Overview

Intelligent Summarization feature will automatically summarize long forms of text, or multiple text documents (e.g., years of advisor notes, transcripts, and lecturer-student interaction reports) into a short summarization snapshot, saving advisors plenty of prep time prior to a student appointment.

This article will take reader's through a common use case of this feature.

Use Case

In many education institutions, student behaviour and academic progress are often recorded across multiple terms. As time passes, the records become lengthy and difficult for faculty members or admins to review efficiently.

The AI Student Summary feature enables users to generate a structured summary by sending student behaviour and academic data from RIO Education to a Large Language Model (LLM). The LLM then produces a concise overview of the student’s progress, key incidents, intervention history, and improvement trends.

This helps staff quickly understand the student’s overall situation without manually reading through multiple term logs.

The Problem and Consequences

A Faculty member spent too much time reviewing a student's support notes as a student can contain up to many terms of support notes. This could take up days or even weeks of the faculty member's time causing a low efficiency for the faculty member's task.

Faculty members can also get tired overtime trying to read the support notes and will have the chance of giving a wrong or inaccurate summary if under the affect of emotions like irritation.

The solution 

AI feature is introduced to help battle against the issue. AI can help to reduce the time required for faculty members to read through the term log bit by bit. AI can help to summarise all the term logs together and give a summary based on the student's support notes.

In short, AI saves time, produces stable results and saves cost.

Scenario

In this scenario, A student named James Smith who have studied over 2 and a half years and accumulated more than 10 Support notes. Each of these notes contain different comments from different staff. 

In a usual scenario, it will take up to days or maybe even weeks to read through every single one of them and summarise them up. The end result could also be inaccurate if it was summarised by a faculty member who is biased towards a specific students.

In such case, AI summarisation solves all the issues mentioned. The summarisation provided by AI is fair and unbiased as everything is summarized based on a fixed prompt by staff.

The AI analysis button will be located at the contact page. A click will call out the AI payload details. Staff can view the payload request and confirm to proceed.

After a few seconds, the result will be displayed with the summary.
 

Although the summary wording results might seem different each time, all of them share the same meaning, which is still in a form of consistency.

User Workflow

Users can generate a student summary directly from the Student Profile page. By clicking Generate AI Summary, the system gathers relevant records across multiple terms and sends them to the configured LLM.

The AI then returns a structured summary highlighting key behavioural patterns, academic progress, and intervention outcomes. This output is displayed instantly in Salesforce and can optionally be saved as a report or case note for future reference.

This allows staff to review a student’s full journey within minutes, instead of manually reading dozens of term-based entries.

Output and Benefits

The AI output provides a clear, professional summary that includes:

• behavioural and engagement trends across terms
• major incidents and risk indicators
• intervention plans and outcomes
• current progress status and recommended follow-up focus

This feature delivers operational value by reducing staff review time, improving consistency in reporting, and supporting earlier intervention for at-risk students. It also improves collaboration between departments, as academic advisors and faculty members can quickly align on a student’s situation using the same consolidated summary.

Although AI-generated summaries should still be reviewed by staff for accuracy, the feature significantly improves efficiency and ensures key information is not missed during student evaluations.

Estimated Cost - Per Request

For the latest pricing, please refer to GPT-4.1 API pricing (official)

Token calculation is based on OpenAI Tokenizer.

Request (Input)

Price (as of Jan 2026): $2.00 per 1,000,000 tokens
Calculated based on 12148 characters. 3881 tokens

Input Cost = 3881 x $2.00 / 1,000,000 = $0.007762

Response (Output)

Price (as of Jan 2026): $8.00 per 1,000,000 tokens
Calculated based on 1089 characters, 197 tokens

Output Cost = 197 x $8.00 / 1,000,000 = $0.001576

Input (Request) cost for 500 tokens (GPT-4.1)
500 tokens × ($2 / 1,000,000) = $0.001424

Total Cost: <$0.01