Course Objective & Scope
For organisations running on AWS, Amazon Bedrock provides managed access to models such as Anthropic Claude, Amazon Nova, Llama and Mistral behind a single API with native IAM governance and PrivateLink network isolation. This course covers the Converse API, managed RAG with Knowledge Bases, Bedrock Agents with AWS Lambda, Bedrock Guardrails and Model Evaluation.
Participants build a secure, observable and cost-controlled Bedrock application using the AWS SDK (Boto3/TypeScript) and produce a reference architecture aligned with their AWS environment.
Who Should Attend?
- Software, cloud and AI engineers building applications on AWS
- AWS solution architects designing AI systems that meet enterprise IAM and network policies
- Technical teams whose data lives in S3, OpenSearch or Aurora/pgvector
- Prerequisite: familiarity with core AWS services (IAM, S3, Lambda) and Python or TypeScript
Key Takeaways
- Use the Bedrock Converse API for multi-model inference, streaming and tool calling
- Build managed RAG pipelines with Bedrock Knowledge Bases on S3 and OpenSearch/Aurora pgvector
- Enforce content filtering, PII redaction and contextual grounding checks with Bedrock Guardrails
- Secure deployments using IAM least privilege, KMS encryption, VPC PrivateLink and CloudTrail/CloudWatch
- Optimise spend across On-Demand, Cross-Region Inference, Prompt Caching and Batch Inference
Curriculum
Amazon Bedrock Architecture and the Converse API
- The Bedrock model catalogue (Claude, Nova, Llama, Mistral) and region/quota management
- Unified messaging, multimodal inputs and tool calling with Converse and ConverseStream
Managed RAG with Bedrock Knowledge Bases
- S3 data sources, chunking strategies and OpenSearch Serverless / Aurora pgvector integration
- Metadata filtering, source citations and custom data connectors
Bedrock Agents, Action Groups and Prompt Flows
- Connecting to enterprise systems via OpenAPI schemas and AWS Lambda action groups
- Versioned workflows with Prompt Management and Bedrock Flows
Bedrock Guardrails and Evaluation
- Configuring denied topics, PII redaction and Contextual Grounding Checks
- Measuring quality and safety with Bedrock Model & RAG Evaluation
AWS Security, Network Isolation and Cost Management
- IAM policies, VPC Endpoints (PrivateLink), KMS and CloudTrail/CloudWatch logging
- Cross-Region Inference, Prompt Caching, Provisioned Throughput and cost tagging
Hands-On: Enterprise AI Service on AWS
- Building a Bedrock + Knowledge Base + Guardrails application for an internal use case
- AWS architecture and security readiness review
Other Courses in This Category
-
Building enterprise AI applications on Azure AI Foundry and Azure OpenAI Service with GPT and reasoning models, Azure AI Search, Entra ID authentication, Private Endpoints, Content Safety and PTU/quota management.
- Live Course
- 6 modules
-
Hands-on programme for building enterprise AI applications on Google Cloud Vertex AI using Gemini models, the Google Gen AI SDK, Context Caching, Grounding, Vertex AI Search, BigQuery and VPC-SC security.
- Live Course
- 6 modules
-
Architectural patterns for turning LLM prototypes into resilient enterprise systems: AI gateways, async queues, circuit breakers, fallback chains, idempotency, guardrails and OpenTelemetry tracing.
- Live Course
- 6 modules
-
How foundation models and LLMs work: tokens, context windows, sampling, hallucination, model families and when to choose prompting, RAG or fine-tuning — a hands-on starting point for technical teams.
- Live Course
- 6 modules
-
A technical deep dive into the transformer: tokenization, self-attention, RoPE, KV cache, scaling laws, SFT, RLHF/DPO and reasoning models, explored hands-on with PyTorch and Hugging Face Transformers.
- Live Course
- 6 modules
-
Hands-on programme for building a near-production LLM application with the OpenAI, Anthropic Claude and Google Gemini APIs, covering streaming, conversation state, retries, rate limits, fallbacks and basic evals.
- Live Course
- 6 modules
Get in touch
