CCDV-F · Foundationsnew · exam live july 2026

Claude Certified Developer – Foundations

Validates that you can build, integrate, and ship production-grade applications, agents, and workflows: Claude API, Agent SDK, Claude Code, MCP servers, evals, security, and cost optimization.

Who it's for: AI/ML engineers, technical leads, and software engineers with hands-on Claude or LLM experience (Python/TypeScript, REST APIs).

53
Questions
120 min
Time limit
720 / 1000
Passing score
$125
Official fee

Practice bank in production — be first in line

We're building the full Developer question bank against the official blueprint below. Leave your email and get notified at launch (plus early free access).

Official exam blueprint

Domains and weights from the official Anthropic exam guide (v1.0). Your score report shows percent-correct per domain.

Agents and Workflows

14.7%

Agent architecture and tradeoffs, Claude Agent SDK, custom agent loops, subagents, and agentic frameworks.

Applications and Integration

33.1%

Claude API mechanics (messages, tools, streaming, caching, batch), application design across interfaces, CLAUDE.md and configuration management.

Claude Code

3.1%

Rules, Skills, Commands, Agents, session management, headless mode, and settings.json configuration.

Eval, Testing, and Debugging

2.6%

Error type identification, recovery strategies, and trace analysis to isolate failure modes.

Model Selection and Optimization

16.8%

LLM fundamentals, model tiers and tradeoffs, token budgeting, prompt caching, and cost modeling.

Prompt and Context Engineering

11%

Context window management, drift prevention, prompt engineering methods, and output validation patterns.

Security and Safety

8.1%

Prompt injection mitigation, guardrail layering, hooks for safety controls, and secrets management.

Tools and MCPs

10.6%

Tool implementation and function calling, tool description writing, and MCP server development and deployment.

Try 3 official-style questions

Same style and cognitive level as the real exam. Click an answer to see the rationale.

sample 1Applications and Integration

Your application sends a 6,000-token system prompt with static policy content on every request, followed by a short user message. Costs are growing linearly with traffic. Which change most directly reduces cost without losing context?

sample 2Agents and Workflows

An agent loop should stop when Claude has finished its task. Which termination condition is the correct primary mechanism?

sample 3Security and Safety

A coding agent has tools to read files, write files, and execute shell commands. Untrusted repository content may contain prompt-injection payloads. Which defense most directly limits the blast radius of a successful injection?

Meanwhile, the free Claude lessons cover a large part of this blueprint.