Project Scope and Technology Choices

#

For my AIDA project, I want to work on a chatbot solution for E.G. The idea is to create a digital assistant that can help visitors and potential stallholders get quick answers to common questions about an event.

The problem I want to focus on is that many users often ask the same questions. These questions can be about opening hours, prices, location, rules, activities, food, or how to apply for a stall. If all of these questions have to be answered manually, it can become time-consuming for the people responsible for the event.

Project idea

#

The project will be a chatbot that can answer frequently asked questions based on a knowledge base. The chatbot should make it easier for users to find information and reduce the number of simple questions that need to be answered manually.

The chatbot should be able to answer questions such as:

• When is the event?
• What are the opening hours?
• What does the entrance cost?
• Where is the event located?
• Are dogs allowed?
• What activities are available?
• How can someone apply for a stall?
• Who should be contacted for special questions?

The chatbot should not replace personal contact completely. Instead, it should work as a first point of help. If the chatbot cannot answer a question, it should guide the user to the correct contact person.

Technology considerations

#

For this project, I am considering using Dify to build the chatbot. Dify makes it possible to create a chatbot and connect it to a knowledge base without building everything from scratch.

The knowledge base will contain structured information about the event. This allows the chatbot to retrieve relevant information before generating an answer. This approach is useful because the chatbot should not just answer from general AI knowledge, but from specific information related to the project.

I am also considering using a RAG approach. RAG stands for Retrieval-Augmented Generation. This means that the chatbot first retrieves relevant information from the knowledge base and then uses that information to generate an answer. This can help reduce hallucinations and make the answers more reliable.

Scope

#

The first version of the project will be kept simple. The goal is to create an MVP that can demonstrate the core idea.

The MVP should include:

• A chatbot connected to a knowledge base
• Answers to common visitor questions
• Basic information for stallholders
• A fallback answer when the chatbot does not know the answer
• Contact information for questions that require personal help

The chatbot will not include advanced features in the first version. It will not handle payment, approve stallholders, or complete bookings automatically. These features would require more data, security, and integration with other systems.

Possible future features

#

If the project was developed further, it could include more advanced functionality. One idea is to add a digital application form for stallholders, where users can submit their information directly.

Another possible feature is visitor flow guidance. If E.G. had data about visitor numbers from previous years, the chatbot could help users choose a less busy time to visit. For example, it could suggest arriving early or later in the day if the middle of the day is usually crowded.

This would require more data, such as ticket scans, entrance counts, or manual observations from previous events.

Reflection

#

My main focus is to build something realistic and useful. The goal is not to create a very advanced AI system, but to create a simple solution that solves a concrete problem.

Through this project, I want to learn more about how AI can be used in practice, especially in relation to chatbots, knowledge bases and RAG. I also want to better understand how project scope affects development. By starting with a small MVP, it becomes easier to test the idea and later add more features if needed.

This project gives me the opportunity to work with both AI and user-focused development. It also shows how a simple chatbot can support communication, save time and improve the user experience.