What was the impact of the AI solution?

The platform improved accessibility to social benefit information and empowered vulnerable families and social workers with better tools to navigate available support. It enhanced SCE's policy advocacy by providing data-driven insights from app usage and offered a scalable solution for broader public sector adoption. The use of Amazon Bedrock and AWS AI services created a transformative solution addressing a complex social issue with generative AI and intelligent search.

Source

Evidence: Low25/100

Save the Children España Simplifies Social Benefit Access with Amazon Bedrock Generative AI

Use case typeConversational supportUpdated Jun 13, 2026

Save the Children España (SCE) tackled the challenge of high non-take-up rates of social assistance benefits such as Minimum Vital Income (IMV) in Spain caused by lack of awareness and application difficulties. They developed a multilingual web application featuring a chat-based AI assistant that delivers localized, context-sensitive information about social benefits to families and provides support to social workers. The solution integrates multiple AWS AI services including Amazon Bedrock for generative large language models, Amazon Kendra for intelligent document indexing and search, Amazon S3, DynamoDB, AWS Lambda, and API Gateway, creating a scalable, extensible platform.

Organization: Save the Children España
Industry: Public Sector
Location: Spain
Published: October 2025

Reported outcomes

Strategic outcomes

Customer experience & trustImproved access to social benefit informationBetter decisions & insightProvided data-driven policy insightsScale & capacityCreated a scalable public-sector solutionNew product / capabilityBuilt a multilingual AI benefits assistant

Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks

Customer: Save the Children España
Provider: AWS
Maturity: Unknown
Linked source: AWS Blog

No explicit deployment-stage evidence found.

Customer identity supportedSource describes one deploymentMaturity evidence evaluated

Primary read

Use case focus

Showing 3 of 3

1Generative AI
2Conversational AI
3Social Services

The main challenge was addressing the non-take-up phenomenon where many eligible families do not receive social benefits due to lack of awareness and complexity in application processes, especially for IMV in Spain which had a 58% non-take-up rate in 2022.

SCE built a free multilingual web app providing comprehensive social benefit information and an intelligent chat assistant powered by Amazon Bedrock LLMs.
The app utilizes Amazon Kendra for natural language semantic search over indexed documents consolidating local and regional government agencies' social program information.
The system handles multiple user roles and permissions, allowing administrators to update and maintain the knowledge base, and supports multiple languages to maximize accessibility.

Technologies

Amazon Bedrock Amazon Kendra Amazon S3 DynamoDB AWS Lambda Amazon API Gateway

The platform improved accessibility to social benefit information and empowered vulnerable families and social workers with better tools to navigate available support.
It enhanced SCE's policy advocacy by providing data-driven insights from app usage and offered a scalable solution for broader public sector adoption.
The use of Amazon Bedrock and AWS AI services created a transformative solution addressing a complex social issue with generative AI and intelligent search.

Architecture

The architecture includes a React-based frontend using AWS Amplify and Amazon S3 for static assets, Amazon API Gateway and AWS Lambda functions for backend services, DynamoDB for data storage, Amazon Kendra for document indexing and search, and Amazon Bedrock for generative AI processing. AWS WAF protects against web exploits, and the system supports multiple languages and user roles for social workers and administrators.

Sources & evidence1

Evidence: Low25/100Evidence strength