← all certifications
Claude Certified Architect - Foundations badge

Claude Certified Architect - Foundations

Make sound production tradeoffs across Claude Code, the Claude Agent SDK, the Claude API, and MCP.

Developers and architects who design production Claude systems and can reason through ambiguous, scenario-based architecture decisions.

60
Questions
120 min
Time limit
$125
Exam fee
720 / 1000
Passing score
Scenario-based multiple-choice and multiple-response; four scenarios drawn from six
Format
Proctored online or at a test center
Delivery
12 months
Validity
v1.0 · July 2026
Guide
Official exam guide (PDF) ↗

Exam domains

Weighted objectives straight from the exam guide.

Agentic Architecture and Orchestration

27%
  • Implement the tool-use lifecycle from stop reason to tool result
  • Choose coordinator and subagent topologies
  • Use Task, allowedTools, isolated context, parallelism, and forked sessions
  • Enforce prerequisites, decompose concerns, and structure handoffs
  • Use hooks for deterministic controls and normalization
  • Choose sequential or adaptive decomposition
  • Resume or fork without carrying stale context

Tool Design and MCP Integration

18%
  • Write precise tool descriptions and boundaries
  • Return structured and retry-aware MCP errors
  • Manage tool distribution and tool choice
  • Scope MCP configuration and resources
  • Choose Claude Code file, shell, and search tools safely

Claude Code Configuration and Workflows

20%
  • Design CLAUDE.md hierarchy, imports, rules, and memory
  • Create project and user commands and Skills
  • Apply path-specific rules
  • Choose plan mode, direct execution, or Explore
  • Use examples, test-driven iteration, and interviews
  • Run headless CI with structured output and independent review

Prompt Engineering and Structured Output

20%
  • State explicit evaluation criteria
  • Use few-shot examples for consistent judgment
  • Enforce schemas with tool use and tool choice
  • Validate, retry, and feed back semantic errors
  • Use batch processing for appropriate workloads
  • Separate generator and independent reviewer passes

Context Management and Reliability

15%
  • Place facts to reduce lost-in-the-middle failures
  • Escalate ambiguity and policy gaps
  • Propagate structured errors and partial results
  • Use scratchpads, subagents, manifests, and compaction for large codebases
  • Calibrate confidence and human review
  • Track provenance, conflicts, dates, and content types

Study path · 21 lessons

01
Certification Strategy
orientation · required
02
Claude Product And Model Landscape
core · required
03
Model Selection And Token Economics
core · required
04
Prompting And Task Decomposition
core · required
05
Context Knowledge Memory And Caching
core · required
06
Output Evaluation And Validation
core · required
07
Messages Api And Application Lifecycle
core · required
08
Structured Output And Defensive Parsing
core · required
09
Tool Use And Agentic Loops
core · required
10
Mcp Server Design And Integration
core · required
11
Claude Agent Sdk And Hooks
core · required
12
Application Security And Secrets
core · required
13
Evals Testing Debugging And Observability
review · required
14
Claude Code For Development Teams
core · required
15
Multi Agent Orchestration And Delegation
core · required
16
Agent Sdk Sessions Subagents And Context
core · required
17
Tool Contracts Errors And Progressive Discovery
core · required
18
Claude Code Memory Rules Skills And Ci
core · required
19
Reliable Extraction Batch And Reviewers
core · required
20
Long Context Reliability Provenance And Escalation
core · required
21
Architect Foundations Scenario Capstone
capstone · required

Go deeper in the main curriculum

Other tracks