Wirewalk Instituteof AI
ven-260 Intermediate Waitlist

Amazon Bedrock: Multi-Model AI on AWS

For developers and AWS architects who need to build, govern and scale applications and agents across the many model providers available in Amazon Bedrock.

The curriculum is being prepared and reviewed. Enrollment is not open yet.

About this course

Bedrock's value is breadth behind one AWS control plane: Amazon's Nova models alongside Anthropic, OpenAI, Meta, Mistral, Cohere, DeepSeek, Qwen and others, all governed by IAM, logged to CloudWatch and billed to your AWS account. That breadth comes with choices that trip teams up: two inference endpoints (bedrock-runtime for Converse and InvokeModel, and bedrock-mantle for OpenAI-compatible and Anthropic Messages APIs, with AWS guidance on which to use for new applications having shifted during 2026), model-specific feature support, cross-Region inference profiles, and four service tiers (Reserved, Priority, Standard and Flex) that trade latency against price.

This course teaches you to make those choices deliberately. You will call models with the Converse API so one request shape works across providers, add tool use and streaming, and plan throughput with inference profiles and tiers. You will cut cost with prompt caching, batch inference, Intelligent Prompt Routing and distillation. You will build retrieval on Knowledge Bases, enforce policy with Guardrails, and evaluate both models and RAG pipelines. The agent module compares classic Bedrock Agents with AgentCore's Runtime, Gateway, Memory, Identity and Policy services. The course closes with custom model import, logging and cost allocation, and a hypothetical reference architecture for a governed internal assistant. Facts are as of October 2026 and checked against the Amazon Bedrock User Guide.

What you will be able to do

  • Configure model access, IAM policies and Bedrock API keys with least privilege
  • Choose between the bedrock-runtime and bedrock-mantle endpoints for a given model, API shape and client, following current AWS guidance
  • Write provider-portable code with the Converse API, including tool use and streaming
  • Select a service tier and cross-Region inference profile to meet latency, cost and residency requirements
  • Build and evaluate a Knowledge Bases retrieval pipeline protected by Bedrock Guardrails
  • Decide between Bedrock Agents and AgentCore and outline an AgentCore deployment with Gateway, Memory and Identity
  • Instrument Bedrock workloads with invocation logging, CloudWatch metrics and cost allocation tags

Syllabus

6 modules · 18 lessons · about 12 hours

Module 1: Bedrock as a Multi-Model Platform

The catalog, access controls and the two inference endpoints.
3 lessons
  1. The Bedrock Model Catalog: Amazon Nova and Third-Party Providers
  2. Model Access, IAM Policies and Bedrock API Keys
  3. Two Endpoints: bedrock-runtime (Converse, InvokeModel) vs bedrock-mantle (OpenAI-Compatible and Anthropic Messages APIs)

Module 2: Portable Inference

One request shape across providers, plus capacity routing across Regions.
3 lessons
  1. The Converse API: One Request Shape Across Model Providers
  2. Tool Use, Structured Output and Streaming with ConverseStream
  3. Cross-Region Inference Profiles: Geographic and Global Routing

Module 3: Price and Performance Levers

Tiers, caching, batch and automatic model selection.
3 lessons
  1. Service Tiers: Reserved, Priority, Standard and Flex
  2. Prompt Caching and Batch Inference
  3. Intelligent Prompt Routing and Model Distillation

Module 4: Knowledge, Safety and Evaluation

Managed retrieval, policy enforcement and measurable quality.
3 lessons
  1. Bedrock Knowledge Bases: Data Sources, Chunking and Retrieval Configuration
  2. Bedrock Guardrails: Content Filters, Denied Topics, PII and Automated Reasoning Checks
  3. Bedrock Evaluations for Models and RAG Pipelines

Module 5: Agents on AWS

Two generations of agent tooling and how to choose.
3 lessons
  1. Bedrock Agents vs AgentCore: Choosing the Agent Layer
  2. AgentCore Runtime, Gateway and Memory
  3. AgentCore Identity, Policy and Observability

Module 6: Production on Bedrock

Customization, monitoring and a reference design.
3 lessons
  1. Custom Model Import and Fine-Tuning Options
  2. Invocation Logging, CloudWatch Metrics and Cost Allocation Tags
  3. Hypothetical Reference Architecture: A Governed Internal Assistant on Bedrock

Exam and certificate

The exam unlocks once you have completed every lesson. It draws 20 questions from a larger bank, spread across the modules, with the answer options shuffled for each attempt. You have 40 minutes and need 80% to pass. After a failed attempt you can try again after 24 hours, up to 3 attempts in total. Feedback is given per module, never as the answer key.

Passing earns a certificate of completion and assessment from the Wirewalk Institute of AI with a unique ID that anyone can check at institute.wirewalk.com/verify. It is not an accredited qualification or a vendor certification. How certification works.

The Wirewalk Institute of AI is independent. This course teaches publicly documented products and is not affiliated with or endorsed by Amazon (Bedrock, Nova, AgentCore, IAM, CloudWatch), Anthropic, OpenAI, Meta (Llama), Mistral AI, Cohere, DeepSeek, or Alibaba (Qwen). Product and company names are trademarks of their respective owners.

More in AI Models and Vendors

All 22 courses in this track
ven-001 Free intro Available

Your First Hour with ChatGPT, Claude and Gemini

A hands-on hour with ChatGPT, Claude and Gemini, told through one small business racing a deadline. Set up an account with a privacy setting you chose, decide what never goes into a personal account, write prompts that produce usable drafts, use files and web search, catch confident mistakes before they go out, and pick the assistant that fits how you work.

1 h · 7 lessons Free intro
ven-110 Basic Available

ChatGPT and the OpenAI Platform for Professionals

A practical, current tour of ChatGPT as a professional tool: choosing a plan and model, prompting well, analyzing files, researching with citations, using images and voice, organizing work in projects and memory, connecting apps and plugins, delegating multi-step work to ChatGPT Work, and knowing which admin and privacy controls matter. Ends with clear guidance on moving a workflow to the OpenAI API.

8 h · 15 lessons See price at checkout
ven-120 Basic Available

Claude for Professionals

Learn Claude by solving one firm's real problem: getting through renewal season with too few analysts and without putting client data in the wrong place. Each module compares the approaches professionals actually choose between, shows a realistic failure and its fix, and ends with a Decision Lab where you make the call under pressure.

12 h · 15 lessons See price at checkout