Wirewalk Instituteof AI
ven-230 Intermediate Waitlist

Anthropic Claude API: Tools, Caching and Agents

For developers who have called an LLM API and now need to build production tool-using applications and agents on the Claude Developer Platform.

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

About this course

The Claude API has grown from a single chat endpoint into a platform for building agents: client tools you execute, server tools Anthropic executes (web search, web fetch, code execution), tool search for large toolsets, prompt caching and batches for cost, context editing, compaction and a memory tool for long-running work, a connector for remote MCP servers, Agent Skills, and the Claude Agent SDK that packages the same agent loop used by Claude Code.

This course works through each layer in the order you need it in a real build. You start with the Messages API request and response shape, streaming and token accounting; move to the tool-use loop and its failure modes; then cut cost and latency with cache breakpoints, the Message Batches API and file uploads. The second half covers long-running agents: managing the context window, connecting MCP servers, packaging procedures as Skills, building with the Agent SDK's subagents, hooks and permissions, and deciding when Anthropic's hosted Claude Managed Agents harness (in beta as of October 2026) is the better fit. It closes with what changes when you call Claude through Amazon Bedrock, Claude Platform on AWS, Google Cloud or Microsoft Foundry instead of the direct API, and how to evaluate an agent before launch. Product facts are stated as of October 2026; beta features are labeled as such and checked against platform.claude.com documentation.

What you will be able to do

  • Construct Messages API requests with system prompts, multi-part content blocks, streaming and appropriate effort or extended-thinking settings
  • Implement a robust tool-use loop with strict JSON Schema tools, parallel calls, tool errors and server tools such as web search and code execution
  • Place prompt-caching breakpoints correctly and verify savings from cache read and write token counts
  • Choose between synchronous calls, the Message Batches API and the Files API for a given workload and estimate the cost difference
  • Design context management for long-running agents using context editing, compaction and the memory tool
  • Build an agent with the Claude Agent SDK that uses subagents, hooks, MCP servers and scoped permissions
  • Decide whether a workload should run its own agent loop with the Agent SDK or use Claude Managed Agents, given data-retention and control requirements
  • Explain the functional and contractual differences between the direct Claude API, Claude Platform on AWS, and Claude on Amazon Bedrock, Google Cloud and Microsoft Foundry

Syllabus

6 modules · 19 lessons · about 12 hours

Module 1: Messages API Fundamentals

The request and response shape every other feature builds on, plus model and reasoning controls.
3 lessons
  1. The Messages API: Roles, Content Blocks and Stop Reasons
  2. Choosing a Claude Model, Effort Level and Extended Thinking per Request
  3. Streaming Events, Token Counting and Rate-Limit Headers

Module 2: Tool Use End to End

Client tools, server tools and the loop that ties them together.
4 lessons
  1. Defining Client Tools with JSON Schema and Strict Structured Outputs
  2. The Tool-Use Loop: tool_use, tool_result, Parallel Calls and Error Results
  3. Server Tools: Web Search, Web Fetch and Code Execution
  4. Scaling to Hundreds of Tools with Tool Search and Deferred Loading

Module 3: Cost and Throughput Levers

Cut spend and latency with caching, batching and file handling.
3 lessons
  1. Prompt Caching: Breakpoints, TTLs and Reading Cache-Hit Usage
  2. The Message Batches API for Asynchronous Bulk Work
  3. The Files API, PDF Inputs and Citations for Long Documents

Module 4: Long-Running Agents on the API

Keep agents coherent across long sessions and connect them to external systems.
3 lessons
  1. Context Editing, Compaction and the Memory Tool
  2. Connecting Remote MCP Servers with the MCP Connector
  3. Packaging Procedures as Agent Skills

Module 5: The Claude Agent SDK

Build agents on the same harness that powers Claude Code.
3 lessons
  1. Agent SDK Basics: The Agent Loop, Built-in Tools and Permission Modes
  2. Subagents, Hooks and Session Management in the Agent SDK
  3. Own the Loop or Hand It Off: Agent SDK vs Claude Managed Agents (Beta)

Module 6: Shipping Claude in Production

Platform choice, administration and pre-launch evaluation.
3 lessons
  1. Claude Through the Clouds: Amazon Bedrock, Claude Platform on AWS, Google Cloud and Microsoft Foundry
  2. Workspaces, API Keys, Usage and Cost Reporting, and Data Retention
  3. Evaluating and Monitoring a Claude Agent Before Launch

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 Anthropic, Amazon (Bedrock), Google Cloud, or Microsoft (Foundry). 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