Higher education dreamy island in the clouds

Higher Education

This is the higher education island with open-source solutions tied to this vertical.

Job Matching Agent

This prototype uses AI-driven matching algorithms to connect students with relevant job postings from Handshake and other online sources. The web-based interface allows students to upload résumés, set career preferences and instantly view personalized recommendations ranked by skill alignment and location fit. Unlike traditional search tools that rely on static inputs and outputs, the interactive chat-style design encourages a conversational back-and-forth experience — an approach students tend to prefer because it keeps them more engaged in their career exploration.

Services used:

  • Amazon Bedrock provides generative AI capabilities to interpret résumés and extract relevant skills
  • AWS Lambda automates back-end logic for data processing and job-matching operations
  • Amazon S3 securely stores anonymized data sets and processed job information
  • Amazon API Gateway manages secure communication between the user interface and back-end functions
  • Amazon DynamoDB maintains structured records of user preferences and job data for quick retrieval
  • AWS Amplify hosts the web application, enabling fast iteration and deployment.

Visit the blog to learn more and access the open-source code.

student at computer with hired in thought bubble

Admissions Agent

This multilingual AI admissions agent provides personalized, step-by-step support throughout the student application process. Designed for accessibility and scalability, the agent guides users through program discovery, application requirements, visa preparation, and follow-up communication—offering localized experiences.

The system design incorporates several key AWS services to support automation and integration.

  • Amazon Bedrock for large language model implementation
  • AWS Lambda and API Gateway for orchestrating backend workflows
  • Amazon DynamoDB for managing student interaction data
  • Amazon Translate for multilingual engagement
  • AWS Amplify for hosting and deployment

The AI agent was developed with a mobile-first design, emphasizing empathy, cultural awareness and transparency. It is structured to integrate future messaging platform support, such as WhatsApp, enabling students to access guidance in their preferred language and medium.

Visit the blog to learn more and access the open-source code.

student imagining graduation

Smart Outreach Hub

College athletic departments face significant challenges in efficiently engaging their vast networks of potential ticket buyers, alumni, and donors due to manual outreach limitations that prevent them from maintaining personalized interactions while dramatically increasing their reach. 

Components Built: 

  • AI-powered conversational interface for conducting natural language SMS dialogues
  • CSV lead list processing system
  • Automated scheduling integration for converting prospects to sales meetings
  • Intelligent workflow management system to determine when to maintain automated engagement versus escalating to human representatives
  • Event-driven architecture for automatic scaling
  • Integration capabilities with existing CRM systems
  • Customizable conversation flows

Core AWS Services Used:

  • AWS CDK – Infrastructure as code for deployment and resource provisioning
  • Amazon Bedrock – Provides access to Claude Sonnet 4 for AI-powered conversations
  • AWS Lambda – Serverless compute for handling campaign processing, message processing, and API endpoints
  • Amazon DynamoDB – NoSQL database for storing campaigns, customers, messages, and conversation history
  • AWS End User Messaging – Manages origination phone numbers and SMS sending/receiving
  • Amazon Simple Queue Service (SQS) – Message queuing for campaign distribution and inbound message processing
  • Amazon Simple Notification Service (SNS) – Routes incoming SMS messages to processing queues
  • Amazon API Gateway – HTTP API endpoint for GraphQL backend
  • Amazon Cognito – User authentication and authorization for sales team members
  • AWS Amplify – Hosts and deploys the React frontend application
  • Amazon CloudWatch – Logging and monitoring (mentioned in pricing section)AWS CDK (Cloud Development Kit) for infrastructure deployment

The solution successfully automated initial contact and qualification processes while maintaining personalized interactions, demonstrating the ability to handle thousands of concurrent conversations cost-effectively through AWS’s pay-per-use pricing model.

Visit the blog to learn more.

Access the Github repository

Automatic Highlight Reel Generator

Collegiate athletics coaches spend significant time manually reviewing practice footage (approximately 10 hours weekly for the University of Pittsburgh diving team), which limits their ability to focus on direct athlete development and creates a critical need for automation in sports video processing. 

Components Built:

  • Zero-shot vision-language model (VLM) for automated video processing
  • Automated detection system for identifying individual dives from continuous footage
  • Highlight reel generation system that processes 2.5-hour practice sessions
  • Open-source framework designed to handle real-world constraints (single-angle footage, background activity, water reflections)

The solution was powered by several key AWS services:

• Amazon S3 – Primary storage for video uploads (videos/ prefix) and processed results (results/ prefix)

• AWS Lambda – Orchestration service that triggers when videos are uploaded to S3 and launches the processing pipeline

• Amazon ECS – Container orchestration service that runs the video processing tasks using Docker containers

• Amazon EC2 – Provides GPU-enabled instances (specifically g4dn.2xlarge with NVIDIA T4 GPU) for the compute-intensive video analysis

• Amazon ECR – Container registry for storing the Docker images containing the video processing application

• AWS CDK – Infrastructure as Code framework used for deploying and managing all the AWS resources

The architecture follows an event-driven pattern where S3 upload events trigger Lambda functions, which then launch containerized processing jobs on GPU-enabled EC2 instances through ECS, making it a scalable and cost-effective solution for automated video processing.

Visit the blog post to learn more.

Access to the GitHub repository.

Illustration showing a large screen with a video being edited.

Diving Analytics Platform

Competitive diving coaches traditionally rely on manual data entry and analysis of athlete performance metrics, creating significant time barriers to providing timely feedback and identifying performance trends, with coaches at the University of Pittsburgh spending approximately 10 hours per week on data entry alone. 

Components Built to Address the Problem:

  • Serverless web application with optical character recognition (OCR) and large language models (LLM)
  • Automated data extraction and processing system for handwritten dive logs
  • User-friendly interface accessible via mobile devices
  • Dynamic performance dashboards with calendar views
  • Color-coded session quality indicators
  • Customizable analytics features
  • Automated data processing triggers
  • Exportable datasets for deeper analysis 

Core AWS Services Used:

  • AWS CDK – Infrastructure as Code for deploying and managing all AWS resources
  • Amazon Bedrock – AI/ML service for automated analysis of diving scoresheets and performance data extraction
  • AWS Lambda – Serverless functions for processing uploaded images and handling backend logic
  • Amazon DynamoDB – NoSQL database for storing diver profiles, training data, and performance metrics
  • Amazon S3 – Object storage for uploaded training scoresheet images and other files
  • AWS Amplify – Frontend hosting and deployment platform for the React application

The solution successfully eliminated manual data entry requirements and reduced weekly administrative workload by approximately 10 hours while providing real-time performance tracking and analysis capabilities.

Link to GitHub repository

Visit the blog to learn more.

GenomicsMapper

In today’s rapidly evolving public health landscape, standardizing genomic data for federal submissions poses a significant challenge for laboratories. GenomicsMapper addresses this by leveraging generative AI to automate the translation of laboratory-specific genomic terminologies into standardized formats required by national repositories.

The innovative solution uses natural language processing to match diverse local terminologies with standardized NCBI BioSample definitions, significantly reducing manual processing time and improving submission accuracy.

AWS services used:

  • Amazon Bedrock
  • AWS Lambda
  • Amazon API Gateway
  • Amazon S3
image of DNA coils in blue with red background

Procurement Scope Builder

In today’s complex procurement landscape, creating comprehensive and accurate statements of work scopes can present a challenge for university procurement teams. Scope Builder uses generative AI to assist procurement specialists during the work scope development process, helping them produce detailed and comprehensive documents. Through a conversational AI interface, the system guides users through the process of creating work scopes, drawing from established best industry practices and relevant past contracts.

AWS services used:

  • AWS Lambda
  • Amazon API Gateway
  • Amazon Cognito
  • Amazon S3
  • Amazon Bedrock

cartoon like human sitting at a desk with a computer screen and small robots fluttering overhead.

PDF Accessibility

Many organizations have document collections containing hundreds of thousands of PDF documents, many of which do not meet the Web Content Accessibility Guidelines (WCAG) 2.1 Level AA standards, making it difficult or impossible for individuals relying on assistive technologies to access those documents. To address this issue, the ASU Cloud Innovation Center developed an innovative, artificial intelligence-driven solution designed to remediate documents. Some readily available remediation solutions cost $3-$15 dollars per page, but with this solution, expenses for AWS services are less than a penny per page.

AWS services used:

  • Amazon S3: Used to securely store and manage the documents being remediated
  • AWS Lambda: Automates the file processing workflows
  • ECS (Fargate): Handles document processing efficiently
  • AWS Step Functions: Coordinates the various processes involved in splitting, processing, and merging documents
  • Amazon Bedrock: Generates alt text for images and charts using advanced LLM capabilities

This solution also integrates Adobe Auto-Tag APIs which are designed to automatically clean metadata, apply appropriate tags, and further enable document remediation. 

More information:

An illustration of a robot looking at a piece of paper