Chatbot Architecture | Engati (2022)

What is chatbot architecture?

Chatbot architecture is a vital component in the development of a chatbot. It is based on the usability and context of business operations and the client requirements.

Developers construct elements and define communication flow based on the business use case, providing better customer service and experience. At the same time, clients can also personalize chatbot architecture to their preferences to maximize its benefits for their specific use cases.

What are the components of a chatbot?

Regardless of how simple or complex the chatbot is, the chatbot architecture remains the same. You have the front-end, where the user interacts with the bot. The responses get processed by the NLP Engine which also generates the appropriate response.

1. The user flow - Starting with intents

The NLU Engine is composed of multiple components of chatbot. To generate a response, that chatbot has to understand what the user is trying to say i.e., it has to understand the user’s intent.

Message processing starts with intent classification, which is trained on a variety of sentences as inputs and the intents as the target. For example, if the user asks “What is the weather in Berlin right now?” the intent is that the user’s query is to know the weather.

Then, we need to understand the specific intents within the request, this is referred to as the entity. In the previous example, the weather, location, and number are entities. There is also entity extraction, which is a pre-trained model that’s trained using probabilistic models or even more complex generative models.

2. Fetching a response

To predict a response, previous user conversations are stored in a database with a dictionary object that has information about the current intent, entities, and information provided by the user. This information is used to:

  • Respond to the user with a message defined by the rules set by the bot builder
  • Retrieve data from your database
  • Make an API call to get results matching intent

The first option is easier, things get a little more complicated with option 2 and 3. The control flow handle will remain within the ‘dialogue management’ component to predict the next action, once again. The dialogue manager will update its current state based on this action and the retrieved results to make the next prediction. Once the action corresponds to responding to the user, then the ‘message generator’ component takes over.

(Video) Chatbot Architecture by Aimee Kisaboyun with Nour Negm

3. Backend Integration

Since chatbots rely on information and services exposed by other systems or applications through APIs, this module interacts with those applications or systems via APIs.

Thus, the bot makes available to the user all kinds of information and services, such as weather, bus or plane schedules or booking tickets for a show, etc.


It is the medium that the chatbot inhabits and where it communicates. On platforms such as Engati for example, the integration channels are usually WhatsApp, Facebook Messenger, Telegram, Slack, Web, etc.

External Integration services

These services are present in some chatbots, with the aim of collecting information from external systems, services or databases.

This is a reference structure and architecture that is required to create a chatbot.

Although the use of chatbots is increasingly simple, we must not forget that there is a lot of complex technology behind it. There is also a lot of design and work in what has to do with defining the personality of the chatbot and the conversation flow and, finally, a lot of functionality and information that we normally access as third-party services via integration.

Chatbot Architecture | Engati (1)

(Video) Architecture of chatbots, webhooks, adding chatbots to your website

What are the different types of chatbot architectures?

Chatbot Architecture | Engati (2)

1. Generative models

Generative models are the future of chatbots, they make bots smarter. This approach is not widely used by chatbot developers, it is mostly in the labs now.

2. Retrieval-based models

Retrieval-based models are much easier to build. They also provide more predictable results. You probably won’t get 100% accuracy of responses, but at least you know all possible responses and can make sure that there are no inappropriate or grammatically incorrect responses.

Retrieval-based models are more practical at the moment, many algorithms and APIs are readily available for developers. The chatbot uses the message and context of conversation for selecting the best response from a predefined list of bot messages. The context can include current position in the dialog tree, all previous messages in the conversation, previously saved variables (e.g. username).

3. Pattern-based heuristics

Heuristics for selecting a response can be engineered in many different ways, from if-else conditional logic to machine learning classifiers. The simplest technology is using a set of rules with patterns as conditions for the rules. This type of models is very popular for entertainment bots. AIML is a widely used language for writing patterns and response templates.

4. Machine learning for intent classification

The inherent problem of pattern-based heuristics is that patterns should be programmed manually, and it is not an easy task, especially if the chatbot has to correctly distinguish hundreds of intents. Imagine that you are building a customer service bot and the bot should respond to a refund request. Users can express it in hundreds of different ways: “I want a refund”, “Refund my money”, “I need my money back”. At the same time, the bot should respond differently if the same words are used in another context: “Can I request a refund if I don’t like the service?”, “What is your refund policy?”. Humans are not good at writing patterns and rules for natural language understanding, computers are much better at this task.

(Video) LIVE: Design and build a Chatbot from Scratch

Machine learning lets us train an intent classification algorithm. You just need a training set of a few hundred or thousands of examples, and it will pick up patterns in the data.

Chatbot architecture for voice bots

This chatbot architecture may be similar to the one for text chatbots, with additional layers to handle speech.

First of all we have two blocks for the treatment of voice, which only make sense if our chatbot communicates by voice.

(Video) DialogFlow( introduction to chatbot architecture

  • Speech recognition: To take care of recognizing what the user says.
  • Speech synthesis: Generating the bot response with a voice
  • Conversation manager: It is the module that decides the flow of the conversation or the answers to what the user asks or requests. Basically this is the central element that defines the conversation, the personality, the style and what the chatbot is basically capable of offering.
  • Natural Language Understanding: To take care of the meaning of what the user wanted to say, either by voice or text.

What should you consider while developing your chatbot’s architecture?

Before building your chatbot, remember your audience. The following factors must be considered to ensure usability and a seamless customer experience:

  • User-friendliness
  • Speed
  • Support for languages
  • Compatibility with channels such as WhatsApp, Facebook Messenger, Slack, etc.
  • Back-end integrations such as CRM solutions, Shopify, Google Calendar for extended usability.
  • Analytics and feedback provision

What are the components of a conversational chatbot architecture?

Following are the components of a conversational chatbot architecture despite their use-case, domain, and chatbot type.


The environment is primarily responsible for contextualizing users’ messages/inputs using natural language processing (NLP). It is one of the important parts of chatbot architecture, giving meaning to the customer queries and figuring the intent of the questions.

Question and Answer System

The Q&A system is responsible for answering or handling frequent customer queries. Developers can manually train the bot or use automation to respond to customer queries. The Q&A system automatically pickups up the answers or solutions from the given database based on the customer intent.


Plugins and intelligent automation components offer a solution to a chatbot that enables it to connect with third-party apps or services. These services are generally put in place for internal usages, like reports, HR management, payments, calendars, etc.

Node Server / Traffic Server

Node servers handle the incoming traffic requests from users and channelize them to relevant components. The traffic server also directs the response from internal components back to the front-end systems to retrieve the right information to solve the customer query.

Front-end Systems

Having an array of front-end systems like Facebook Messenger, WhatsApp Business, Slack, Google Hangouts is extremely important apart from the website or mobile app-based chatbots to secure the possibility of interacting with the majority of the customer base.

(Video) Chat Bot Architecture

How is questions and answer training done in chatbot architecture?

Following are the two ways to train bots in chatbot architecture.

Manual Training

The process in which an expert creates FAQs (Frequently asked questions) and then maps them with relevant answers is known as manual training. This helps the bot identify important questions and answer them effectively.

Automated Training

Automated training involves submitting the company’s documents like policy documents and other Q&A style documents to the bot and asking it to the coach itself. The engine comes up with a listing of questions and answers from these documents. The bot can then answer these questions confidently.


What is the architecture of chatbot? ›

Most chatbot architectures consist of four pillars, these are typically intents, entities, the dialog flow (State Machine), and scripts. The dialog contains the blocks or states a user navigates between. Each dialog is associated with one or more intents and or entities.

What questions should a chatbot answer? ›

Your chatbot must be programmed to answer any question related to your product or service, this will avoid any confusion on what you offer and save time for your customer service team.
Common questions to answer
  • How much?
  • What's the price?
  • I need a quote.
  • How much does it cost?

Is building a chatbot difficult? ›

Coding a chatbot that utilizes machine learning technology can be a challenge. Especially if you are doing it in-house and start from scratch. Natural language processing (NLP) and artificial intelligence algorithms are the hardest part of advanced chatbot development.

Which algorithm is used for chatbot? ›

Among other things, some of the most popular algorithms used by conventional Chatbots are Naïve Bayes, Decision Trees, Support Vector Machines, Recurrent Neural Networks (RNN), Markov Chains, Long Short Term Memory (LSTM) and Natural Language Processing (NLP).

What are the limitations of Chatbots? ›

Each of them is strictly connected with a specific limitation of this technology or its bad implementation.
  • Unclear scope of the chatbot and/or too broad purposes of its utilization. ...
  • Setting unrealistic expectations is often the reason why chatbots fail. ...
  • Lack of customer perspective in building the chatbot.
12 Oct 2021

How is customer satisfaction measured in chatbot? ›

The measurement of customer satisfaction in a chatbot conversation is similar to the measurement of a conversation with a human employee. It's usually done via a short questionnaire after the conversation and it can cover questions, such as: Was the user able to understand the bot without any problems?

How many businesses use chatbots? ›

1. 23% of customer service companies are currently using AI chatbots. Whilst many companies are keen to take advantage of AI chatbots, however, the number of companies actually using them is still relatively low.

What metrics do you monitor to improve your conversational AI pipeline? ›

Traditional metrics may even be misleading.
Here's what we've learned are the five chatbot metrics that produce the most useful insights.
  • Active and engaged rates. ...
  • Confusion triggers. ...
  • Conversation steps. ...
  • Average number of conversations per user.
4 Oct 2016

What is a good question to ask a bot? ›

15 questions that will test your bot
  • Are you human? / Are you a robot?
  • What is your name?
  • How old are you? / What's your age?
  • What day is it today?
  • What do you do with my data? / Do you save what I say?
  • Who made you?
  • Which languages can you speak?
  • What is your mother's name?
9 May 2019

How do you confuse bot? ›

How to Break a Chatbot - Eight Ways
  1. 1 - Tell the Chatbot to Reset or Start Over. ...
  2. 2 - Use Filler Language. ...
  3. 3 - Ask Whatever Is on the Display Button. ...
  4. 4 - Answering Outside the Pre-Selected Responses. ...
  5. 5 - Ask for Help or Assistance. ...
  6. 6 - Answer the Question with Non-Traditional Answers. ...
  7. 7 - Say Goodbye. ...
  8. 8 - Ask Odd Questions.

What is rule based chatbot? ›

A rule-based chatbot uses a tree-like flow instead of AI to help guests with their queries. This means that the chatbot will guide the guest with follow-up questions to eventually get to the correct resolution. The structures and answers are all pre-defined so that you are in control of the conversation.

How hard is it to code a chatbot? ›

Because building a chatbot with code is immensely difficult for people with no development background and limited exposure to coding languages, it's good to research sample chatbot code from expert developers as a jumping-off point for those determined to learn how to build their own bot without help.

How long does it take to build a chatbot? ›

Implementing a chatbot takes 4 to 12 weeks, depending on the bot's scope, the time required to build your knowledge base and its technical complexity.

Which is the best chatbot platform? ›

Here are the 10 of the best AI chatbot platforms to build the exact right bot for your business.
  1. Lobster by EBI.AI. EBI.AI have created their own advanced conversational AI platform that comes with a free trial. ...
  2. ProProfs Chat. ...
  3. Chatfuel. ...
  4. MobileMonkey. ...
  5. Aivo. ...
  6. ItsAlive. ...
  7. Imperson. ...
  8. Pandorabots.
12 Sept 2022

Do chatbots use deep learning? ›

Since chatbots mimic an actual person, Artificial Intelligence (AI) techniques are used to build them. One such technique within AI is Deep Learning which mimics the human brain. It finds patterns from the training data and uses the same patterns to process new data.

What kind of AI is used in chatbots? ›

Artificial intelligence in chatbots comes in many forms. The most common are natural language processing (NLP) which powers the language side of the chatbot, to machine learning (ML) which powers data and algorithms.

Are chatbots AI or machine learning? ›

The Types of Chatbots

Chatbots are often associated with Artificial Intelligence (AI). This happens because AI gives them the ability to handle requests without the need for human intervention. However, some chatbots don't have AI and, as such, are more basic.

Why do most chatbots fail? ›

Most chatbots provide a scalable way to interact with a larger customer base on a 1:1 basis but they fail when they are incapable of leveraging NLP. They are unable to deliver an experience as smooth, efficient, and meaningful as a multi-layered, human-to-human-like conversation does.

What can a chatbot not do? ›

Chatbots lack proper human escalation protocols. Users like to know that they can still rely on humans whenever technology fails. However, most chatbots do not have an escalation workflow to allow a human to take over the conversation when the bot is unable to help.

Why chatbots are not working? ›

One of the main reasons behind the failure of chatbots is the lack of human intervention that plays a crucial role in configuring, training, and optimizing the system without which bots risk failure. As a result, many companies have not been able to implement them even after investing in them.

Are chatbots really effective? ›

Like all successful automation efforts, customers service chatbots can reduce costs, but the improvements they make in customer experience are far more impactful. Bots are available 24 hours a day, 7 days a week, and often answer customers' questions more quickly than human agents can.

Do people prefer chat bots? ›

As mentioned before only 0,5% of people actually prefer chatbots over live chats. The majority would like their chat partner to be a real human being. The survey also show that over +50% of all the respondents have had bad experiences with chatbots.

Why chatbots are the future? ›

The future of chatbots is that they are predicted to be utilized for 47 per cent of businesses for customer support and virtual assistants, will be used by 40%, which suggests that by 2022 chatbots will help companies gain market share and become an investment in improving customer service over the next few years.

How do you measure Pipeline Growth? ›

Calculate this by dividing the number of opportunities by the overall number of leads. For example, if 10 leads out of 100 move to the opportunity stage, the lead to opportunity conversion rate is 10 percent. The higher the rate, the better the lead qualification process.

What is a pipeline KPI? ›

It shows how much revenue is passing through your pipeline on a monthly basis. In other words, the KPI measures how fast your sales reps are converting leads. Sales pipeline velocity combines many of the KPIs we've already discussed: SQLs, average deal value, and sales cycle length.

How do you tell if a girl is a bot? ›

Here are a few ways to identify a typical bot while swiping:
  1. A profile not linked to an Instagram or Facebook account. ...
  2. A profile linked to a social media account that looks fake. ...
  3. The bio looks fishy. ...
  4. The photos look too good to be true.
3 Feb 2021

How can you tell if someone is a bot? ›

The most common way to tell if an account is fake is to check out the profile. The most rudimentary bots lack a photo, a link, or any bio. More sophisticated ones might use a photo stolen from the web, or an automatically generated account name. Using human language is still incredibly hard for machines.

What are the best practices in chatbot building? ›

6 Best Practices For Chatbots
  • 1) Set Expectation for your Chatbots.
  • 2) Be mindful of the Chatbot's greeting.
  • 3) Be Upfront About Bot Functionality.
  • 4) Try to make the messages as human as possible.
  • 5) Make it Easy For Your Customers To Leave.
  • 6) Reengage Users Through The Chatbot.

How do you end a chatbot conversation? ›

This tag is used to end the conversation so that the user can reinitiate the session again. All you need to do is to use the 'End' tag in the Goto and bot would end the session.

What is Omnichannel chatbot? ›

An omnichannel chatbot is an AI-enabled chatbot that provides customers with an integrated buying and customer support experience across all channels. You can deploy and manage a single omnichannel chatbot across all devices and communication channels to offer consistent user support.

Is chatbot easy? ›

Chatbot platforms are the best place for beginners to start with, These platforms are simple, easy to use design and we don't need any kind of coding knowledge, it is simply a drag and drop function.

How do you make a chatbot without coding? ›

5 Best Chatbot Platforms that Require no Coding
  1. Wotnot. Wotnot helps companies build out simple and complex chatbots for their businesses. ...
  2. Chatfuel. More than 46,000 chatbots have been created using ChatFuel. ...
  3. MobileMonkey. ...
  4. Engati. ...
  5. Botsify.

How expensive is a chatbot? ›

How much does a chatbot cost? Please, give me a simple answer.
In-House Chatbot CostsAgency Chatbot Fees
Chatbot Software Platform$50-$500/month$50-$500/month
Chatbot Setup and DevelopmentSalaries (5-100 hours of work)$500-$2,500
Ongoing chatbot support and maintenanceSalaries (0-10 hours of work per week)$50-$5000/month

How much does it cost to develop a chatbot? ›

Considering all the factors, custom development of your chatbot can approximately cost anywhere between $20,000 to $80,000. This chatbot price range would include everything, right from the overall design to the development, and integration of data analysis features like machine learning.

Can you make money from Chatbots? ›

These days, you may have heard that many people earn money with chatbots. You may ask, can you earn 100 dollars a day online? Answer: Definitely, Yes! Chatbots play an important role in the business sector such as enhancing the user experience, increasing traffic, and 10x the overall ROI.

What is the most powerful chatbot? ›

Best AI Chatbot for Customer Service: Netomi

It has the highest accuracy of any customer service chatbot due to its advanced Natural Language Understanding (NLU) engine. It can automatically resolve over 70% of customer queries without human intervention and focuses holistically on AI customer experience.

Is Siri a chatbot? ›

Yes! Technologies like Siri, Alexa and Google Assistant that are ubiquitous in every household today are excellent examples of conversational AI. These conversational AI bots are more advanced than regular chatbots that are programmed with answers to certain questions.

What is the most advanced AI chatbot? ›

Mitsuku is claimed to be the most human-like conversation bot in the world. The chatbot has won Loenber price multiple times for the most human-like conversation.

How do Chatbots work an overview of the architecture of Chatbots? ›

A chatbot interacts on a format similar to instant messaging. By artificially replicating the patterns of human interactions in machine learning allows computers to learn by themselves without programming natural language processing.

What is conversational architecture? ›

A conversation architect designs powerful, strategic conversations. They determine the questions to trigger the conversations and design the processes to convene and host them.

What is chatbot and how it works? ›

A chatbot is a software or computer program that simulates human conversation or "chatter" through text or voice interactions. Users in both business-to-consumer (B2C) and business-to-business (B2B) environments increasingly use chatbot virtual assistants to handle simple tasks.

How chatbot works step by step? ›

Put simply, chatbots follow three simple steps: understand, act and respond. In the first step, the chatbot processes what the user sends. Then, it acts according to a series of algorithms that interpret what the user said. And finally, it picks from a series of appropriate responses.

What are the technologies used in chatbot? ›

Artificial intelligence (AI), natural language processing (NLP), and machine learning are chatbot underlying technologies. They bring chatbot innovation, hence brand communication, to an entirely new personalized level.

What is rule based chatbot? ›

A rule-based chatbot uses a tree-like flow instead of AI to help guests with their queries. This means that the chatbot will guide the guest with follow-up questions to eventually get to the correct resolution. The structures and answers are all pre-defined so that you are in control of the conversation.

Which of these are considered to be best practices in chatbot building? ›

One of the best practices for designing a chatbot is to outline your goals clearly before you even start building it. It helps you to understand the queries or questions your customers might be expecting by using the chatbot.

What is chatbot intent? ›

Intent is chatbot jargon for the motive of a given chatbot user. It's the intention behind each message that the chatbot receives. Intent is all about what the user wants to get out of the interaction. For example, a user says, 'I need new shoes.

What is chatbot in NLP? ›

Often referred to as virtual agents or intelligent virtual assistants, these NLP chatbots help human agents by taking over repetitive and time consuming communications. This frees up the human agent to concentrate on those more complex cases that require human input.

What is chatbot Analytics? ›

Chatbot analytics is the real-time data that your chatbots is generating through its interaction with people. This data can be really useful and present a great value for your business.

Which is the best chatbot? ›

7 Best Chatbots (September 2022)
  • The Best Chatbots of 2022.
  • HubSpot Chatbot Builder.
  • Intercom.
  • Drift.
  • Salesforce Einstein.
  • WP-Chatbot.
  • LivePerson.
  • Genesys DX.
15 Aug 2022

How AI is used in chatbot? ›

A chatbot system uses conversational artificial intelligence (AI) technology to simulate a discussion (or a chat) with a user in natural language via messaging applications, websites, mobile apps or the telephone.


1. What is a Chatbot?
(IBM Technology)
2. Rasa Chatbot Tutorial | All important concept | NLU | CORE | Building First chatbot | RASA - 3
(Binod Suman Academy)
3. Webinar : How to build a chatbot in just 10 minutes using Engati.
(Engati - The Best Free Chatbot and Live Chat Platform)
4. Build your own chatbot simple & easy using - Part 1 Architecture
(Penguin Tech)
5. Build your own chatbot using Python | Python Tutorial for Beginners in 2022 | Great Learning
(Great Learning)
6. Generative Chatbot Architecture
(Anand Uthaman)

You might also like

Latest Posts

Article information

Author: Fredrick Kertzmann

Last Updated: 09/08/2022

Views: 5928

Rating: 4.6 / 5 (46 voted)

Reviews: 85% of readers found this page helpful

Author information

Name: Fredrick Kertzmann

Birthday: 2000-04-29

Address: Apt. 203 613 Huels Gateway, Ralphtown, LA 40204

Phone: +2135150832870

Job: Regional Design Producer

Hobby: Nordic skating, Lacemaking, Mountain biking, Rowing, Gardening, Water sports, role-playing games

Introduction: My name is Fredrick Kertzmann, I am a gleaming, encouraging, inexpensive, thankful, tender, quaint, precious person who loves writing and wants to share my knowledge and understanding with you.