How Wisdom Business Academy Uses Kampus Sense AI Agents to Improve CIMA Learning

Wisdom Business Academy (WBA) is a leading professional education institution and CIMA Registered Tuition Partner in Sri Lanka. It supports students across different stages of professional accountancy education, including learners preparing for demanding CIMA objective tests and case study examinations.

WBA already uses Kampus Wave, Axis, and Pulse to support digital learning, student administration, enrolment, payments, and mobile access. Kampus Sense extends this ecosystem by bringing purpose-built AI assistance into the education experience.

The objective was not to replace lecturers or traditional academic guidance. It was to give students more opportunities to learn, practise, ask questions, and receive support between scheduled classes while giving academic staff practical AI tools for content preparation.

CIMA students must understand complex business concepts and learn how to apply them within realistic scenarios. This is particularly important for case study examinations, where success depends on analysis, professional judgement, and the ability to connect technical knowledge with information provided in the pre-seen material.

Lecturers provide the academic direction students need, but individual support cannot always be available at every stage of independent study. Students may encounter questions while reviewing a module, analysing a pre-seen document, or practising a mock examination outside normal class hours.

Creating high-quality practice material also requires considerable academic effort. Lecturers must prepare questions, construct realistic mock scenarios, review written responses, and provide actionable feedback.

WBA implemented five Kampus Sense agents, each designed around a clearly defined educational workflow. Rather than asking students and staff to adapt a general-purpose chatbot, every agent has a dedicated role, its own instructions, and the appropriate academic context.

1. CIMA Case Study Feedback Agent

Students can submit written practice answers and receive structured formative feedback on relevance, application to the case, completeness, clarity, and potential areas for improvement. The agent encourages reflection and repeated practice while lecturers retain responsibility for academic judgement and formal assessment.

2. CIMA Case Study Mock Generator

The Mock Generator creates additional case study scenarios and questions using the configured academic context. It expands the range of practice material available, helps students prepare for unfamiliar scenarios, and gives lecturers a productive starting point for new mock examinations.

3. CIMA Pre-Seen Tutor

The Pre-Seen Tutor helps students explore the organisation, industry, stakeholders, risks, business environment, and other information contained in the relevant pre-seen material. Students can investigate relationships between facts and revisit important details while preparing for lecturer-led discussions and examinations.

4. Module Assistant

The Module Assistant acts as an always-available learning companion for a specific module. Students can ask about concepts in their learning resources, request simpler explanations, and explore connections between topics. Its scope remains focused on the configured module and approved academic content.

5. Question Generator

The Question Generator assists lecturers and academic staff with preparing draft questions based on selected topics and learning objectives. Staff review and approve all material before use, keeping academic teams in control while reducing repetitive preparation work.

WBA configures each agent for a defined academic purpose and adds the relevant learning material to its knowledge base. Students or authorised staff then select the appropriate agent and interact with it using the context and boundaries established by the institution.

This focused approach makes the experience more relevant than a general chatbot. Students use the guidance for further study and practice, while lecturers retain oversight of teaching, formal feedback, and assessment.

The agents complement WBA's existing learning environment by helping students move from passive review to active engagement. They can ask questions, test their understanding, explore a pre-seen document, practise new scenarios, and identify areas that require more attention.

Early feedback from WBA students and staff has been positive. Students value being able to obtain relevant assistance while studying independently, particularly when working through complex module content, pre-seen material, and case study practice.

The five agents create more opportunities for students to engage actively with their learning. Instead of relying only on notes and model answers, they can explore concepts through questions, practise against new scenarios, and use formative guidance to improve their responses.

Academic staff have also responded positively to purpose-built AI assistance within controlled educational workflows. Question generation and mock-exam support provide useful starting points while staff retain responsibility for reviewing and approving academic material.

A general-purpose AI assistant may not understand an institution's course structure, teaching approach, learning resources, or academic expectations. Kampus Sense gives WBA a more controlled model: every agent is designed for a specific educational task and connected to the relevant knowledge and instructions.

This creates a more useful experience for students while allowing the institution to determine how AI is applied within teaching and learning. It also provides a repeatable foundation for expanding AI-assisted education across additional modules and programmes.

The five-agent implementation establishes a foundation that WBA can extend across additional modules, qualifications, and student-support workflows.

Future opportunities include revision agents for individual subjects, additional mock-exam workflows, lecturer-reviewed marking assistance, course summarisation, and agents designed to identify common areas where students require more support.

As the implementation develops, student and staff feedback can be used to refine agent instructions, expand approved knowledge bases, and introduce new AI-supported learning experiences.