Building Agentic AI Applications on AWS
How to Build Agentic AI Applications on AWS with OpenSearch, S3 Vectors, Bedrock and AgentCore
Join BigData Boutique and AWS for a free workshop on building secure, enterprise-grade agentic AI applications — from the retrieval foundations that keep agents grounded, to the end-to-end architecture that lets them reason and act.
Classic RAG (Retrieval Augmented Generation) is hitting a wall and agentic workloads are evolving to remediate that. Any agent needs to perform information retrieval, to ground itself on organization sources of truth, be contextual, and avoid hallacinations. As organisations move from answering questions to building goal-directed agents that execute on behalf of the business, the demands on the underlying retrieval and orchestration layers change completely.
This half-day workshop maps out what it actually takes to get there on AWS — using Amazon OpenSearch Service for keyword + vector semantic search, S3 Vectors, Amazon Bedrock, and Bedrock AgentCore — grounded in real production experience rather than slideware.
Seats are limited. Reserve your spot today.
Agenda
- 08:30 – 09:00 — Breakfast & Networking
- 09:00 – 09:30
Opening Keynote: The Shift to Autonomy with Retrieval Foundations
We look at why classic RAG (Retrieval-Augmented Generation) is hitting a wall, the rise of goal-directed AI agents, and what it takes to build a secure, enterprise-grade retrieval foundation. - 09:30 – 10:30
From Legacy Search to AI-Powered Product
An accessible introduction to vector search, semantic search and hybrid search, including a deep dive into Amazon OpenSearch Service. Learn how hybrid search — combining vector embeddings with keyword precision — creates the highly accurate context data that agents rely on to function without hallucinating. - 10:30 – 10:45 Coffee Break
- 10:45 – 11:15
Customer Spotlight: Solving for Scale
A live enterprise case study. See how a peer organisation successfully leveraged OpenSearch to power their production AI workloads, showcasing real metrics, data challenges, and lessons learned. - 11:15 – 12:00
Advanced Architecture: Building Agentic Apps on AWS
Moving from simple search to active execution. We map out the end-to-end blueprint of how Amazon OpenSearch interacts with Amazon Bedrock AgentCore, detailing memory persistence, reasoning loops, and guardrails. - 12:00 – 12:15 — Debrief, Q&A & Next Steps
- 12:15 – 13:00 — Lunch & Open Discussion
Who Should Attend
This workshop is designed for builders and decision-makers who want to move beyond GenAI hype and ship production-grade agentic systems on AWS.
- Developers & ML Engineers ready to build agents that act, not just answer
- Cloud & Solution Architects designing retrieval and agent infrastructure on AWS
- Platform & Data Engineers running OpenSearch and vector workloads in production
- Innovation & Engineering Leaders turning agentic AI into real business value
What You'll Take Away
- A clear view of why classic RAG breaks down and what a secure retrieval foundation looks like
- Practical patterns for hybrid search on Amazon OpenSearch Service and S3 Vectors
- A real-world enterprise case study with metrics, challenges, and lessons learned
- An end-to-end blueprint for agentic apps on Amazon Bedrock AgentCore — memory, reasoning loops, and guardrails
- Direct access to BigData Boutique architects and AWS experts throughout the day
About BigData Boutique
We are a team of Big Data and ML/AI experts, with over 15 years of experience - providing end-to-end consulting services for modern data platforms.
BigData Boutique has achieved the Amazon Web Service (AWS) Service Delivery designation for Amazon OpenSearch Service, recognizing that BigData Boutique has deep technical knowledge, experience, and proven success in delivering Amazon OpenSearch Service to customers.
Follow the sun availability with varying SLAs for production incident response and a shared Slack channel, to ensure smooth operation of your data clusters.