Exam Prep
Anthropic · CCAR-F · Study references

Claude Certified Architect - Foundations

The vendor’s own documentation for each objective of the exam, free to use.

Agentic Architecture & Orchestration7 objectives

Design and implement agentic loops for autonomous task execution10 pages

  • Agent SDK execution loop

    Understand the message lifecycle, tool execution, context window, and architecture that power your SDK agents.

  • Calendar Agent Tutorial: Five Rings

    A guided walkthrough from a single tool call to a production-ready agentic loop.

  • Claude Code Core Architecture

    Understand the agentic loop, built-in tools, and how Claude Code interacts with your project.

  • LLM Agents Architecture Patterns

    Compares agent architecture patterns and frameworks, contrasting workflows with autonomous agents and describing common composable building blocks for LLM systems.

  • Programmatic Tool Calling with Claude API

    Explains programmatic tool calling, where Claude invokes tools from code execution, and how to enable it on tool definitions.

  • Server-Executed Tools Mechanics

    Work with Anthropic-executed tools: server_tool_use blocks, pause_turn continuation, mixed server and client tool turns, and domain filtering.

  • Task Budgets API Reference

    Give Claude an advisory token budget for the full agentic loop to help the model self-regulate on long agentic tasks.

  • Tool Runner API

    Use the SDK's tool runner to handle the agentic loop, error wrapping, and type safety automatically.

  • Tool Search with Embeddings

    Scale Claude applications to thousands of tools using semantic embeddings for dynamic tool discovery.

  • Tool Use Concepts

    Understand the tool use loop, where tools execute, and when to use tools instead of prose.

Orchestrate multi-agent systems with coordinator-subagent patterns5 pages

  • Claude Outcomes: Agent Verification

    Shows how to verify managed agent outputs with an outcome grader, covering outcome definitions, rubrics, citation checks, and the iteration loop.

  • Coordinator Pattern Cost Structure

    Two-model team economics via the multiagent coordinator config — a frontier coordinator plans and synthesizes while cheap search workers do the token-heavy web reading in parallel threads, compared against a rigor-matched solo-frontier control with real bills. Covers per-thread usage.list_cost metering, cost attribution, and a session budget as the fan-out guardrail.

  • Dynamic Workflows Reference

    Dynamic workflows orchestrate many subagents from a script Claude writes and you can rerun. Use them for codebase audits, large migrations, and cross-checked research.

  • LLM Agents Architecture Patterns

    Compares agent architecture patterns and frameworks, contrasting workflows with autonomous agents and describing common composable building blocks for LLM systems.

  • Multiagent orchestration configuration

    Coordinate multiple agents within a single session.

Configure subagent invocation, context passing, and spawning8 pages

  • Agent SDK execution loop

    Understand the message lifecycle, tool execution, context window, and architecture that power your SDK agents.

  • Agent Teams Configuration

    Coordinate multiple Claude Code instances working together as a team, with shared tasks, inter-agent messaging, and centralized management.

  • Context Management Approaches

    Choose between tool search, programmatic tool calling, prompt caching, and context editing to manage context bloat.

  • Cross-session messaging in Claude Code

    Explains cross-session messaging in Claude Code, covering version requirements, how sessions find and message each other, and delivery behavior.

  • Dynamic Workflows Reference

    Dynamic workflows orchestrate many subagents from a script Claude writes and you can rerun. Use them for codebase audits, large migrations, and cross-checked research.

  • Git worktrees isolation

    Explains using git worktrees to isolate Claude Code sessions, covering creation, trust requirements, switching, and permission prompts for paths.

  • Subagents Configuration and Usage

    Create and use specialized AI subagents in Claude Code for task-specific workflows and improved context management.

  • Subagents programmatic SDK reference

    Define and invoke subagents to isolate context, run tasks in parallel, and apply specialized instructions in your Claude Agent SDK applications.

Implement multi-step workflows with enforcement and handoff patternsNot documented8 pages

  • Advanced Tool Use Features

    Introduces advanced tool use features for the Claude API, such as deferred tool loading, programmatic tool calling, and input examples, and their effect on efficiency.

  • Agent Teams Configuration

    Coordinate multiple Claude Code instances working together as a team, with shared tasks, inter-agent messaging, and centralized management.

  • Claude Code Development Recipes

    Step-by-step guides for exploring codebases, fixing bugs, refactoring, testing, and other everyday tasks with Claude Code.

  • Dynamic Workflows Reference

    Follow an agent's workflow runs: their states and events, when the work is done, what a run blocks, budgets, and limits.

  • Dynamic Workflows Reference

    Dynamic workflows orchestrate many subagents from a script Claude writes and you can rerun. Use them for codebase audits, large migrations, and cross-checked research.

  • Dynamic Workflows with Agent SDK

    Trigger a dynamic workflow from the Agent SDK to fact-check a report against source documents with parallel verifier and skeptic subagents.

  • Programmatic Tool Calling

    Let Claude call your tools from code in the code execution container, cutting model round trips and token use in multi-tool workflows.

  • Thinking with tool use walkthrough

    Walk through a complete two-turn tool-use round trip that preserves thinking blocks correctly, and see how interleaved thinking changes the flow.

Apply Agent SDK hooks for tool call interception and data normalization2 pages

Design task decomposition strategies for complex workflows1 page

  • Dynamic Workflows Reference

    Dynamic workflows orchestrate many subagents from a script Claude writes and you can rerun. Use them for codebase audits, large migrations, and cross-checked research.

Manage session state, resumption, and forking5 pages

  • ant beta:sessions connect

    Attach the ant CLI to a Claude Managed Agents session to follow its transcript live, send messages, allow or deny tool calls, or open the session viewer in your browser.

  • Claude Code Checkpoints

    Track, rewind, and summarize Claude's edits and conversation to manage session state.

  • Compliance API Sessions Endpoints

    List the sessions your users run in Claude apps and agents, such as Claude Cowork and Claude Code, and retrieve their transcripts through the Compliance API.

  • Session Browser API

    List, read, rename, tag, and fork Agent SDK sessions on disk to build a conversation history sidebar without writing a transcript parser.

  • V2 Session API Reference

    Reference for the removed V2 TypeScript Agent SDK session API, with session-based send/stream patterns for multi-turn conversations.

Tool Design & MCP Integration5 objectives

Design effective tool interfaces with clear descriptions and boundaries4 pages

  • Calendar Agent Tutorial: Five Rings

    A guided walkthrough from a single tool call to a production-ready agentic loop.

  • Code Execution Tool Reference

    Run Python and bash code in a sandboxed container to analyze data, generate files, and iterate on solutions.

  • Computer Use Tool

    Give Claude screenshot, mouse, and keyboard control of a desktop environment with the computer use tool, the computer_toolset_20260801 client toolset.

  • Tool Search Configuration

    Scale your agent to thousands of tools by discovering and loading only what's needed, on demand.

Implement structured error responses for MCP tools2 pages

Distribute tools appropriately across agents and configure tool choice5 pages

Integrate MCP servers into Claude Code and agent workflows5 pages

  • Agent SDK Plugin Loading

    Load custom plugins to extend Claude Code with skills, agents, hooks, and MCP servers through the Agent SDK

  • Custom tools integration

    Serve custom tools from a self-hosted sandbox worker, and wrap an MCP server inside your network as custom tools without running a tunnel.

  • MCP Server Configuration & Tools

    Configure MCP servers to extend your agent with external tools. Covers transport types, tool search for large tool sets, authentication, and error handling.

  • Model Context Protocol CLI Setup

    Add an MCP server to Claude Code, verify the connection, and find the configuration on disk.

  • Remote MCP Servers

    Connect Claude to third-party remote MCP servers through the MCP connector API. Browse example servers and review the steps to connect.

Select and apply built-in tools (Read, Write, Edit, Bash, Grep, Glob) effectively5 pages

Claude Code Configuration & Workflows6 objectives

Configure CLAUDE.md files with appropriate hierarchy, scoping, and modular organization4 pages

  • Claude Code Enterprise Deployment

    A decision map for administrators deploying Claude Code, covering API providers, managed settings, policy enforcement, usage monitoring, and data handling.

  • Claude Code memory and instructions

    Give Claude persistent instructions with CLAUDE.md or AGENTS.md files, and let Claude accumulate learnings automatically with auto memory.

  • Large Codebase Configuration

    Configure Claude Code for monorepos and large single-tree codebases with nested CLAUDE.md files, sparse worktrees, code intelligence, and per-package skills so Claude stays focused on the code you're working in.

  • Settings File Examples and Keys

    Realistic settings.json files for a developer, a team, and an organization: copy one, keep the keys you want, and change the values.

Create and configure custom slash commands and skills9 pages

  • Agent SDK Custom Tools

    Define custom tools with the Claude Agent SDK's in-process MCP server so Claude can call your functions, hit your APIs, and perform domain-specific operations.

  • Agent Skills in SDK

    Control which skills Claude can invoke in Claude Agent SDK sessions, dispatch commands by name, and author skills your sessions discover

  • Agent Skills SDK Configuration

    Control which skills Claude can invoke in Claude Agent SDK sessions, dispatch commands by name, and author skills your sessions discover

  • Claude Code Pricing and Usage

    Track token usage, set team spend limits, and reduce Claude Code costs with context management, model selection, extended thinking settings, and preprocessing hooks.

  • Claude Code Settings Configuration

    Change Claude Code settings, pick the scope a key belongs in, verify the change, and learn which value Claude Code uses when a key is set in several places.

  • Cloud Environments Configuration

    Configure cloud environments for Claude Code cloud sessions: network access levels, environment variables, setup scripts, and environment caching.

  • Repository Skills Discovery

    Explains how Claude managed agents discover skills stored in a repository, covering required file locations, frontmatter description matching, and discovery limits.

  • Sharing skills

    Explains how to share Claude Code skills through repositories, plugins, and enterprise settings, and how subagents load skills.

  • Skills and Frontmatter Configuration

    Create, manage, and share skills to extend Claude's capabilities in Claude Code. Includes custom commands and bundled skills.

Apply path-specific rules for conditional convention loading2 pages

  • Claude Code Context Management

    An interactive simulation of how Claude Code's context window fills during a session. See what loads automatically, what each file read costs, and when rules and hooks fire.

  • Claude Code memory and instructions

    Give Claude persistent instructions with CLAUDE.md or AGENTS.md files, and let Claude accumulate learnings automatically with auto memory.

Determine when to use plan mode vs direct execution5 pages

  • Claude Code Auto Mode Billing

    Resolve the Claude Code notice saying this session isn't eligible for auto mode's no-charge classifier requests: what it means, why it appears, and what to do.

  • Claude Code best practices

    Shares best practices for working effectively with Claude Code, including context management, plan mode, scripted headless usage, and permission modes.

  • Claude Code Permission Modes

    Control whether Claude asks before acting. Switch permission modes with Shift+Tab in the CLI, the mode indicator in VS Code, or the mode selector in Desktop.

  • Orchestration Mode Implementation

    Build a session-level mode that grants standing consent for multiagent fan-out, switched on and off with mid-conversation system messages.

  • Trustworthy AI Agents Policy

    Outlines Anthropic's policy view on trustworthy AI agents, covering agent components, user permission controls, and defenses against prompt injection.

Apply iterative refinement techniques for progressive improvement2 pages

  • Claude Fable 5 Prompting Patterns

    Behavioral differences and prompting patterns for Claude Fable 5 and Claude Mythos 5, covering effort, instruction following, long runs, memory, and scaffolding changes.

  • Hallucination Minimization Techniques

    Minimize hallucinations in Claude's outputs by allowing uncertainty, grounding responses in direct quotes, and verifying claims with citations.

Integrate Claude Code into CI/CD pipelines6 pages

  • Agent SDK CLI non-interactive mode

    Use the Agent SDK to run Claude Code programmatically from the CLI, Python, or TypeScript.

  • Channels Research Preview

    Use channels to push messages, alerts, and webhooks into your Claude Code session from an MCP server. Forward CI results, chat messages, and monitoring events so Claude can react while you're away.

  • Claude Code best practices

    Shares best practices for working effectively with Claude Code, including context management, plan mode, scripted headless usage, and permission modes.

  • Claude Code for GitLab CI/CD

    Learn about integrating Claude Code into your development workflow with GitLab CI/CD

  • Consistency techniques for Claude

    Make Claude's outputs more consistent by specifying exact formats, prefilling responses, constraining with examples, and grounding answers in retrieval.

  • Structured Outputs API

    Return validated JSON from agent workflows using JSON Schema, Zod, or Pydantic. Get type-safe, structured data after multi-turn tool use.

Prompt Engineering & Structured Output6 objectives

Design prompts with explicit criteria to improve precision and reduce false positives6 pages

  • Claude Fable 5.1 Migration Guide

    Behavioral differences and prompting patterns for Claude Fable 5.1 and Claude Mythos 5.1, covering effort, progress updates, tool-call batching, conversation history, writing style, formatting, task completion, compaction summaries, scope and test coverage, search triggering, safeguard false positives, file edits, long outputs, subagents, and vision.

  • Claude Prompt Engineering Reference

    Comprehensive guide to prompt engineering techniques for Claude's latest models, covering clarity, examples, XML structuring, thinking, and agentic systems.

  • Code Review Service Facts

    Set up automated PR reviews that catch logic errors, security vulnerabilities, and regressions using multi-agent analysis of your full codebase

  • Hallucination Minimization Techniques

    Minimize hallucinations in Claude's outputs by allowing uncertainty, grounding responses in direct quotes, and verifying claims with citations.

  • Insurance Support Ticket Classifier

    Build classification systems with Claude using RAG and chain-of-thought for insurance tickets.

  • LLM Evaluation Methodology

    Define measurable success criteria for your LLM application and build evaluations to test it, from exact match checks to LLM-based grading.

Apply few-shot prompting to improve output consistency and quality6 pages

  • Claude Fable 5 Prompting Patterns

    Behavioral differences and prompting patterns for Claude Fable 5 and Claude Mythos 5, covering effort, instruction following, long runs, memory, and scaffolding changes.

  • Claude Prompt Engineering Reference

    Comprehensive guide to prompt engineering techniques for Claude's latest models, covering clarity, examples, XML structuring, thinking, and agentic systems.

  • Claude Sonnet 5 Prompting Patterns

    Behavioral differences and prompting patterns for Claude Sonnet 5, covering effort, adaptive thinking defaults, and tool use.

  • Claude Sonnet 5.5 Prompting Patterns

    Prompting patterns specific to Claude Sonnet 5.5: effort, initiative and scope, running without up-front thinking, JSON output, progress updates, tool use, mid-turn messages, coding verification, tool calls, visual inputs, and refusals.

  • Consistency techniques for Claude

    Make Claude's outputs more consistent by specifying exact formats, prefilling responses, constraining with examples, and grounding answers in retrieval.

  • Insurance Support Ticket Classifier

    Build classification systems with Claude using RAG and chain-of-thought for insurance tickets.

Enforce structured output using tool use and JSON schemas5 pages

  • Claude API Usage Primer

    This guide is designed to give Claude the basics of using the Claude API. It gives explanation and examples of model IDs/the basic messages API, tool use, streaming, thinking, and nothing else.

  • Strict Tool Use Configuration

    Enforce JSON Schema compliance on Claude's tool inputs with grammar-constrained sampling.

  • Structured Outputs API

    Get validated JSON results from agent workflows

  • Structured Outputs API

    Return validated JSON from agent workflows using JSON Schema, Zod, or Pydantic. Get type-safe, structured data after multi-turn tool use.

  • Tool-Call Lifecycle Handling

    Parse tool_use blocks, format tool_result responses, and handle errors with is_error.

Implement validation, retry, and feedback loops for extraction quality12 pages

  • API error codes and handling

    Understand the HTTP status codes, error response shape, and request IDs the Claude API returns, and handle errors with the SDK's typed exceptions.

  • Claude Skills Setup and Usage

    Create documents, analyze data, automate workflows with Claude's Excel, PowerPoint, PDF skills.

  • Compliance API Error Responses

    Explains common Compliance API error responses, how to identify them by status and error type, and how query filters and pagination behave.

  • Consistency techniques for Claude

    Make Claude's outputs more consistent by specifying exact formats, prefilling responses, constraining with examples, and grounding answers in retrieval.

  • Dynamic Workflows Reference

    Dynamic workflows orchestrate many subagents from a script Claude writes and you can rerun. Use them for codebase audits, large migrations, and cross-checked research.

  • Evaluator-Optimizer Workflow

    Walks through a generator-evaluator feedback loop that retries output with prior attempts, using XML-tagged prompts and Python helper functions.

  • LLM Evaluation Methodology

    Define measurable success criteria for your LLM application and build evaluations to test it, from exact match checks to LLM-based grading.

  • Message Streaming API

    Stream Messages API responses incrementally with server-sent events, including text, tool use, and thinking deltas.

  • Skills Authoring Guide

    Lists best practices for authoring Agent Skills, covering naming, description writing, file organization, and progressive loading of SKILL.md content.

  • Structured Outputs API

    Get validated JSON results from agent workflows

  • Structured Outputs API

    Return validated JSON from agent workflows using JSON Schema, Zod, or Pydantic. Get type-safe, structured data after multi-turn tool use.

  • User Input and Approval Requests

    Surface Claude's approval requests and clarifying questions to users, then return their decisions to the SDK.

Design efficient batch processing strategies1 page

  • Message Batches API

    Process large volumes of Messages requests asynchronously with the Message Batches API, cutting costs by 50% and increasing throughput.

Design multi-instance and multi-pass review architectures5 pages

  • Agent Teams Configuration

    Coordinate multiple Claude Code instances working together as a team, with shared tasks, inter-agent messaging, and centralized management.

  • Claude Code best practices

    Shares best practices for working effectively with Claude Code, including context management, plan mode, scripted headless usage, and permission modes.

  • Claude Fable 5 Prompting Patterns

    Behavioral differences and prompting patterns for Claude Fable 5 and Claude Mythos 5, covering effort, instruction following, long runs, memory, and scaffolding changes.

  • Code Review Service Facts

    Set up automated PR reviews that catch logic errors, security vulnerabilities, and regressions using multi-agent analysis of your full codebase

  • Orchestration Mode Implementation

    Build a session-level mode that grants standing consent for multiagent fan-out, switched on and off with mid-conversation system messages.

Context Management & Reliability6 objectives

Manage conversation context to preserve critical information across long interactions5 pages

  • Claude Code Context Management

    An interactive simulation of how Claude Code's context window fills during a session. See what loads automatically, what each file read costs, and when rules and hooks fire.

  • Context Editing and Compaction

    Automatically manage conversation context as it grows with context editing.

  • Context Management Approaches

    Choose between tool search, programmatic tool calling, prompt caching, and context editing to manage context bloat.

  • Context Window Management

    Understand how the context window works, how extended thinking and tool use count toward it, and how to manage context as conversations grow.

  • Session Memory Compaction

    Manage long-running Claude conversations with instant session memory compaction using background threading and prompt caching.

Design effective escalation and ambiguity resolution patternsNot documented0 pages

Implement error propagation strategies across multi-agent systemsNot documented17 pages

  • Agent Hooks Configuration

    Intercept and customize agent behavior at key execution points with hooks

  • Agent SDK execution loop

    Understand the message lifecycle, tool execution, context window, and architecture that power your SDK agents.

  • Agent Teams Configuration

    Coordinate multiple Claude Code instances working together as a team, with shared tasks, inter-agent messaging, and centralized management.

  • Agent Teams Configuration

    Explains how to configure and use experimental agent teams in Claude Code, covering enabling settings, team roles, and coordination tradeoffs versus subagents.

  • API error codes and handling

    Understand the HTTP status codes, error response shape, and request IDs the Claude API returns, and handle errors with the SDK's typed exceptions.

  • API Limits and Rate Limiting

    To mitigate misuse and manage capacity on the API, limits are in place on how much an organization can use the Claude API.

  • Claude API Refusal Fallback

    Explains how Claude API refusals are signaled and billed, and how server-side and client-side model fallback handle safety-declined requests.

  • Claude Code Hooks Reference

    Reference for Claude Code hook events, configuration schema, JSON input/output formats, exit codes, async hooks, HTTP hooks, prompt hooks, and MCP tool hooks.

  • Claude Code Runtime Errors

    Look up Claude Code runtime error messages with what each one means and how to fix it.

  • Coordinator Pattern Cost Structure

    Two-model team economics via the multiagent coordinator config — a frontier coordinator plans and synthesizes while cheap search workers do the token-heavy web reading in parallel threads, compared against a rigor-matched solo-frontier control with real bills. Covers per-thread usage.list_cost metering, cost attribution, and a session budget as the fan-out guardrail.

  • Dynamic Workflows Reference

    Follow an agent's workflow runs: their states and events, when the work is done, what a run blocks, budgets, and limits.

  • Dynamic Workflows Reference

    Dynamic workflows orchestrate many subagents from a script Claude writes and you can rerun. Use them for codebase audits, large migrations, and cross-checked research.

  • Inference Hooks

    Describes how inference hooks send prompts and tool calls to an organization's security server for allow or deny verdicts, and how failures are handled.

  • Multiagent orchestration configuration

    Coordinate multiple agents within a single session.

  • Structured Error Responses

    Implementing structured error responses for MCP tools with proper categorisation and recovery metadata

  • Structured Outputs API

    Get validated JSON results from agent workflows

  • Subagents Configuration and Usage

    Create and use specialized AI subagents in Claude Code for task-specific workflows and improved context management.

Manage context effectively in large codebase exploration4 pages

  • Claude Code Context Management

    An interactive simulation of how Claude Code's context window fills during a session. See what loads automatically, what each file read costs, and when rules and hooks fire.

  • Context Editing and Compaction

    Automatically manage conversation context as it grows with context editing.

  • Context Management Approaches

    Choose between tool search, programmatic tool calling, prompt caching, and context editing to manage context bloat.

  • Large Codebase Configuration

    Configure Claude Code for monorepos and large single-tree codebases with nested CLAUDE.md files, sparse worktrees, code intelligence, and per-package skills so Claude stays focused on the code you're working in.

Design human review workflows and confidence calibration2 pages

  • Claude Cookbooks Index

    Practical guides and code examples for building with Claude. Learn prompting techniques, tool use, multimodal capabilities, and more.

  • Demystifying evals for AI agents

    Explains core evaluation terminology for AI agents, such as tasks, trials, graders, and transcripts, and how evaluation harnesses and suites are structured.

Preserve information provenance and handle uncertainty in multi-source synthesis7 pages

  • API Citations Support

    Demonstrates the Claude API citations feature across plain text, PDF, and custom content documents, explaining citation location formats and how chunking affects what gets cited.

  • Citations Feature Overview

    Describes how to enable and read citations in Claude API document blocks, covering citation fields and PDF versus plain text source handling.

  • Claude Citations Feature

    Describes how the Citations feature attaches source references to Claude's answers, covering document setup and citation location formats for each document type.

  • Claude Research Multi-Agent System

    Describes how a multi-agent research system coordinates lead and subagents, with analysis of token usage, performance drivers, and scaling effort to query complexity.

  • Claude Text Watermarking

    Explains how Claude's text watermarking works, what it can and cannot detect, and where its limitations lie, for readers interested in provenance of AI-generated text.

  • Consistency techniques for Claude

    Make Claude's outputs more consistent by specifying exact formats, prefilling responses, constraining with examples, and grounding answers in retrieval.

  • Hallucination Minimization Techniques

    Minimize hallucinations in Claude's outputs by allowing uncertainty, grounding responses in direct quotes, and verifying claims with citations.

All certifications

Terms of use

  • This list is free to use. Every link goes to the vendor’s own site; we don’t control those pages and they may change or move.
  • Each page’s summary is ours, written to say what the page covers. It isn’t the vendor’s and may be imperfect. The list is provided as is, without warranty, and isn’t endorsed by any vendor.
  • We count visits and the links opened, against a random id kept in your browser. Nothing personal is recorded. If you sign up, that id is tied to your account so we can tell whether this list is useful.
  • Anything you submit to this list may be published.