Aristek SystemsContact Us
Preview of case

AI-driven question-answering system for learners

The Aristek team assisted a US-based eLearning provider in developing an LLM-based chatbot that powers a scalable Q&A learning experience for students. The solution enables learners to ask questions across multiple subjects and receive contextual responses based on the platform’s internal knowledge base.

Data science & AIEdTech
Icon 1USA
Icon 2Education
Icon 3Since 2024

  • Summary

    This case study shows how an AI question answering system was implemented for a US K-12 eLearning platform. The solution uses a retrieval-augmented generation approach to power modern AI-powered question-answering systems, providing fast and accurate responses to student questions while maintaining strict data protection.

    In this material, we explain the implementation process, the architecture behind the chatbot, and the results it delivered for students and teachers.

Key achievements

Image
1

month project duration

>1000

requests per minute system capacity

5+

points NPS growth

Challenge

The educational platform is used by students of all ages, from Kindergarten to high school. The platform already had a chatbot, but its current functionality did not meet the provider’s growing needs.

  • Teachers were not always available to answer all questions and answer students fully, especially across multiple domains.

  • Due to the high competition in the market, the customer was looking at new ideas to stay on top. They decided to use AI to facilitate decision-making, improve learning culture and adopt new forms of learning.

  • The main prerequisite for the AI-driven question-answering system for learners was the highest degree of data protection both within the system and towards any third parties.

Solution

After a series of joint meetups, it was decided to utilize the existing platform’s functionality and integrate the new AI-based tool with it. The chatbot was designed as part of modern AI-powered question-answering systems, capable of responding to student questions across multiple subjects while maintaining context and ensuring data security.

  • 1

    Conduct basic administrative tasks (e.g., replying to student’s questions in various domains)

  • 2

    Preserve the request history and maintain context in the dialogue process

  • 3

    Process an ever-growing variety of educational materials in the system

  • 4

    Provide personalized learning support depending on the pupil’s age

  • 5

    Integrate with the existing systems seamlessly

  • 6

    Ensure low query latency to keep students engaged

  • 7

    Have a high level of security and ensure no PII leakage

  • 8

    Handle multiple student inquiries simultaneously

Project scope

For the project, the Aristek team relied on subject matter expertise in AI-based development and the education domain. It consisted of the following steps:

Icon

  • Pipeline for data collection and processing.

  • Data extraction and embedding calculation.

  • Setting up a question-answering system utilizing retrieval-augmented generation techniques.

  • System testing (load up to 1000 requests per minute).

How it works

Here’s an example of how the chatbot supports Q&A learning in practice:

1

The pupil asks a question about the water cycle via the learning platform’s chat interface.

2

The AI chatbot processes the query, using its knowledge base and context from previous interactions to formulate a comprehensive answer.

3

The platform displays the response, along with options to explore related topics or ask follow-up questions.

4

The pupil can then delve deeper into the topic or explore suggested related concepts.

5

If needed, the chatbot uses adaptive questioning to assess understanding, refining its explanations until the student’s query is fully addressed. Depending on the student’s grade, the answer is presented differently.

Screenshots

  • Image of slide 0
  • Image of slide 1
  • Image of slide 2
  • Image of slide 3
  • Image of slide 4

Key features

AI systems such as ChatGPT are highly criticized as they may create text that seems credible at first glance but may in fact contain errors or nonsense. Thus, the trustworthiness of the answers is always questioned.

Taking this fact into account, the question-answering system was implemented with the ability to retrieve an excerpt from the training material and a link to its location.

Such tooltips are shown as in-app messages. Their key features include:

  • 1

    Providing contextual excerpts

    When a user asks a question, the AI system retrieves a relevant excerpt from the existing database of training materials. Instead of generating a full response, the tooltip displays a concise, pre-existing text chunk that directly answers or clarifies the query. This ensures accuracy and helps avoid incomplete or incorrect answers.

    How it works: If someone asks about “Newton’s laws of motion,” the tooltip could provide a short text from the course material that explains the first law, such as: “Newton’s First Law states that an object in motion will stay in motion unless acted upon by an external force.”

  • 2

    Streamlining access to further information

    It can be cumbersome to find what you need instantly – it can take hours. For our solution, it takes an average of three milliseconds to provide an answer. Tooltips augment excerpts with a link to the full location of the content within the learning material. This saves a lot of time searching for the right paragraph or article in the institution’s database.

  • 3

    Increasing adaptability to any tone of voice

    There’s no need for the user to enter the precise query. The system supports human-like communication and provides the answer according to the search meaning, ensuring that even vague or incomplete questions are met with relevant responses.

Tools & technologies

Python
GitHub
GPT-4
Jira
OpenAI

Team

  • Image of slide 0

    Data scientist x2

Project results

The implemented solution demonstrates how AI-powered question-answering systems can transform digital learning environments. By providing instant explanations and contextual references, the platform improved student engagement while allowing teachers to focus on higher-level instruction.

  • Icon of card 1

    Customer gained a competitive edge by offering round-the-clock, personalized support to students across all subjects, which had a significant positive impact on student engagement.

  • Icon of card 2

    Students of all age groups benefited from instant access to tailored explanations and assistance, allowing them to learn at their own pace and receive help whenever they needed it, regardless of time or topic complexity.

  • Icon of card 3

    Teachers could focus on higher-level instruction and personalized guidance, as the AI chatbot handled routine questions and provided in-depth, holistic explanations.

    AI-powered tooltips save hours of searching for materials and free up valuable time for more impactful educational activities and deeper student interactions.

The introduction of the tooltips feature makes the entire system independent of third-party vendors, as all information is retrieved from an internal database.

In addition, the solution was designed with flexibility in mind, allowing for seamless transition between cloud and on-premise deployments. This architecture ensures that, if required, migrating from cloud to on-premise infrastructure can be accomplished with minimal effort and disruption.

Overall, these initial positive results have opened up exciting prospects for further collaboration with the customer.

Image
24/7

availability for student support

>1000

requests per minute handles the system

5+

points the customer grew the platform’s NPS

  • Aristek provided us with much-needed technology-specific expertise and support in the AI-based system implementation.

    We were surprised at how fast it was possible to get such a project up and running. Also, it turned out to be not as difficult as it seemed at first glance, and we can already track positive changes in the engagement levels of students of all ages.

    This solution became an all-rounder for inquisitive whyers worldwide, and we look forward to continuing to work on this project with the Aristek team.”

    The customer’s product manager says
    Photo of author

Insights

  • Students ask very different questions than expected

    During testing, it turned out that many student questions were vague or incomplete. Instead of precise queries, learners often asked things like “Why does this happen?” or “Can you explain again?” The system had to rely on context and previous dialogue to understand what the student meant.

  • Strict accuracy requirements changed the AI design

    In education, even small mistakes can reduce trust quickly. Because of this, the team moved away from purely generative answers and relied more on retrieving verified excerpts from the course materials.

  • Scalability mattered more than feature complexity

    The platform already had learning content and user flows. The real challenge was making sure the system could respond instantly even during peak usage when many students asked questions simultaneously.

Our key takeaways

Image
Icon 1

Use trusted educational content as the primary knowledge base.
AI answers should rely on verified learning materials to maintain accuracy.

Icon 2

Combine generative AI with retrieval techniques.
Retrieval-augmented generation helps reduce hallucinations and increases reliability.

Icon 3

Design AI responses for different age groups.
Adaptive explanations improve learning outcomes and student satisfaction.

Icon 4

Focus on response speed.
Fast answers help keep students engaged during learning sessions.

FAQ

The chatbot uses retrieval-augmented generation, which means responses are based on verified learning materials stored in the platform’s internal database. The system can also show excerpts and links to the original content.

Yes. The system in this case study was tested with loads of more than 1000 requests per minute, allowing thousands of students to receive answers simultaneously.

Yes. The system was designed with strict security rules and internal data storage. This prevents personal information from being shared with external systems or third parties.

Want to know the cost of your AI project?

Answer a few quick questions to get an estimate.

Costs calculator

Contact our expert

If you have any questions regarding the case study or have similar project to be discussed, do not hesitate to contact us.

Image

We use third-party cookies to improve your experience with aristeksystems.com and enhance our services. Click either 'Accept' or 'Manage' to proceed.