Free & open-source — no account required

CCA-F prep that tells you if you're ready

Most prep sites give you questions and a score. This one gives you real proctoring, real tracking, and evidence-based recommendations — so your practice score actually predicts your real score.

Take the diagnosticSee the learning path

No card· No account· No limits

117

Lessons

Structured across all 5 domains

800+

Questions

Domain, mixed, and full mock formats

∞

Mock exams

Unlimited, weighted to the real split

720/1000

Pass score

Same scale, same format as the real exam

The exam, at a glance

The CCA-F has 60 single-answer questions in 120 minutes, scored 720/1000 to pass. Weighted across 5 domains:

Agentic Architecture27%

The highest-weighted domain. Agent loops, planning, tool orchestration, multi-agent coordination, and the Claude Agent SDK (state, durable workflows, queues, retries, observability).

Claude Code20%

Configure and drive Claude Code: CLAUDE.md, custom commands, plan mode, hooks, MCP integration, CI/CD, and team workflow patterns.

Prompt & Structured Output20%

Explicit criteria, few-shot, chain-of-thought, XML structuring, and reliable structured output via JSON schemas, tool_use, and validation-retry loops.

Tools & MCP18%

Design effective tools (clear descriptions, structured errors, safe execution) and integrate the Model Context Protocol — architecture, resources, tools, prompts, transports, and security.

Context & Reliability15%

Manage the context window (budgeting, compression, caching, RAG) and build for reliability: retries, fallbacks, guardrails, validation pipelines, and production hardening.

Agentic Architecture
Claude Code
Prompt & Structured Output
Tools & MCP
Context & Reliability

Why your scores here are real

Three things that make this different from other CCA-F prep sites.

Proctored exam conditions
Mocks detect tab-switches, copy, DevTools, and fullscreen exits. You can't game your score — which means your mock score actually predicts your real one.
Real captured data
Every scroll, answer, and confidence rating is recorded locally. Your dashboard and readiness reflect what you actually did — never placeholder numbers.
Evidence-driven recommendations
Recency-weighted mastery, overconfidence detection, and scenario-vs-recall gaps rank what to study next — with a direct link to fix each gap.

Know where you are, every step

Each phase feeds the next — diagnostic shapes your path, practice feeds your readiness.

01~15 min

Diagnose

60-question diagnostic maps your strengths and gaps across all 5 domains with an estimated score.

Take diagnostic
02self-paced

Learn

116 lessons in domain-weight order with embedded warmups and checkpoints.

Open the path
03daily

Practice

Flashcards, mixed practice, and domain drills — spaced repetition surfaces what you're about to forget.

Start flashcards
04120 min

Mock & ready

Full-length mocks under proctoring. Readiness view tells you when to book the real exam.

Try a mock

Straight answers

Questions you're probably asking right now.

You'll know when you're ready.

Not because a progress bar says so — because your diagnostic, practice, and mock scores across all 5 domains tell you.

Take the diagnosticTry a mock exam
FrontendX — not affiliated with AnthropicChangelogGitHubDownload book