Chatbot Jacob - Case Study
The ESOMAR mobile app was developed with the primary goal of optimizing the value of membership for its users.
- ensuring that the app was user-friendly and easy to navigate for members.
- integrating the various resources and features in a seamless and cohesive way.
the development team used a combination of custom code and the low-code solution FlutterFlow to create a highly functional and visually appealing app that met the needs and preferences of ESOMAR and its members.
The benefits for the client: ESOMAR
The Era of AI: An Intro
Artificial intelligence is drastically changing our outlook on technology soon, there will come a time when no aspect of our lives is left uninfluenced by for all intents and purposes AI in some way, which essentially is quite significant. But the kind of good news is, most of these changes are affecting us in beneficial ways, and advancements in AI technology are significantly helping businesses for the most part to improve their means of operation.
One innovative application of AI is the development of AI chatbots. Every company that strives for greatness has to offer the most value to its clients in the shortest amount of time. For that reason, AI chatbots are widely used in business to boost sales, enhance customer service, and develop a brand voice. But what precisely is an AI chatbot? To put it as simply as possible, it is an artificially intelligent robot or computer program that can communicate with people by using natural language processing and machine learning. AI chatbots have a lot of potential and businesses are now starting to realize the advantages of utilizing chatbots to enhance the consumer experience through customer care and online sales.
Similarly, dev-UP has used the power of AI to help ESOMAR take its business to a whole new level! ESOMAR is a not-for-profit membership organization for people engaged in the market, opinion and social research, and data analysis. There are numerous customer queries received by the organization on a daily basis, and we have created a chatbot that significantly improves the lives of our customers by making their experiences easier and more convenient.
How Was Chatbot Jacob Built?
Chatbot Jacob was built using a platform called Xenioo but we went the extra mile and extended the platform by using our own AI models. This, in return, enables chatbot Jacob to also handle NLPs and answer a diverse range of questions. It’s a unique AI chatbot that is guaranteed to make ESOMAR’s customer service more efficient, user-friendly, and accessible to a wide variety of people. These chatbots are actually pretty simple and rely on some fundamental rules in order to determine the best response for a given customer scenario. They are also referred to as expert systems and typically use pre-programmed if-then statements.
Chatbot Jacob can search through all the different platforms of ESOMAR and present to the customer the exact information they require. ESOMAR, being a business community of insights and analytics, has several platforms on its website that are often not easy to navigate, especially for a newcomer. There’s Directory, About, Events, Reports and Publications, and multiple other tabs to view. Importantly, ESOMAR has a blog website called Research World that is specifically focused on marketing. Skimming through all these different pages and looking for a specific piece of relevant information can be challenging and if we’re being honest, not everyone has the time for that either. Wouldn’t life be a whole lot easier if you could just direct your question to an AI chatbot and have it go through multiple pages of information to bring you exactly what you require? That’s what chatbot Jacob does flawlessly and without wasting a minute of your time.
Another amazing feature of chatbot Jacob is that you can ask it questions that you do not find under the FAQ tab on the website. FAQs cover a range of frequently-occurring queries. You’ll find plenty of help through them, but in case your question is different from the list of questions we’ve already answered for you, chatbot Jacob will be at your service!
Using NLP, we have built chatbot Jacob to be able to link different variations of the same query and direct the user to the relevant piece of information. So, for example, if a customer asks “where do I find my invoice?”, “invoice – where can I find it?” or “is there a way to find my invoice,” then the chatbot will make the relevant connection and guide the user to the right answer, which might sound like “the invoice can be found in such and such location.” That means even if you feel like you don’t have the exact words to put your query in, you can rely on our AI bot to make the connection and direct you to the required information.
Chatbot Jacob is more special and helpful than the regular AI chatbots out there – at the backend, it is connected to like five or six data sources, which means it is immediately directed to an APL data hub, which in turn contains five or six APIs.
The primary objective of chatbot Jacob is quite simple: answer any and every question a customer might have comprehensively, and ensure their query is resolved. Customer service is one of the most important aspects of a business and without the needs of customers being promptly addressed, it is difficult for any organization to truly prosper. That’s why the aim of chatbot Jacob is to make customer
service the utmost priority for ESOMAR, and it does so by making answers available to all the possible
questions customers might have.
Finding relevant content and information on a website can sometimes be challenging, especially if one is new to the platform. People usually want their queries answered right away without having to go through any extra steps that’s exactly what chatbot Jacob does. You enter your question into the chatbot and Jacob will direct you to the most appropriate answer that fully satisfies your concern.
Another main objective of ESOMAR’s chatbot, Jacob, is to collect and present relevant survey results to interested customers. This includes information such as other customers who are members, the opinions of members, etc., which several people find quite helpful. This means that thanks to chatbot Jacob, customers don’t have to go the usual route of contacting a member of the customer service team through phone or e-mail and wait several minutes or hours to have their query resolved or learn a specific piece of information.
Chatbot Jacob, as supportive and user-friendly as it is, comes with certain challenges. The main problem
developers have had in the production of this AI chatbot is combining data sources and simultaneously
optimizing speed and accuracy. The AI model has to handle the combination of answering different
versions of the same questions or maybe even random, unconnected words. People will inevitably
search for whatever makes sense to them and the job of the AI model is to send the words to the right
API in order to search through five or six different data sources correctly.
To say chatbot Jacob will make the lives of ESOMAR customers easier would be an understatement. It will undoubtedly make the process of looking for relevant information much simpler, which will result in a more satisfied customer base. Quicker help, easier navigation, no need for long waiting times on phone calls or having to type out emails what else does a customer ask for?
Moreover, conventional customer service is pretty limited in the sense that you cannot call up an individual and ask them for help 24/7. In contrast, AI chatbots provide their services at all times. It doesn’t matter what time of the day it is or where you’re located your query will not have to wait hours before getting resolved!
Not only do the customers benefit from the existence of such a versatile chatbot but the businesses significantly reduce their costs too by not wasting essential resources on activities that can easily be automated. Instead of answering the same questions over and over again manually, why not use the valuable human labor and time for much more productive processes?
Thanks to the ever-evolving process of deep learning, chatbots can play out dynamic interactions with customers and operate successfully automatically in various complex contexts and repeat the process as many times as required!
Chatbot Jacob is set to go into production in the first week of January 2023 after being developed for almost one year. In the long term, the AI model can be used elsewhere and the next step going into the future is to integrate the model into other platforms.
If you'd like to discover more about the tool and see how it could benefit you, feel free to
The benefits for the client: ESOMAR
The Power of AI: An Intro
Just imagine the following: you have a giant database with a wealth of valuable content at your disposal, but you cannot use it to its full potential. What a pity, right? But what if there is an opportunity to extract this potential? Just as any seasoned treasure hunter must have powerful tools and resources at his disposal, today’s ‘digital treasure hunter’ is no different.
Technology, and in particular the power of Artificial Intelligence (AI), can help you fulfill more of your organization’s potential. Read on to learn how this works in practice through the ANA case study. You will learn how dev-UP harnessed the power of AI to make ANA’s search engine more accurate, flexible, and intelligent.
In the opening, we mentioned the challenge of this case. The challenge in making ANA’s search engine more powerful consisted of improving the speed and accuracy. Firstly, the speed of the search engine needed considerable improvement. It sometimes took ten seconds (or more) before the user received a result after entering a search term.
Secondly, the search engine had to be more accurate. The accuracy could do with some improvements as typing errors, for instance, often resulted in no or fewer (relevant) results. A fix was necessary because such a problem could result in membership cancellations due to the deteriorating user experience of ANA. Overcoming this challenge required a robust solution. And what better way to create such a solution than with AI as a strong catalyst?
ESOMAR allowed dev-UP to work on developing and implementing a solution. Given the AI expertise of dev-UP, a solution has been found based on intelligent application of various AI capabilities. Part of the solution was the use of Azure Cognitive Search. This cloud search service with built-in AI capabilities helps identify and explore relevant content at scale. Machine learning techniques make it possible to gain insights from various types of content.
In addition, Azure Cognitive Search also provides semantic search capabilities to understand user intent and contextually rank the most relevant search results. Furthermore, we used Azure’s Bing Spell Check to ensure a fast and high-quality spell check when entering search terms. Previously, search terms were not necessarily corrected, which led to fewer or no results. Combining efforts of Azure Cognitive Search and the Bing Spell Check, this is no longer an issue.
In short, this solution has resulted in a much faster, more accurate and more robust search engine. However, we did not stop there. Dev-UP always goes the extra mile but still keeps things simple. How is that possible?
We keep IT simple by identifying the key benefits technology can bring in your specific situation, a step-by-step implementation, and interim demos to keep you up-to-date about the progress.
The capabilities mentioned in this case sound great. However, the most important thing is what the solution brings your organization of value: What’s in it for me (WIIFM)? In addition to the improved intelligence, speed, and accuracy, Azure has set up their infrastructure in a way that supports automatic scaling.
Using the Advanced Search, members can search more specifically for content based on, for example, date, author, or company name. It is possible to tailor the solution to work with data sources already present within the organization using custom code. No new data needs to be acquired, which saves resources. Finally, during the process, we focused on security by only granting full access to the knowledge base to people with the correct authorization, i.e., the members.