Making Learning Personlized and fun, with unique AI Technology

Building Institutional Intelligence: Capturing Organisational Knowledge in Education

Intro summary – Client & outcome. A large university with tens of thousands of students and staff struggled to provide consistent answers to administrative questions and to help new staff navigate its complex policies. By consolidating disparate knowledge repositories into a single AI‑powered knowledge hub with generative search, the university reduced average inquiry‑handling time by 14 % and improved user satisfaction by 3%

1 Context & Challenge

Before the project, information about university policies, procedures, course requirements and support services was scattered across SharePoint sites, intranets and departmental wikis. New staff and students found it difficult to locate reliable answers. Support agents (e.g., in the registrar’s office) spent significant time searching for information across multiple systems, leading to long wait times and inconsistent responses.

2 Goal / Success criteria

• Consolidate knowledge. Integrate content from disparate repositories into a single, searchable knowledge hub.

• Enable conversational access. Provide an AI assistant that can answer questions using natural language and cite sources.

• Improve service metrics. Reduce average handle time for inquiries and increase satisfaction scores.

3 Approach / Implementation

• Content migration. The project team migrated ~2,500 documents (policies, FAQs, procedures) from SharePoint, intranets and CRM systems into a central knowledge base.

• Generative AI search. A generative AI module (“Instant Answers”) was added on top of the knowledge hub. The model synthesised answers from multiple documents and cited sources, enabling staff and students to ask questions in plain language.

• Role‑based access and compliance. Access controls ensured that sensitive data (e.g., HR policies) were only accessible to authorised staff. The system met strict security and compliance requirements.

4 Outcomes & Metrics

In a 30‑day pilot with ~60 support agents, the university saw measurable improvements:

• Reduction in handle time. Average inquiry‑handling time dropped by 14%

• Satisfaction increase. User satisfaction scores (measured through surveys) improved by 3%.

• Compliance success. The solution passed 100 % of the evaluation requirements, including functionality, user experience, security and compliance.

5 Challenges & Lessons Learned

• Content hygiene. Ensuring that documents are up to date and well‑structured is essential for generative search to work properly.

• User trust and adoption. Staff initially cross‑checked AI‑generated answers manually; trust grew as the system consistently cited accurate sources.

• Contextualising responses. The AI sometimes provided generic answers without understanding campus‑specific nuances; fine‑tuning and prompt engineering helped improve relevance.

6 Next Steps / Extensions

The university planned to extend the knowledge hub to include academic advising content and student‑support resources. The generative AI layer could be integrated into chatbots and voice assistants for 24/7 support.

Tools and Architectures Highlighted

Key tools included a central knowledge‑management platform, generative AI search (Instant Answers), role‑based access controls, and integration with legacy systems. These components created an institutional intelligence layer that captures and surfaces tacit knowledge across the organisation.

Source

Disclaimer: The case studies presented here are for illustrative purposes only and are based on publicly available information. They do not represent projects executed by Zynolabs and are intended solely to demonstrate the types of AI solutions and outcomes that could be achieved in comparable scenarios.