Back to blog

AI Chatbot for Sales Increasing and Quick Access to Info

Eva is a chain of stores for beauty and care located in Ukraine. The chatbot was launched for quick access to information about the stores.

          Financial Benefit:

Lowering costs for call center maintenance

Increasing of client conversion

Advertising and promotion cost reduction

Clients attraction by showing bonuses in loyalty card

 

          Goals:

Lead generation

Increasing sales

Increasing client loyalty

Increasing client conversion

Reducing costs for live agent department

Reducing workflow for live agent department

Avoiding personal contact with the service department

 

          Features:

FAQs automatically available in messenger

Finding the nearest store

Changing language in chatbot interface

Link to the online stores

Personal phone number recognition

Link to the online stores

Personal phone number recognition

Automation advertising promotion

 

          Technologies:

DialogFlow is an end-to-end, build-once/deploy-everywhere development suite for creating conversational interfaces for websites, mobile applications, popular messaging platforms, and IoT devices.

Corezoid is ta cloud OS that was used to manage chatbots flow and to track users activity

AWS Lambda is a serverless compute service that runs your code in response to events and automatically manages the underlying compute resources for you.

Back to blog

AI Chatbot for The Ukrainian Largest Supermarket Chain

In frames of digitalization of shops chain, one of the biggest Ukrainian supermarkets launched a Facebook Bot. It was created for customer engagement simplification and business process automation. On the first day, the loyalty card was added by 18,000 clients with the chatbot. In only a week, it increased up to 60,000 users who got the card in messenger. The main goal is to avoid the dissemination of plastic cards.
          Financial Benefit:

Advertising and promotion cost reduction

Lowering cost per engagement with the client

Increasing of client conversion

Lowering cost per live agent department keeping

 

          Goals:

Increasing sales

Loyalty card digitalization with a QR code

Service improvement by clients feedback

Simplification of personal engagement with a client

Reducing cost for live agents department

 

          Features:

An online loyalty card is able in Facebook Messenger

Personal phone number recognition

Automation advertising promotion

Finding the nearest store

Changing language in chatbot interface

Link to the online stores

Personal phone number recognition

Automation advertising promotion

 

          Technologies:

DialogFlow – is an end-to-end, build-once/deploy-everywhere development suite for creating conversational interfaces for websites, mobile applications, popular messaging platforms, and IoT devices.

Corezoid –  is ta cloud OS that was used to manage chatbots flow and to track users activity

AWS Lambda – is a serverless compute service that runs your code in response to events and automatically manages the underlying compute resources for you.

varus-chatbot

Back to blog

Chatbot For Online Diagnostics and Sales in Messenger

Recently Yves Rocher Ukraine announced that engagement with clients will be maintained by the new digital tool – chatbot on Facebook Messenger! A virtual assistant will help to find the best care cosmetic. The bot will analyze the users’ answers based on a large-scale information base formed by the brand’s experts and offer specific Yves Rocher products that best meet the needs of customers, skin type and its features. The main chatbot’s aim is to sell more and promote the brand.
          Financial Benefit:

Increasing client conversion

Advertising and promotion cost reducing

Lowering cost per engagement with the client

 

          Goals:

Simplification of personal engagement with a client

Increasing client conversions by offering a personal discount if user share email address

Digitalization of clients engagement

 

          Features:

Online skin or hair diagnostic in messenger

Help in choosing individual care cosmetics

Offering personal discount

Showing actual offers and bonuses

Survey results saving

Choosing the language of communication

 

          Technologies:

Corezoid – is the cloud OS that was used to manage chatbots flow and to track user activity.

Back to blog

AI Chatbot for Queue Management

The clients request was to build a smart appointments management system for american beauty points.  The automated queue management enables a higher level of time utilization and more convenient service for the end customers

          Financial Benefit:

Lowering cost per conversation with a potential client

Lowering cost per live agent department keeping

Increasing stylist time for a service, not for queue management

Increasing revenue by queue management and filling all working hours without declined visits

 

          Goals:

Simplification of service ordering via chatbot

Quick appointment scheduling to the stylist

Queue management to avoid losing time and money

Avoiding any paper notebooks and involving stylist in scheduling

 

          Features:

Complicated AI functionality for scheduling appointment

Request to include phone number to waiting list 

Rescheduling or canceling appointments

Searching the available client just once there is a cancellation

Internal CRM for managing clients

Own calendar management with the ability to setup working hours and blackout dates

 

          Technologies:

AWS Lambda is the computing service from that allows running code without creating, setting up and managing servers. The AWS Lambda helped to place code that provides the addition of stylists’ services name from the database to DialogFlow

AWS API Gateway is a service that allows for creating and maintaining a scalable API service, which can interact with any other Amazon service (Lambda, S3, App running on ec2 instance etc.) in the project.

Node.js is a server-side, asynchronous, event-driven runtime environment, that allows us to build a server-side application using javascript syntax with the most recent ES standards support.

Botkit is the Node.js framework, that has implemented some easy and convenient methods for working with different bot platforms and programming flow of the dialog with complicated business logic and various API integrations support.

DialogFlow the platform is necessary to gather and recognize a client’s intent and produce human-like responses.

PHP API was used to create the backend project portion. It allows us to focus not only on the framework code, but also the business logic.

Back to blog

Chatbot for Home Service Ordering

The chatbot is your personal helper: It finds the best maid or gardener to make your life easy. Embed online payment for client convenience.
          Financial Benefit:

Increasing sales in the channel without live agent support

Increasing of cross-sales

More sales conversations without any extra costs

Reducing costs per every conversation

Reducing costs for the internal staff

 

          Goals:

Simplification of ordering home services

Sales without a live agent

Quick connection with a live agent in case of need

Ability to communicate through all preferred messengers (Facebook Messenger, Slack, Telegram, Twilio)

 

          Features:

24/7 customer service. Even when the customer is in another timezone, he will be served immediately

Ability to connect with a live agent during the conversation

Integration with Stripe for checking and saving payment data

Integration with CMS

Email notification about the client’s request to invite a live agent to the conversation

Location recognition

Integration with the calendar

 

          Technologies:

FlowXO is a complete platform to create, manage and publish your chatbot

DialogFlow is an end-to-end, build-once deploy-everywhere development suite for creating conversational interfaces for websites, mobile applications, popular messaging platforms, and IoT devices.

Back to blog

SMS Chatbot for Engagement with Voters

Project description

The chatbot was built to automate petitions, engagement with senators to get their reply quick and clear. We provided chatbot integration with customer API.

Duration: September – ongoing

petition_bot

Development team

Developers, Project Managers, QA Engineer

What we built

voters_chatbot

The solution includes

Mail messages analyzer to provide responses redirection from senator to citizens.

The services and Frameworks we used

Botkit is a Node.js framework, that has implemented some easy and convenient methods for working with different bot platforms and programming flow of the dialog with complicated business logic and various API integrations support.;

Twilio is the cloud communication platform that was used for SMS mailing;

Node.js + Express.js were used to build backend API for the bot that works in сhat.

voters_chatbot_1

Development process

The first step is creating a queue where the appropriate staff can take the item and start a conversation with the voter. The second step was to gather all the information that the voter answered and send it to the API for storage.

The third step was integration with the mailing system for getting senator’s responses.

Bot architecture

Bot architecture

Technical challenges

We improved the speed of processing item such as the system has queue solution. Throng library allows processing items in parallel.

 

The result
 Users get the solution for how to reach a senator and get his/her answer as soon as possible. It increases citizens’ trust in the senator and the solves thorny issues that people faced.

Back to blog

Web Widget for Knowledge Base

Project description

We created a solution for federated search in the form of chatbots. These chatbots are able to connect with any possible resources and generate the answer.

Duration: 1 month

Development team

3 Node.js Developers, 2 Project Managers

What we built

knowledge_base_bot

The solution includes

The web widget that allows getting identified access to a knowledge base.
Integration with NLP engine that provides recognition of users’ request.

knowledge_base_bot_1

The services and Frameworks we used

Botkit is  the Node.js framework, that has implemented some easy and convenient methods for working with different bot platforms and programming flow of dialogs with complicated business logic and various API integrations support.

jQuery, Native.js is the library was used in the project for creating client side for the widget (chatbot);

Node.js + Express.js were used to build the backend API for the bot that works in сhat.

Development process

First off, we created simple web chatbot and after that connected to the bot service Wit.ai to create API parser to all existing intents – articles title to wit.ai, and train service. Then we created a client-side for chatbot as a widget.

Bot architecture
Bot architecture
The result
The federated search becomes more easily with the chatbot. There are no needs to surf from link to link in search of appropriate information. Chatbot will provide the appropriate answers in a split second.

Back to blog

AI Chatbot for Local Coffee Chain

Project description

The main solution idea is to create closer relationships between coffee lovers and cafe chain representatives. Since the chatbot was launched, clients have simple access to special offers and discounts. Before, this customer can log in with a phone number. When the customer is looking for the nearest cafe, chatbot will propose a few points that are nearby to the client showing Viber maps and moving to Google maps. Also, chatbot presents scored points and helps to understand what value from it customers is having now. If a customer is satisfied or has the offer to improve services, there is a possibility to leave feedback.

The new approach for building chatbot features impressive customization and easy-to-use interface. So, Chatbots.Studio became a provider who helps increase cross sales and improves engagement with the existing customer.

Duration: 2 months.

Development team

Developers, Project Manager QA Engineer.

What we built
2CupsBot
The solution includes

Viber Messenger

The services and Frameworks we used

We selected a set of tools matching our project requirements and client needs.

Viber REST API  + library messaging-api-viber, i18n were used for localization.

Winston and AWS cloudwatch  are monitoring and management services built for developers. In our case, we built logs using the aforementioned tools.

.env lets you customize your individual working environment variables and were used for storage of variables.

Eslint is pluggable and configurable linter tool for identifying and reporting on patterns in JavaScript. In our case, it was used for code formatting.

Aws EC2 is a web service that provides secure, resizable compute capacity in the cloud.

AWS CodeBuilt is a fully managed continuous integration service that compiles source code, runs tests, and produces software packages that are ready to deploy.

AWS CodeDeploy is a fully managed deployment service that automates software deployments to a variety of compute services such as Amazon EC2, AWS Fargate, AWS Lambda, and your on-premises servers.

Node.js + Express.js were used to build backend API for the bot that works in сhat.     

Amazon DynamoDB is a key-value and document database that delivers single-digit millisecond performance at any scale.

Development process

We know that a client wants to know how his/her product is developing, that’s why we gave sympathetic consideration and described in details each step of the development.

First development team chose tech stack. After this developers constructed architecture and development road. We made a huge roadmap and helped with the project all along with architecture decisions. Then created a basic authorization for users and implemented API methods that provide 2Cups. Development team built our own webhooks for the client needs.

The next step was full testing of the product and bug fixing. After that, we started the second version. Run it for all cafes in Ukraine.

The last step was to correct the auto-deploy system for the future upgrades of the product.

Bot architecture
The result

Chatbots.Studio team created chatbot for the cafe chain to optimize engagement with customers. The company has a 34% cross sales increasing after implementation discount and offers system into Viber via chatbot. Obviously, that new sales channel brought more revenue to the client and helps to build trusting relationships for B2C business.

Back to blog

Platform for Live Agent Connection

bot_for_live_agent

The Rake bot was created for W5Golf – the company which provides a system for optimization of relevant engagements and improving services. It also provides customer experience optimization solutions and helps develop customer experience strategies that deliver results.

Dashboards and reports

Project description

The main goal was to build a bot for not only communication. The bot understands all kinds of questions related to company services and recognizes human speech. Also, the system provides bots hosting and live agents connection. The system is really efficient such as current clients conversation is able to be saved. It helps the bot to move towards the right step when it gets the client’s message.

Duration: 1.5 year.

Development team

Node.js and Angular.js developers, QA Engineer.

What we built

BotsTable

ManagePlatform

The solution includes

Facebook – the system automatically adds new FacebookApplication configurations and gets inbound messages from Facebook page he/she is signed.

SMS Twilio – the service that provides clients and live agent communication via SMS and provides notification mailing for appropriate clients.

We created own web-widget to place on any website. Users get access to the bot via mentioned webwidget and messages history.

The services and Frameworks we used

We selected a set of tools matching our project requirements and client needs.

Botkit is open source platform were used to create bots for different Messengers like Skype, Facebook Messenger, Twilio and Web-widget.

NodeJS + Express.js help to deploy web-server.

Loopback is the framework that was selected to automate API generation for the work with a database. It includes standard CRUD methods generation and provides delimitations of database access.

Angular.js is an open source framework that allows creating web-interface for administration dashboard for chatbot management.

MongoDB was used for saving clients and bots data.

Google Engine is the platform for project deploying. It provides automation scaling depends on server load.

Development process

The first step was prototyping the system that provides bots connection and disconnection without overloading.

Then we created module files that contain the logic of bot’s workflow. After that, we developed an administration panel for customers.

Bot architecture

Bot architecture

Technical challenges

As the system is multilevel, we founded the solution that provides bots addition and removal without system restarting. One of the client’s requirement was system scaling. So, it seems to be impossible to set up a standard Google App Engine balancer. It can break the wholeness of a client’s conversation.

We built the solution that saves the current a client’s conversation and moves the bot to the necessary next step when it gets the message.

The result
  • Technical result: We provided automation scaling system that acts depend on server load.
  • Business result: We didn’t build a simple bot where are few options for choice on buttons. Our chatbot is able to communicate with people, understand all kinds of questions related to company services and recognize human speech.

Back to blog

Helper for Live Agent and Customer Engagement

BeeOpen

Project description

BeeOpen is the new solution for better engagement clients with live agents. It means that a client gets the appropriate and complete answer regarding the issue.

BeeOpen – is the system that allows live agents to provide answers, and assign the task to the specialists. It is a more convenient solution, unlike others because the system is able to initiate calls, create tasks and provide statistics.

Duration: since June – ongoing

Development team

Developers, Project Manager, Tech Lead, QA Engineer

What we built
Services and frameworks we used

Node.js helps to deploy the web-server.

React, React Native are JavaScript libraries for building user interfaces.

Redux is the open-source JavaScript library for state management with flexible architectures.

SocketIO is a library that enables real-time bidirectional and event-based communication between the browser and the server.

React Native is the framework that was used to build a cross-platform solution for the mobile version.

Incontact is the messaging platform that provides online chatting live agents with clients.

The solution includes

WebClient is a workplace for the live agent, which included knowledge base, answers scripts, tasks management, and customers info management.

Messenger is a separate module which is connected to Rake core. It allows live agents to chat with customers.

solution includes

The result

We are creating a system for business processes and simplification of live agents’ working process. The system differs by its wide range of functionality – it is also able to initiate calls. The statistic implemented to the solution gives entrepreneurs the opportunity to see and gantlet how much benefits it could bring to their business.

Get a Quote

Menu