Back to blog

Facebook Messenger Chatbot for Automation Building Process

Project description

We have built a solution that allows users to get information about the construction process, stored in the Geometrid database. Its flexibility allows it to be easily used with different projects without making any major changes to the bot.

Duration: 1 month

Development team
Developers, Tech Lead, Project Manager, QA Engineer
What we built
building_process_automatization_bot
The solution includes

Support for different messengers, like Facebook Messenger, Slack, Viber or Skype, as well as a web-based widget.

The services and frameworks we used

DialogFlow is the platform, which provides analyzing and recognition of user’s query, as well as easy integration with many messengers.

Node-RED is the programming tool for wiring together hardware devices, APIs and online services.

AWS Elastic Beanstalk is the service for deploying and scaling web applications and services

Development process

We always demonstrate to our clients how their platform or bot are developing to assure them of high-quality services and the team’s product set in mind.

Firstly, we’ve gathered all the client’s requirements and brain-stormed regarding best practices of implementation. When the strategy of project running was identified, we started to develop chatbot using DialogFlow. After that, we gathered all possible required intents and set up them all. We created the server with Node-RED help and set it up to process user’s questions into database queries. The last step, when the logic was created and tested, we deployed it to Elastic Beanstalk server.

Bot architecture
Bot architecture
The result

The Chatbots.Studio team built a solution that allows for easy and quick access to information stored in the database about any object related to the building. The main benefit is, that using this bot does not require the user to know any database querying languages, or install any additional software, as this bot is available on the most popular messengers.

Back to blog

AI Chatbot for Education Planning

Project description

Chatbots.Studio team created a solution for Latvian educational centers. It is a service for tracking user’s learning map and progress with the automated chat bot interface. The chatbot helps to choose the appropriate learning course, asks about time that works for student and schedule the learning plan. Push notification function reminds users about a planned course even after half a year has passed.

Duration: January – ongoing

Development team

Developers, Project Manager, QA Engineer

What we built
The solution includes

Web Widget (chat interface on the website). Soon it will be possible to engage with the visitors through WhatsApp and Facebook Messenger

The services and frameworks we used

Typescript is the programming language that provides static type checking for code quality.

Nest.js is a framework for building backend applications

MySQL is an open source relational database management system

TypeORM was used for simplicity and fast development of database related code

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

Passport is the library used for different types of authorization

React.js is a JavaScript library for building user interfaces.

Redux  – State management library which implements Flux pattern. Used for managing application state and supporting scalability.

Redux-Saga – Async layer of redux actions for managing API calls, socket connections, and another little bit more complicated action handling.

DialogFlow – the platform is necessary for gathering and recognizing a client’s intent and produce human-like responses.

AWS is a service that provides application hosting, database hosting.

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.

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 Codestar – Complex tool for managing continuous delivery of application with a simple interface.

Amazon EC2  – is a web service that provides secure, resizable compute capacity in the cloud. In our case, it was used for code hosting and scaling.

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.

The result

The Chatbots.Studio team built a solution that allows for easy and quick access to information stored in the database about any object related to the building. The main benefit is, that using this bot does not require the user to know any database querying languages, or install any additional software, as this bot is available on the most popular messengers.

Back to blog

Telegram Chatbot as Personal Assistant in E-commerce

Project description

The main purpose of the project was to simplify and automate the process of making purchases in the women lingerie store.

Having swiped up the Instagram story, the user should be redirected to the chat with the bot, where they can then make the order.

Furthermore, the ordering logic was asked to be made in the most convenient possible way for: more handy and less complex while being as little time-consuming as possible.

Duration: 2 months

Development team

Developers, Project Manager, QA Engineer

What we built
The solution includes

The Telegram bot used for accepting and processing orders for targeted goods from women lingerie shop. It also stands for delivery details and payment process.

Manual communication with buyers was almost completely replaced by the bot, but some external stuff is also possible if needed: the customer can get in touch with an agent by simply clicking the special button.

The services and frameworks we used

Node-RED is the main and very powerful indeed tool: its light-weight runtime is built on Node.js, taking full advantage of its event-driven, non-blocking model.

To implement the main functionality we used the Telegram Bot API – from default interaction with clients to convenient built-in-chat payment opportunities (LiqPay).

MongoDB was used for saving info about clients and orders.

Moreover, there is the integration with the Corezoid app where shop API lives and Nova Poshta API to automate the process of selecting a post office and creating a consignment note.

For supporting any misunderstandings in a chat and buyer’s wish to talk to a human, we connected Planfix service.

Chatbase was integrated as well, so that we are able to track and analyze users’ interaction with the bot.

Development process

Firstly, we developed a static sample of the bot to agree on the client’s requirements and certainly get the feedback from prospective buyer’s.

Then we began step-by-step to implement handy features and improve UX in general, at the same time, adding eye-catching UI for the target audience.

At the last stage, we implemented human support and additional service for gathering statistics of the bot’s conversations and order history.

Bot architecture

The result

Telegram bot integrated with lots of services is ready to serve 24/7 and meet customers’ needs and expectations.
Speedy, straightforward and customer-centric: all that we hoped for and our client needed!
Aside from decreasing agents’ workload and speeding up the process of orders from the client side, we achieved the desired efficiency and productivity.
As a result, we satisfied the demands of both sides (shop and it’s customers) and are eager to continue perfecting the bot/user interaction.

Back to blog

Facebook Messenger AI Chatbot for Real Estate Industry

Project description

The main value of the solution is to simplify and make easy property search without additional email, letters, or long calls agents. Just a few clicks and the user gets the latest and hottest offers. Moreover, the chatbot allows to enter their own criteria and helps to choose a property that suits you. This could be for example, by budget or amount of bedrooms. For any help, the chatbot quickly connects a user to a live agent and he/she will hold a conversation. When the user is ready to buy or sell a property, our chatbot will offer to make an appointment to move forward.

It is your personal pocket real estate agent that finds the best choice for you, 24/7!

Duration: January – ongoing

Development team
Developers, Project Manager. QA Engineer
What we built
real_estate_bot
The solution includes

Facebook Messenger, WhatsApp, Slack (for operators).

The services and frameworks we used

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

AWS EC2 is a web service that provides secure, resizable compute capacity in the cloud. In our case, it was used for code hosting and scaling.

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.

Smooch.io is a platform that connects software and ready projects to any messaging application.

Development process

We know that a client wants to know how his/her product is developing, that’s why we kept that consideration in mind and described in detail each step of the process.

To make a client assured that project development is moving along in the right direction, we always provide describe in details each step of the development.

The first step of integration with services: Vebra, Acuity Online Appointment Scheduling. After that, our team investigated and connected with the existing project Smooch.io. This preparation allowed us to build Facebook and WhatsApp chatbot quickly and with high quality.

Bot architecture
The result

The project is still going on, we already helped the real estate client build new sales channels, unload agent’s workflow and make client’s audience happy, because of fast service.

We built an easy-to-use chatbot that helps to find the best property for you, depending on your query and make appointments with the operator.  Also, the bot was connected with a Slack channel so the operator can easy to help a user.

Get a Quote