The Ultimative Chatbot Guide

The Ultimative Chatbot Guide

Everything you need to know about chatbots for your business!

  • Chatbot basics & technology
  • Chatbots for your company & implementation tips
  • Statistics & trends
Thank you for your message. It has been sent.
There was an error trying to send your message. Please try again later.

By submitting my email address, I consent to being contacted and to the storage and processing of my personal data according to the privacy policy of Onlim GmbH. This consent can be revoked at any time in writing.

Chatbot Basics & Technology

Chatbot Basics & Technology

Chatbots are a form of automated service – like a robot that customers can communicate with via chat.

You can use a chatbot in different ways via text and voice. For example on a website, via Facebook Messenger or via a voice assistant such as Amazon Alexa, Siri or Google Assistant.

Essentially, it’s a virtual conversation in which one party is an online talking robot that can carry out a defined task or give automated replies to users’ questions.

There are two types of chatbots – the ones structured by hard coded questions/answers and the ones that are able to learn through Machine Learning.

The first have a smaller knowledge base and limited skills. They can only give correct output based on specific instructions, meaning the questions asked must correspond to their set programming.

Chatbots that are able to learn can understand understand natural language and therefore do not need as specific commands. That means bots based on Machine Learning get smarter with every interaction. The effort behind these automated systems is of course much greater.

More about rule-based vs. AI-based chatbots can be found in the next section.

There are two main chatbot types:

Rule-based and AI-based chatbots.

With a rule-based chatbot, possible user queries and potential answers are defined in advance. If a question is asked that has not been previously defined, the chatbot will not be able to assist in answering the question.

In contrast to rule-based bots, chatbots based on Artificial Intelligence are able to process natural language. This is done with the help of Natural Language Understanding (NLU). AI-based chatbots are able to learn semi-automatically.

Which type of chatbot is best suited for your company mainly depends on the following two factors.

For example, if you need a chatbot that should only perform a very limited number of clearly defined tasks, it is sufficient to use a rule-based bot. An AI-based bot makes more sense if the chatbot is used for different tasks or to solve more complex problems. Rule-based bots are often used for marketing purposes, such as distributing information or offers, while AI-based chatbots are more common in customer service.

Another crucial factor to consider is the budget and time available to implement the chatbot bot. In general, a rule-based bot can be implemented much cheaper and with less work.

Two very important factors for the overall performance of a chatbot are the structure and quality of the data that are available for answering questions. This is where Knowledge Graphs come in.

Knowledge graph is a synonym for a special kind of knowledge representation. It stores facts in the form of edges between nodes in a graph/network. In addition, most knowledge graphs also store the schema of the data (e.g., class hierarchies). Knowledge Graphs develop their full potential especially with large and complex data structures.

When used for chatbots, a Knowledge Graph offers two direct advantages – improved data integration and simultaneous improvement of conversations.

New data sources can be integrated more easily, since they only have to be brought to a single specific format and scheme. Knowledge Graphs also offer increased flexibility for expanding existing knowledge. That way, new facts are saved directly as new nodes and edges in the graph.

It is also possible to link several Knowledge Graphs without any problems, either using the same nodes or adding new edges. This allows to build up a modernly managed corporate knowledge base, which can be retrieved via API and voice interfaces using natural language.

Chatbots for your business & implementation

Chatbots for your business & implementation

Chatbots are suitable for many industries and use cases.

They are well-known to be able to provide excellent customer service, but there are also some great examples of chatbots in marketing & sales.

With chatbots, companies benefit from:

  •  Automated 24/7 support that can be taken over by an employee at any time if required
  • Communication and accessibility on the channels preferred by customers
  • Increased interaction and opening rates
  • Automated lead generation
  • Efficient use of resources
  • Innovative competitive advantage

These points should be considered before implementing a chatbot:

  • How often does your company have direct customer contact?
  • Does your customer service receive recurring requests frequently?
  • How intensive are your customer requests?
  • Which communication channels do your customers prefer?
  • What added value can a chatbot create for your business?
  1. The use case

It is important to understand the specific use case as detailed as possible. Many companies often ignore the benefits for the user and only consider the use case from a company perspective. Ask yourself, where can a chatbot improve the user experience and at the same time offer the best possible support for employees?

  1. The implementation

Three of the most important factors during the implementation are the project team, the scope of the use case and the connection to various data sources. Engage the right internal/external people for the project, define a clear use case and do not underestimate the importance of internal/external data sources for the general performance of the chatbot.

  1. Multichannel capability

One reason for the success of chatbots is the fact that customer communication habits are taken into account. Note which channels make sense for your target group and whether e.g. voice assistants are also a possibility in order to be perfectly prepared for future customer communication.

  1. Test & optimize

Semi-automatic learning systems “live” from a large number of interactions. This is the only way to quickly optimize the chatbot. Therefore, it is essential to provide the necessary resources for the optimization of the chatbot, especially after the launch.

Statistics & Trends

Statistics & Trends

Chatbots and voice assistants from a user perspective:

  • Consumers see the following advantages of chatbots: 24h service (64%), immediate answers (55%), answers to simple questions (55%). (Drift, 2018)
  • 60% of Germans have already used a voice assistant, among them 30% are intensive users. (Splendid Research, 2019)
  • Consumers would prefer a voice assistant over a website or app because it is more practical (52%). (Conversational Commerce by Capgemini Report – 2018)

Chatbots and voice assistants in companies:

  • 58% of those questioned said that technologies such as chatbots or voice assistants have changed their expectations towards companies and will continue to do so in the future (77%). (Salesforce, 2019)
  • These departments will benefit most from chatbots: customer service (95%), sales/marketing (55%), order processing (48%). (Mindbrowser, 2017)
  • Companies that use AI, chatbots and automation are experiencing an increase in overall customer satisfaction. (LivePerson, 2019)
  1. AI becomes “smarter”

Knowledge Graphs will play an important role in the future development of AI-systems. Many chatbots will access Knowledge Graphs that are publicly available and thus, have access to plenty of content and can therefore better understand data, tasks and interactions.

  1. Stronger focus on goal achievement

With the ability to understand data better, chatbots can build expert knowledge in specific domains and become better at solving specific problems by providing precise answers to complex questions or even perform complex automated processes themselves.

  1. Chatbots become more human

Technology providers will continue to work on improving the human aspect of their chatbots – reducing misinterpretation of queries, understanding the nuances of human dialogue, the accents or cultural dialects, and the intentions of customers.

  1. „Voice assistants are booming and blooming“

The use of voice assistants is steadily increasing and is expected to triple by 2023. Voice commerce and voice search are also gaining in importance. This year, companies need to think about a voice-based strategy to stay relevant to customers.


Further questions?

You find all the answers and everything you need to know about chatbots for your business in our Chatbot Guide!


Non-binding and free

Non-binding and free

Contact us

Contact us

We want to learn more about your business and the challenges you are facing. Then we can determine if our chatbot and voice assistant solution is the right choice for your business. If you’re ready to start your AI-powered, automated customer communication journey, request a consultation right here or call us at +43 1 997 44 31 in order to get an immediate response.