatbots can take on daily routines from the staff.

chatbots can take on daily routines
Source: https://bit.ly/26zD64P

 

First of all, let’s consider the metrics that measure the effect of automation with chatbots for business:

  • Transactions number executed by one employee;
  • Mistake numbers for one transaction;
  • Timeframes for service providing;
  • Service availability;
  • Client satisfaction.

 

Typical scenarios on how chatbot automates working process:

  • Accepts and handles customer requests. The bot provides consultations, answers on FAQs, and passes the conversation to a live agent;
  • Manages the schedule and queue without personal assistance. The bot accepts and handles new client appointments. Also, it notifies clients about upcoming or past events.

This leads to providing a broad customer service, with always available assistance and quick engagement.

 

Let’s consider some examples of using a bot for automation of working processes according to scenario.

Taking into account our experience, Chatbots.Studio developed the chatbot for the beauty industry that helps make an appointment for a stylist without direct human integration, manages waiting lists, cancels and reschedules appointments and manages stylist availability.

 

How does the bot automate the stylist working process?

  • The stylist doesn’t handle requests from clients. Therefore the stylist doesn’t waste time on appointments and handles more important work;
  • An availability to book services 24/7. A customer can book the service at a convenient time to not disturbing stylist;
  • The stylist doesn’t manage conflicts regarding in the queue. In case of appointment canceling, the bot makes an appointment for a client from the waiting list.

Another one TrackerBot, which tracks orders sent by delivery services like “Ukrposhta”, “Nova Poshta”, “Delivery” and “Meest Express”. Also, delivery bot provides easy to access customer support to resolve any issues quickly.

 

How does bot automate delivery posts staff working process?

Chatbot reduces the workload of call centers solving issues.

  • There is no need to provide support through calls, web or live;
  • The bot handles all FAQs. In case of unexpected question, the bot passes the conversation to a live agent;
  • The bot connects with maps and sends the information regarding the track location to the nearest offices with a work schedule;
  • Bot connects with the backend and presents the costs of delivery.

 

A customer gets the chance, and doesn’t waste time calling support or surfing the Internet for the appropriate information.

As can be seen, businesses can benefit from automation working process with bots. To implement it for businesses correctly, identify metrics of efficiency to get the appropriate results. So, follow me and stay in top of chatbots novelties.

Back to blog

Chatbots for Business: Top Benefits and Success Measurement

Chatbots.Studio is pleased to announce our latest overview digest on how entrepreneurs can benefit from using chatbots for business. How business wins big from bots — is a major buzzing topic in media.

We will describe each benefit structured with financial indicators. The chain of articles with benefits will be published a few times per week here.

We don’t claim that it is the only, comprehensive list of bot benefits, but it’s one that really boosts business.

There are bots which bring a few benefits for business, for example, the lead generator is able to open new sales channels and gather leads. If you notice that your bot doesn’t refer to the benefits we mentioned below, it may well be worth rethinking if your bot does good work.

Take a look at GrowthBot that brings strong value for marketers and sales gathering appropriate leads.

We divided benefits into two groups according to how bots impact the bottomline: cost reduction and profits increase.

Cost reduction includes following benefits for business:

 

Take a look below on how the chatbot automates stylist’s daily work process.

 

Profits increase includes following benefits for business:

  • New sales channels — a chatbot in messenger as new solution to increase revenue;
  • Cross-selling — a chatbot in messenger sales additional services or goods to existing customers.

 

Take a look at Sephora chatbot that offers goods via KiK messenger.

 

The benefits were identified and explored with metrics for each to understand how it impacts the bottom line. We will consider each benefit with examples to understand how it works with specific business cases.

So, follow me on Medium and be among the first to know how chatbots will restart your business and help it quickly grow.

Back to blog

Bring Clients from Offline to Chatbot: Tools and Channels

Our clients implement bots for business to reduce the costs and increase profits. To get results from the bot, there should be a certain number of active users.

The worst thing can happen with entrepreneurs is losing money without results to show for the money spent, which is applicable for chatbots development as well. That’s why, it is important for us not just to develop the bot, but also share knowledge on how to attract clients to bots.

Let’s focus on how to bring client from offline to bot in messenger.

This article contains the following items:

  • Tools for engagement with customers.
  • Link delivery channels.
  • Common mistakes of using QR codes for business.

 

Tool for engagement with customers

A Chatbot can’t start a conversation without a subscription to a channel with a bot. We need to present a link for customers to lead them to the bot.

Let’s take into consideration how to lead the customer, step-by-step to the chatbot. You can use the standard link or embed it into QR codes. The first step is to present the customer the link with bot inappropriate messenger.

PrivatBank embed link with information into QR code.

PrivatBank QR code
PrivatBank QR code

 

The following action is confirming readiness to start chatting with bots.

Use QR codes correctly and embed information you need to get. For example:

  • Shop identification (the place client scanned QR code).
  • Goods/services that client is interested in.
  • The way how the client finds bot.

 

After the client has started to communicate with the bot, the entrepreneur gets the list of benefits. There are leads subscribed to bot, information about Mobile OS, place and date of scanning QR codes, goods or services the clients are interested in. It allows for creating personalized offers, selling additional services and planning out a marketing strategy.

 

Link delivery channels

 

SMS

It is an expensive and cumbersome way to communicate with clients. Let’s see how to benefit sending a link through SMS and just what can go wrong.

Advantages:

  • SMS can cover a wide range of customers from a client database. Conversion rates are up to 10%.
  • No chance to be banned because customer connects with the bot by themselves.
  • The easy way to implement and expand bots for SMS. There are a lot of services for mailing prospects easily, affordably and quickly.

 

Disadvantages:

  • Expensive messages ( about one cent per message in Ukraine).
  • The limited number of characters, which prevents you from good messaging or engagement with any kind of media.
  • Isn’t possible to send big links.

SMS works well to cover a wide range of prospects. However, there is little chance to gather leads to a community because of no info about the preferable messenger.

E-mail

Despite the huge flow of email every day, e-mail marketing provides high open (about 19$%) and click (about 4%) rates. Also it is the great way to personalize a message, at least, you may know prospect name.

To connect customers to chatbot through email, send them a personalized link in the letter with name and services you provide. It is not necessary to know which preferred messenger, because the bot works through the web as well. Email gives the ability to chat with a live agent as well. It is an expensive way to hold the client and sell the service but works quite well.

Posters

Link embed in QR codes may be located on a visible area and takes up a lot of space. Posters cover only a few advertiser’s needs, such us service adv and gathering leads through QR codes to preferable messenger. The benefits for the customer can be a discount or special offer that the customer gets after scanning QR codes.

Poster with QR code placed on visible area.

 

So, as can be seen, posters are effective way to attract the customer from offline to bots.

Price tags

QR codes placed on price tags allow for identifying goods, location and the time where the code was scanned.

Sharp’s QR code
Sharp’s QR code on price tag. Source: https://bit.ly/2Mq9iq8

Offer this value to encourage customer to connect with bot, for example:

  • Personal discount.
  • Mark of goods absence.
  • Report about goods/service bad quality.

 

Common mistakes of using QR codes for business

 

The Messenger isn’t specified.

We faced cases of QR codes without information as to where it leads to. Let the customer know that links lead to the messenger with a bot but not to a mobile application. Additional actions like authorization, providing access to personal data aren’t really that necessary for bots.

QR code with info
The good example of QR code with info where it leads to. Source: https://bit.ly/2nS9uzQ

 

Customers don’t know what they can get from QR codes and bot subscriptions.

Let them know what they can get by scanning the code. For example:

  • Discount card.
  • One-time bonus.
  • Service on a priority basis.
  • Drawing on prices.
QR code with benefits
The good example of QR code with benefits for followers. Source: https://bit.ly/2nVXNbc

No Call to Action

Ask customers to scan the code and connect to a chatbot in the mentioned messenger.

CTA with QR code
The good example of CTA with QR code. Source: https://amzn.to/2N1lLNc

 

We describe only the one tool for how to bring customers from offline to online — link, there are different ways to attract customers to the bots. Find that which works best for you and use it correctly. Also, provide benefits to the customers and encourage them to scan a code and connect with the bots.

Back to blog

The Guide How to Choose Chatbot Development Service Provider

It could look like the selection of a chatbot development service provider for your project, may be similar to the selection of software outsourcing provider, but in reality, it has several peculiarities, which are worth watching.

Focus on chatbot development services

Chatbots and Virtual Assistants are considered to be a hot topic and many custom software development providers are extending their offering with chatbots development. On the one hand, it looks pretty easy to snag a chatbot development trend. On the other, there is a knowledge that comes with expertise. For example:

  •         How to correctly identify intents, train NLP engines and maintain the context of a conversation  
  •         Specifics of each messenger and communication channel, especially related to accounts approval
  •         Best practices for building engaging conversations

So buying a service from the provider that has a focus on chatbot development services, lets you avoid mistakes made by previous clients.

You can easily check if the service provider is, “one-shop-for-all-purposes” or if it’s a dedicated chatbot provider, by looking at their offering on the web sites, checking the agency name (guess with BOTfriends, Chatbots.Studio, Unibot and others with the similar names are doing?) and looking at how companies are marking themselves on listings. For example, there are only two 100% chatbot development providers on the clutch listing.

Proven portfolio and existing chatbots

That is a must – the agency should have a portfolio of working chatbots. Check the website for case studies and ask for a demo in case some of the bots are protected (delivered by subscriptions, require specific permissions to access it and etc.). I would recommend becoming pretty wary if the chatbot development agency can’t demonstrate any sort of live chatbot.

Tools that are used by the company

Some service providers promote their own tools for chatbot development. It has a clear value proposition, as the bot become cheaper and delivery is done quicker when comparing the development of the bot from scratch.

However the client should be careful with such an approach, first of all, you are getting locked in with the chatbot agency and technology, so simply will not be able to find another provider as no one works with their proprietary solution. And second, big players like Google, Amazon, Microsoft, IBM have more endless resources to keep their solution relevant and updated.   

Contribution to the chatbot development community

Chatbots are a relatively new topic, which is rapidly evolving over recent times, so from my perspective, a good chatbot provider should help contribute to the knowledge of the chatbot community. For example, we have a chatbot development methodology, video courses, meetup and internship for the talented developers.

List of chatbot development service providers

Yep, I know that you are not only looking for Chatbots.Studio to be a provider. So without further adieu here is a list of independent ratings where you can find a chatbot development service provider for yourself – Top Chatbot Development Companies.

Back to blog

Why End Users are Frustrated with AI Chatbots and What to Do?

Have you ever met really stupid chatbots, that don’t understand what you want and thus pretend to have Intelligence? I do, and many people I am talking about chatbots have had the same experience.

Error bot
One of my potential clients mentioned, ‘all the bots have been invented to shortcut support costs’ — that’s the impression users could get from a poorly designed chatbot. So why does this happen:
Inflated expectations from AI bots

There’s a lot of buzz about AI chatbots that are mainly presented as robots that could provide a high level of human-like communication. Bots have they own characters and have their faces either human-like or robot-like.

So, a high level of expectations mostly driven by vendors of NLP engines who would love to promote their technology, which is still not that mature. If someone from the vendors is reading this post, could you share examples of general intelligence projects built based on your solutions? And yet clients expect to have true intelligence while talking to the bot.

Incorrect training methodology

AI bots require training. Training means helping a bot better recognize intent and context in which it is running a dialog. Practically a system administrator (NLP, Conversation expert — whatever you want to call him/her) should review the failovers and enhance the rules in NLP engine to better recognize user intents.

And that is the dead loop: on the one hand, you need to have a good corpus conversation to train your NLP engine on the relevant conversations and on the other. On the other, the user will not start talking to your bot until it is good enough and thus you could not get a good enough sense of the conversations.

So, what can be done with all of that?

Actually, there are 2 options:

  • Have better tools and processes
  • Avoid using AI chatbots

 

Better process of AI bot training

That’s something we can do right now without waiting for the big players to update their solutions or making costly investments in data science.

a) Use all of your existing conversations with end clients to train your NLP engine from day one. Whatever you have: call records, mail conversations or queries to live agent to you FB, everything could be used to train your NLP before the day zero.

b) If there is no corpus of historical conversations you can use live agents, who would follow the defined conversation scripts. Once enough training has been provided, you can slowly bring automatic responses.

c) Involving a live agent immediately when the intent is not recognized or a client is not happy with the response.

The approach is costlier but friendlier for end-users and differs from the advertised flow — launch your AI bot and train it once it gets going.

Improving the NLP engines

NLP Engines will also become better and better for example. For example the NLP engines should support common misspellings (which seems not to be the case https://www.quora.com/Natural-Language-Processing-APIs-for-common-misspellings)) work better while there is a growing number of intents in the system. In addition they should self-learn from the all conversations that are in the system (not only in one account) and provide recommendation of what is missing in the bot. I personally have started to lose the difference between NLP engines specially for English, they look almost the same from NLU perspective.

If you read all of that and still have a wiliness to read for another minute, please ask yourself — do I REALLY need an AI chatbot?
  1. Many users expect to get a very specific service from the bot (book an appointment, buy a ticket, issue the order and etc.) they do not expect a bot to handle all possible conversations. It’s like imagine yourself going to the supermarket — do you expect a salesperson to tell jokes or chat with you about Deep Learning? Probably not and the same goes with a bot. In case you can avoid having AI in your bot, why are you making things overly complicated?
  2. NLP for English and Western European Languages is good enough. It’s very much driven by the market demand and nature of the language itself (it is structured), while there is not many (or there are simply not available) engines for other languages, almost nothing exists for Ukrainian. So, what the language carefully before building a AI bot on that language.
  3. You need to have enough conversations to train the bot even from the very beginning. If you do not have a good corpus of conversation, refer to the tricks above or do not do AI bot. Recently one potential client contacted me to build AI FAQ bot for his new real-estate business. I clearly recommended to him to not do that, as lack of conversational data will lead to a poor experience and waste of time and money.

To be honest, there are cases when you need to equip your bot with AI for sure:
  1. The bot interface does not support any buttons. WhatsApp and SMS are the most common examples of that case. You will HAVE to use AI in that case.
  2. There is a lot of content to share with your end-users, so building a bot with the buttons and distinct conversation is not the issue For example, a big FAQ will need to have this kind of scenario.

 

We are building bots in Chatbots.Studio on a daily basis and we are excited about it. The key idea for this article was to help clients make a fully aware decision about the type of chatbot they need. We see each and every day how bots are taking a more prominent role in the digital worlds and it is our shared goal to make it better for our end-clients.

 

I would love to hear your cases and stories about the issues that your are facing while building AI chatbots.

Get a Quote