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

AI Chatbot for Tracking Pricing List

slackbot

Project description

Chatbots.Studio created an amazing solution that will turn the world of retail business on its head. Everyone knows that to be successful in a market means to know your competitors really well. Our chatbot helps companies keep tabs on their competitor’s pricing so they can better adjust their own.

The bot greets a user and suggests tracking a specific pricing page. The changes will be displayed to the user once we receive a response of what exactly changed, the main condition here is for the end user to pay with PayPal for the subscription, as there will not be the possibility to check for the changed information.

Duration: January – ongoing.

Development team

Developers, QA Engineer, Project Manager,

What we built

apify-integration

The solution includes

Slack Corporate Messenger

The services and Frameworks we used

ApifyThe scalable web crawling and scraping library that simplifies the development of web crawlers, scrapers, data extractors, and web automation jobs.

Sequelize – Sequelize is a promise-based Node.js ORM for Postgres, MySQL, MariaDB, SQLite and Microsoft SQL Server. It features solid transaction support, relations, read replication and more.

Botkit – is a 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

Node.js is the 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.

Development process

This solution is currently in developing but for now, we already have a working chatbot that has satisfied marketers’, entrepreneurs and product owners. At the beginning of the project, developers launched a simple scraper, which saved the information to the AWS S3 bucket. Now, Slack bot has been integrated including the persistent data storage – MySQL which is under development currently.

At the beginning of the project, I launched simple scraper, which saved information to the AWS S3 bucket. Now, Slack bot has been integrated including the persistent data storage – MySQL which is under development currently.

Bot architecture

Bot architecture

The result

Chatbots.Studio is developing a chatbot that brings real results and value to business without additional acts. Cutting edge technologies were used to augment the marketing strategy. When the owners implement chatbot in their business, there is no longer any reason to buy expensive tools to measure competitor pricing or to employ special buyers. Chatbot tracks competitor pricing for goods or services and showcases them to you in the appropriate order. After that, you can make a decision as to what to change or improve in your business with confidence.

So, adjust the business strategy with our chatbot and grow!

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.  

Get a Quote