Practice for all four Claude certification exams, each against its own published blueprint: scenario items at exam register, flashcards scheduled by spaced repetition, and explanations written against the skill you actually missed.
Minutes and pass mark are the same in all four exam guides, v1.0, effective July 2026. Questions is Synthay’s practice bank across the four.
A support agent exposes four tools. Users who ask to open a ticket keep receiving documentation instead. The tool descriptions each read as one line and share vocabulary. Which change most reliably corrects selection?
// agent.tools[] — as deployed
{ "name": "search_docs", "description": "Find help content for the user" }
{ "name": "create_ticket", "description": "Help the user with their issue" }
{ "name": "lookup_order", "description": "Get information for the user" }
Forcing tool_choice repairs one request and breaks every other path through the workflow. Descriptions that name their trigger and their boundary fix selection wherever the tool appears.
Synthay item, written to the published blueprint.
Not an Anthropic exam question. Illustrative drill state.
A graded miss is saved with its rationale and scheduled for review in one day. Your next cold answer determines the interval after that.
“Tools and MCPs” is 10.6% of the published CCDV-F exam and three separate competencies. Synthay records the question’s skill alongside its result.
Illustrative saved outcome for a Synthay practice question.
Read why your chosen option fails, why the correct answer works, and how the general explanation connects them.
Forcing tool_choice to create_ticket repairs one request and breaks every other path through the workflow. Rewrite each tool’s description to state what it returns, when to use it, and when not to.
A graded miss starts a one-day review interval. Due cold successes advance through 3, 7, 21 and 60 days; one more cold success completes the ladder. Reviews are available throughout their due day. Hints and answer reveals require a new run on a later day.
Intervals run from each graded review, rather than from the original miss. Authored flashcards use a separate SM-2 based schedule.
Readiness measures correct coverage across the practice bank, with a separate tally for this submission. It is a study signal, not a predicted exam score.
Illustrative session data. Domain weights and score-report format from the CCDV-F exam guide, v1.0.
The CCAO-F guide states the approximate share of scored items in each of its seven domains and lists thirty objectives beneath them, without weights of their own. Synthay’s paths follow those numbers rather than a syllabus of our own invention.
The CCDV-F guide states the approximate share of scored items in every domain, resolved to twenty-five sub-skills. Synthay’s paths follow those numbers rather than a syllabus of our own invention.
The CCAR-F guide states the approximate share of scored items in each of its five domains and lists thirty task statements beneath them; every question sits in one of six shared scenarios. Synthay’s paths follow those numbers rather than a syllabus of our own invention.
The CCAR-P guide states the approximate share of scored items in each of its seven domains and lists thirty-eight objectives beneath them, without weights of their own. Synthay’s paths follow those numbers rather than a syllabus of our own invention.
Tile width follows exam weight, with a floor so the lightest domains stay legible. Every objective listed has Synthay questions; a linked name opens its lesson.
Domain weights as published in the Claude Certified Associate – Foundations exam guide, v1.0, effective July 2026.
Tile width follows exam weight, with a floor so the lightest domains stay legible. Every sub-skill listed has Synthay questions; a linked name opens its lesson.
Domain and sub-skill weights as published in the Claude Certified Developer – Foundations exam guide, v1.0, effective July 2026. The guide notes that domain percentages are not themselves used to determine a pass or fail result.
Tile width follows exam weight, with a floor so the lightest domains stay legible. Every domain listed has Synthay questions; a linked name opens its lesson.
Domain weights as published in the Claude Certified Architect – Foundations exam guide, v1.0, effective July 2026.
Tile width follows exam weight, with a floor so the lightest domains stay legible. Every objective listed has Synthay questions; a linked name opens its lesson.
Domain weights as published in the Claude Certified Architect – Professional exam guide, v1.0, effective July 2026.
The program publishes four exam guides, and Synthay has a question bank for each, written against that guide’s own domains. No prerequisite links them — each is sat on its own, so start with the one you’re booked for.
For non-developer professionals: prompting, output validation, product selection, governance. No API or software-development experience assumed.
30Lessons
240Practice questions
For engineers who build, integrate and ship Claude applications, agents and workflows. Eight domains, from Applications and Integration at a third of the paper down to Debugging at 2.6%.
25Lessons
302Practice questions
Agentic orchestration, tool and MCP interfaces, Claude Code configuration, context reliability. Five domains, twenty-seven task statements. Each paper draws 4 scenarios from a bank of 6.
30Lessons
360Practice questions
End-to-end solution design, retrieval pipelines, evaluation and observability, governance and stakeholder lifecycle.
38Lessons
252Practice questions
Exam figures as published in each credential’s exam guide, v1.0, effective July 2026. All four are proctored by Pearson VUE, run 120 minutes, pass at a scaled 720 of 100–1,000, and stay valid 12 months. None lists a mandatory prerequisite. Fees are paid to Pearson VUE, not to Synthay. Question counts are Synthay’s own bank, not Anthropic’s.
Preparation that fits between a standup and a deploy: driven from the keyboard on a laptop and by thumb on a phone, resumable mid-session, and honest about how much of the paper you have left.
Select answers, commit a drill answer, request a hint, flag a mock item and move between questions from the keyboard.
Fifteen items, thirty minutes, no explanations until you submit. Items are drawn per domain in the published proportions, and come in both formats the guide lists — multiple-choice and multiple-response, which states how many responses to select — so a short form carries the shape of the real paper without asking two hours of you.
Item counts derived by applying the guide’s published domain weights to a 15-item form. The two lightest domains, at 3.1% and 2.6%, round to zero at this length.
Weights, item counts and policies on this page are quoted from the published exam guides, with the version they were read from. Guide revisions are reviewed before the question bank and this page are updated.
| Credential | Code | Guide | Effective | Questions |
|---|---|---|---|---|
| Associate – Foundations | CCAO-F | v1.0 | Jul 2026 | 240 |
| Developer – Foundations | CCDV-F | v1.0 | Jul 2026 | 302 |
| Architect – Foundations | CCAR-F | v1.0 | Jul 2026 | 360 |
| Architect – Professional | CCAR-P | v1.0 | Jul 2026 | 252 |
Questions are Synthay’s practice bank for each exam, written against that guide’s domains, with mocks sampled per domain at the published weights. They are not a claim to reproduce the live item bank.
Short lessons, one per exam skill, that ask before they explain. About eight minutes each, feedback on every answer, and the items you miss come back in spaced review next to your questions.
Prompt, check and choose Claude for everyday business work, one short lesson per exam skill.
Build agents, API integrations, tools and MCP servers by reading and completing real code.
Agent loops, tool and MCP design, Claude Code and context management, taught inside the exam's six scenarios.
Judge and justify end-to-end Claude solution design, from architecture and retrieval to evaluation and governance.
Exam policy below is quoted from the published guides. Where the answer is about Synthay rather than the exam, it says so.
Something not covered? Ask usNo. Synthay is an independent preparation product, not affiliated with, endorsed by, or authorized by Anthropic. Everything quoted here comes from the publicly available exam guides, cited with the version it was read from.
No, and they never will be. Every item in Synthay is written by us against the published blueprint. Candidates accept a confidentiality agreement covering all exam content before the exam begins; live items are Anthropic’s confidential property, and reproducing them would put your credential at risk as well as ours.
No. None of the four guides lists a mandatory prerequisite or required course, and no ordering between the credentials is published — Architect – Professional does not require Architect – Foundations. The credential is awarded on exam performance alone.
For CCDV-F the guide recommends, without requiring: one to five years in software engineering, six months or more hands-on with Claude or comparable LLM systems, proficiency in Python and/or TypeScript, and fluency with REST APIs and CLI tools.
Results are reported on a 100–1,000 scale with a cut score of 720. The exam is criterion-referenced: you are measured against a standard set by a formal standard-setting study, not against other candidates. The published domain percentages describe how items are distributed — the guide states they are not used to determine your pass or fail result.
Your score report gives pass or fail, the scaled score, and percent-correct by domain.
You may retake after a waiting period that lengthens with each attempt: 14 days after the first failure, 30 after the second, 90 after the third. You may sit a given exam up to four times in a rolling twelve months, and the fee applies to each attempt. Limits are per exam, so not passing one does not block you from registering for a different one.
Twelve months from the date it is awarded. Renewal is a free, non-proctored assessment on the Anthropic Partner Academy, with no fee for renewing on time. If the credential lapses you must retake the full exam at the full fee to regain certified status.
Pearson VUE, online proctored and/or at a test center per program policy, with registration through the Anthropic Partner Academy. CCDV-F is $125 USD; Associate – Foundations is $99, Architect – Foundations $125, Architect – Professional $175. You can cancel or reschedule up to 24 hours before your appointment; changes inside 24 hours forfeit the fee.
We won’t promise that, and neither will anyone honest. The CCDV-F guide is explicit that Anthropic does not guarantee any particular resource ensures a passing result, and it recommends combining study with building and operating a real Claude application. Synthay covers each exam’s blueprint and shows you where you are weak; the hands-on part is still yours.
After a session, see correct coverage across the practice bank for every domain, with your weakest sub-skills one click from their own drills. No card details, no trial countdown.
Independent preparation. Not affiliated with Anthropic.
Readiness by domain
Your weakest sub-skill — D8 · Tool Implementation — is one click from its own drill.
Illustrative cumulative readiness after multiple sessions.