A live record of certifications, courses, training, and awards — pulled directly from the source of truth.

Introduction to Amazon Bedrock Guardrails, including configuring content filters, word filters, and PII redaction policies to mitigate harmful or off-policy outputs from foundation models.

This comprehensive course equips developers with advanced techniques for optimizing response times for Large Language Model (LLM) applications using Amazon Bedrock. Through hands-on instruction and practical examples, students will master the intricacies of prompt caching, latency optimization, and intelligent routing strategies essential for building high-performance AI applications.

This training is meant for data engineers and GenAI application developers who want to integrate tools while using Amazon Bedrock (Bedrock) Foundation Models (FM). Upon completing this training, you will understand the concepts of tool integration, the framework used by Bedrock, and best practices for integrating tools with Bedrock.

Hands-on tutorial covering Amazon Bedrock AgentCore Gateway, which converts existing APIs and tools into agent-ready capabilities. Walks through configuring inbound and outbound auth, exposing tools to agents, and managing tool catalogs.

Introduction to Amazon Bedrock AgentCore, AWS's platform for deploying and operating AI agents at scale. Covers the runtime, gateway, memory, identity, observability, and tools components, and how they work with frameworks such as LangGraph, CrewAI, and Strands.

Tutorial on Amazon Bedrock AgentCore Identity, which handles agent authentication and access management. Covers integration with existing identity providers, OAuth-based delegation, and securely scoping agent permissions to downstream services.

Tutorial on Amazon Bedrock AgentCore Memory, the managed service for persistent agent context. Covers short-term and long-term memory stores, summarization strategies, and how to maintain personalized state across multi-turn agent interactions.

Tutorial on Amazon Bedrock AgentCore Observability, which provides built-in metrics, traces, and logs for AI agents. Covers monitoring runtime, gateway, memory, and identity components and integrating telemetry with CloudWatch and OpenTelemetry-compatible backends.

Tutorial on the Amazon Bedrock AgentCore Runtime, a secure serverless environment for hosting agents. Covers deploying agents, isolating sessions, and using built-in primitives such as the secure browser and code interpreter.

Tutorial covering AgentCore's built-in tools, including the secure browser runtime and code interpreter. Walks through how agents use these tools to execute web workflows, run code, and produce visualizations safely at scale.

Framework for evaluating the business value and return on investment of Amazon Bedrock projects. Covers value driver identification, cost modeling for foundation model usage, and methods for quantifying productivity and revenue impact of generative AI.

Introduction to Amazon Bedrock, AWS's fully managed service for foundation models. Covers available model providers, the playground, key APIs for inference and customization, and core concepts like Knowledge Bases, Agents, and Guardrails.

Demonstrates building automated generative AI workflows with Amazon Bedrock Flows, the visual builder for orchestrating prompts, models, knowledge bases, agents, and Lambda functions into multi-step applications.

Hands-on walkthrough of using Amazon Bedrock Data Automation to extract structured insights from unstructured content and automatically generate handout notes from documents, audio, and video.

Simulation-based lab where learners interact with a virtual customer to explore the Amazon Bedrock playgrounds. Provides hands-on experience choosing foundation models and crafting prompts for chat, text, and image use cases.

Covers running large-scale batch inference jobs on Amazon Bedrock, including job submission, input and output formats in S3, cost considerations, and patterns for processing high-volume document and content workloads.

Hands-on guide to building cross-platform mobile chat experiences using React Native and Amazon Bedrock. Covers client-server design, secure invocation of foundation models, and streaming responses to mobile UIs.

Reference solution for building an intelligent eDiscovery system with Amazon Bedrock Agents. Covers document ingestion, retrieval-augmented generation over legal corpora, and agent orchestration for review workflows.

Hands-on lab using Amazon S3 Vectors as a vector store with Amazon Bedrock Knowledge Bases. Covers indexing embeddings in S3, configuring knowledge bases, and querying for retrieval-augmented generation use cases.

Architectural patterns for building cost-effective retrieval-augmented generation applications using Amazon Bedrock Knowledge Bases backed by Amazon S3 Vectors. Covers ingestion design, chunking strategies, and cost-versus-latency tradeoffs.

End-to-end guide to building generative AI applications on Amazon Bedrock, including model selection, prompt design, knowledge bases, agents, guardrails, and integrating Bedrock with application back ends.

Walkthrough of building production-ready AI agents in TypeScript using the Effect library and Amazon Bedrock. Covers structured concurrency, error handling, and integrating tools and memory for reliable agent execution.

Practical guide to building production-grade agents on Amazon Bedrock AgentCore. Covers using the runtime, gateway, memory, identity, and observability primitives together to deploy reliable agents at scale.

Covers using Amazon Bedrock Guardrails to apply content filters, denied topics, sensitive information redaction, and contextual grounding checks to keep generative AI applications safe, on-topic, and policy-aligned.
I'm always learning and applying new skills — let's talk about how I can help on your next project.
Get in Touch