Engagement Overview
The Edward M. Kennedy Institute supports civic education and public programming. Its Tactical Edge engagement centered on migrating legacy infrastructure to AWS and modernizing selected applications that support digital experiences and internal operations.
The Challenge
- Understand legacy infrastructure dependencies before moving public-facing and internal applications.
- Match compute and database capacity to actual workload needs.
- Plan content delivery, backups, monitoring, and operational ownership alongside the migration.
The Approach
- Assess the existing estate and sequence workloads into migration and modernization steps.
- Match application, storage, and database needs to suitable AWS services.
- Include recovery planning, security controls, monitoring, and cost visibility in the operating model.
What Changed
The engagement established an AWS infrastructure and application-modernization path for the Institute's digital services. Operational readiness depends on application testing, recovery checks, and a clear handoff to the team that runs the environment.
AWS Agentic AI Capability Extension
The following architecture describes capabilities that could extend this engagement's workflow. It distinguishes possible additions from the original customer work.
An educational-content assistant could help staff locate an approved program resource, summarize its teaching context, and prepare a draft response to a visitor or educator. Editors would review public-facing material before publication.
| Service | Role in the extension |
|---|---|
| Amazon Bedrock | Draft summaries and staff responses from approved educational and program material. |
| Bedrock Knowledge Bases | Search curated teaching resources and operating documents, returning supporting sources. |
| AgentCore Runtime and Gateway | Read program details or prepare an internal content task through approved application APIs. |
| AWS workflow services | Use Lambda for application integrations and Step Functions for editorial approvals, with CloudWatch for workflow monitoring. |
AgentCore can host an application's agent and expose approved tools through Gateway, with Identity for service access and Observability for execution traces. The application defines its tool permissions, validation, and approval steps.[1]
Bedrock Knowledge Bases can retrieve relevant source material and include citations in generated responses. Select the retrieval configuration and apply the source content's access rules before supplying it to a model.[2]
Existing Amazon Bedrock Agents deployments can use action groups and knowledge bases for orchestration. AWS now calls this service Bedrock Agents Classic and has closed it to new customers; new agent implementations should evaluate AgentCore.[3]
Bedrock Guardrails offers configurable content, sensitive-information, and grounding checks. Test the selected checks against representative requests and keep authorization and human approvals in the application workflow.[4]
Operating Boundaries and Evaluation
Keep public educational content distinct from staff-only and student information. Apply retrieval permissions before model use and retain editorial approval for publication.
Evaluate source accuracy, citation coverage, staff task completion, editorial corrections, accessibility, and the cost of each supported workflow.
AWS References
These references document the extension's AWS capabilities.
- Amazon Bedrock AgentCore overview. https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/what-is-bedrock-agentcore.html
- Amazon Bedrock Knowledge Bases. https://docs.aws.amazon.com/bedrock/latest/userguide/knowledge-base.html
- Amazon Bedrock Agents Classic. https://docs.aws.amazon.com/bedrock/latest/userguide/agents.html
- Amazon Bedrock Guardrails. https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails.html