Generative AI on AWS for AI-Powered Report Card Remarks & Parent Progress Summaries

Converg-INAWSGenerative AI
Case Study · Education Technology

Generative AI on Amazon Web Services (AWS) for AI-Powered Report Card Remarks & Parent Progress Summaries

01About Client

IndiSage is a cloud-based School Resource Planning (SRP) solution developed by Capternal Systems Pvt. Ltd., Pune. It supports preschools, K-12 schools, international schools, colleges and multi-campus education groups across India.

The solution provides web and mobile experiences for school administrators, teachers, students and parents, covering student and teacher profiles, attendance, fees and payments, transport tracking, timetables, examinations, homework, learning content, quizzes, behavior records, library, payroll, leave, documents, certificates and smart notifications.

IndiSage engaged Converg-IN to introduce Generative Artificial Intelligence (AI) capabilities on Amazon Web Services (AWS) using Amazon Bedrock to reduce teachers’ manual workload and provide parents with clearer, personalized insight into student progress while maintaining a cost-optimized AWS consumption model.

02Business Need

At the end of every term, teachers manually prepare individual report-card remarks for students. With classes of around 30–50 students and multiple classes per teacher, this becomes a time-consuming activity, and remarks can become generic or repetitive.

Parents receive marks and grades but may have limited plain-language context about a student’s strengths, improvement areas and practical next steps. There is also a need for regional-language communication for parents who prefer languages such as Hindi or Marathi.

The solution therefore needed to generate high-quality, data-grounded drafts from information already available in IndiSage, keep teachers in control of what is published, protect student data and operate within a predictable, low-cost AWS envelope.

03Proposed Solution

AI Report Card Remarks & Parent Progress Summary

Converg-IN designed and implemented a Generative Artificial Intelligence (GenAI) workflow that uses existing student data to generate personalized report-card remarks and parent-friendly progress summaries.

Student marks, attendance, homework completion, quiz scores and behavior records are retrieved from IndiSage.
Student names and contact details are removed before data is sent to the Generative Artificial Intelligence (GenAI) layer; internal IDs are used instead.
AWS Lambda (Lambda) prepares structured student data and invokes Amazon Bedrock using the MiniMax model.
The model generates concise remarks covering strengths, an improvement area and a practical suggestion, together with a short parent summary.
English and regional-language summaries, including Hindi and Marathi, are supported.
Amazon Bedrock Guardrails check generated content for harmful, biased, demeaning or restricted content.
AI drafts are stored in Amazon DynamoDB for teacher review. Teachers can edit, approve or reject every draft before publication.
Deployments are automated via AWS CloudFormation stack.
Approved content is written back to the IndiSage report card.

Responsible AI, Security & Cost Optimization

Teacher-in-the-loop approval ensures no AI-generated remark is published automatically.
Outputs are grounded only in the student data supplied by IndiSage and validated before saving.
Amazon Bedrock Guardrails provide content and sensitive information controls.
Least-privilege AWS Identity and Access Management (AWS IAM), AWS Key Management Service (AWS KMS), AWS CloudTrail and Amazon Bedrock model invocation logging support security and auditability.
The Generative Artificial Intelligence (GenAI) layer is serverless and pay-per-use, with AWS Budgets and AWS Cost Anomaly Detection used for cost governance.
The target monthly AWS GenAI and related components consumption is approximately USD 150–200.

04AWS Services Used

CategoryAWS Services / Technologies
Generative AIAmazon Bedrock with MiniMax model, Amazon Bedrock Guardrails
ComputeAWS Lambda (Lambda); Amazon Elastic Container Service (Amazon ECS) with AWS Fargate (Fargate)
Container RegistryAmazon Elastic Container Registry (Amazon ECR)
DatabaseAmazon Relational Database Service (Amazon RDS) for MySQL; Amazon DynamoDB (DynamoDB)
StorageAmazon Simple Storage Service (Amazon S3) for student datasets, versioning, Server-Side Encryption with Amazon S3-Managed Keys (SSE-S3), public access blocking, and bucket policies
NetworkingAmazon Virtual Private Cloud (Amazon VPC), Internet Gateway (IGW), public subnets, route tables, routes, security groups (SG), AWS Cloud Map (Cloud Map) for service discovery
API ManagementAmazon API Gateway (API Gateway), Representational State Transfer Application Programming Interface (REST API), AWS Identity and Access Management (IAM) authorization, request throttling, AWS Lambda integration
Security & IdentityAWS Identity and Access Management (AWS IAM), IAM roles and policies, least-privilege access, Amazon Simple Storage Service (Amazon S3) Block Public Access (BPA), Hypertext Transfer Protocol Secure (HTTPS) transport enforcement, AWS Key Management Service (AWS KMS), AWS Security Hub, Amazon Inspector
Monitoring & GovernanceAmazon CloudWatch Logs (CloudWatch Logs), CloudWatch Container Insights for Amazon ECS, container health checks, AWS Lambda logs, AWS CloudFormation, AWS CloudTrail, Amazon Bedrock model invocation logging
Backup & RecoveryAmazon S3 Versioning, Amazon S3 resource retention policies, Amazon Relational Database Service (Amazon RDS) automated backups with a 7-day retention period
Application DeploymentAWS CloudFormation, Amazon Elastic Container Registry (Amazon ECR) image scanning, immutable container image tags, Amazon Elastic Container Service (Amazon ECS) deployment circuit breaker and rollback
Cost ManagementAWS Budgets, AWS Cost Explorer, cost allocation tags

05AWS Deployment Architecture

06Business Benefits / Quantitative Outcome:

Up to 70%
reduction in teacher effort spent drafting report-card remarks.
80%
faster report-card preparation during peak term-end periods.
English, Hindi & Marathi
multilingual parent communication.
100%
teacher approval before any AI-generated content is published.
Cost-optimized
GenAI solution using serverless AWS services and Amazon ECS tasks.

07About Converg-IN Private Limited:

Converg-IN offers cost-effective cloud solutions using industry-leading design principles and best practices. Converg-IN Private Limited is an AWS Advanced Consulting Partner that delivers cost-effective cloud and Generative AI solutions built on AWS Well-Architected Framework principles. Our team of 15+ certified cloud architects covers the full cloud lifecycle: consulting and cost optimization, migration (including SAP and VMware), security, modernization, DevOps, and 24x7 managed services.

Our Modernization & GenAI practice helps customers move Generative AI from experimentation to production using Amazon Bedrock and the wider AWS artificial intelligence and machine learning (AI/ML) services stack. We have delivered GenAI workloads for customers in sports technology, education, life sciences analytics, and AI-driven contact centers. We design every solution to be simple to deploy, secure by default, and cost-efficient to operate.

We deliver with an automation-first approach, using AWS CloudFormation to provision environments quickly and repeatably. Security and governance are central to every engagement. With a proven track record across industry verticals, Converg-IN is a trusted partner for organizations adopting Generative AI on AWS.

Not sure what fits your business needs?
Get free consultation!

Experience you can trust, service you can count on.

More Case Studies