GCC Chatbot: Scouting America

Overview

The Arizona State University Artificial Intelligence Cloud Innovation Center (AI CIC), powered by Amazon Web Services (AWS), collaborated with Scouting America’s Grand Canyon Council (GCC) to prototype an AI-assisted volunteer support assistant for GCC’s network of adult leaders. Serving approximately 3,000 registered adult volunteers across Arizona, the project focused on placing trusted council and national resources in one accessible location. The prototype was designed as a mobile-first assistant to support consistent program delivery while maintaining human escalation pathways for safety-sensitive and complex situations.

Problem

GCC’s existing support framework places technology as the first ring of assistance surrounding unit leaders. GCC volunteer leaders increasingly want to interact with digital tools first to resolve routine questions, particularly outside normal business hours during evenings and weekends.

Volunteers frequently need quick answers regarding policy, safety, training, registration, council procedures etc. Previously, answers depended on availability and individual contacts, creating friction for volunteers, consuming staff time on repetitive inquiries, and raising the risk of inconsistent guidance. As a local non-profit, GCC required a practical and cost-conscious system that strictly constrains answers to approved source materials without relying on open-internet content.

Student Spotlight

Approach

A mobile-first serverless volunteer support assistant on AWS was built with core flows spanning public retrieval-augmented chat, bounded document ingestion, and administrative oversight.

  • AI & knowledge grounding: Amazon Bedrock Knowledge Base backed by S3 Vectors uses Claude Haiku 4.5 and Titan Text Embeddings v2 to generate Markdown answers grounded strictly in approved GCC policies and Scouting America documents, complete with source citations.
  • User experience: Mobile-first installable Progressive Web App (PWA) with bilingual English and Spanish support, voice input, text-to-speech, local chat history, light/dark themes, and text-size accessibility controls.
  • Safety & escalation: Bedrock Guardrails and custom Lambda logic monitor incoming queries, automatically routing out-of-scope, low-confidence, or safety-sensitive topics to GCC staff via Amazon SNS and Amazon SES alerts.
  • Content ingestion & admin: Amazon Cognito-protected dashboard allows administrators to perform size-enforced document folder uploads, monitor usage metrics, review rated feedback, and process source updates through a bounded SQS worker queue.
  • Infrastructure (AWS): Next.js static export deployed to a private S3 origin behind CloudFront, API Gateway, Lambda, DynamoDB for chat logs, Object-Locked S3 archives for audit logs, CloudWatch alarms, and infrastructure defined via AWS CDK.

Industry Impact and Problem Solving

For safety-sensitive or high-risk topics, this solution maintains clear guardrails by prioritizing immediate escalation to human contacts. By providing 24/7 access to approved Scouting America and GCC resources, the tool reduces repetitive support requests and staff interruption load, improves answer consistency, and reveals recurring areas of volunteer confusion through usage analytics. 

 

This project is a great example of what happens when you combine a nonprofit's deep mission expertise with AWS cloud technology and the energy of ASU student innovators. GCC's volunteers now have a trusted AI assistant that's available 24/7, grounded in approved resources, and designed with the safety guardrails that working with youth requires. We're excited to see this model expand across the Scouting movement and beyond.

— Joe Ruprecht, Global Account Executive, Amazon Web Services 

 

Scouting is delivered by volunteers, and our responsibility is to make it as easy as possible for them to get the information and support they need, when they need it. Working with the ASU AI Cloud Innovation Center and AWS helped us take that challenge and turn it into something tangible. Compass demonstrates how AI can put trusted information at a volunteer’s fingertips while preserving the human relationships and judgment that are essential to Scouting. Just as important, this collaboration helped us think differently about how technology can strengthen the volunteer experience and ultimately allow our leaders to spend more of their time delivering great experiences for young people.

Andy Price, Scout Executive/CEO, Grand Canyon Council, Scouting America

Potential for Wider Application

While built for the Grand Canyon Council, this prototype can be adapted across other local Scouting councils, non-profits, and volunteer-driven organizations. Its modular architecture enables expansion into adjacent operational workflows such as leader training, registration, and event systems, offering a flexible model for organizations requiring bounded document intelligence and human escalation pathways.

Supporting Artifacts

Github LinkClick Here

 

Next Steps

Grand Canyon Council’s next step is to move Compass from prototype to practice deliberately. We plan to begin with a limited internal beta, expand to a pilot with selected volunteer leaders, and then move toward broader deployment as we validate accuracy, usability, governance, and the effectiveness of our human escalation pathways. The project has also broadened our thinking about AI. We began with a specific question—how can we help volunteers find trusted answers more easily?—but the experience demonstrated a much larger opportunity to use AI to reduce friction throughout the volunteer journey. We see Compass not as a replacement for staff or experienced volunteer leaders, but as another layer of support that can make their expertise more accessible and allow people to focus their time where human relationships, judgment, and leadership matter most. As we learn from actual volunteer use, we expect those lessons to inform how the Grand Canyon Council thoughtfully applies AI to other aspects of our work. 

About the ASU CIC

The ASU Artificial Intelligence Cloud Innovation Center (AI CIC), powered by AWS, is a no-cost design thinking and rapid prototyping shop dedicated to bridging the digital divide and driving innovation in the nonprofit, healthcare, education, and government sectors. 

Our expert team harnesses Amazon’s pioneering approach to dive deep into high-priority pain points, meticulously define challenges, and craft strategic solutions. We collaborate with AWS solutions architects and talented student workers to develop tailored prototypes showcasing how advanced technology can tackle operational and mission-related challenges. 

Discover how we use technology to drive innovation by visiting ASU AI CIC or contacting [email protected]

Photos