Stop studying.
Start shipping.
The Claude Certified Associate - Foundations exam (code CCAO-F) is for professionals who put Claude to work every day: analysts, project managers, consultants, and operations people who operate Claude with real discipline rather than build on the API. Bayesian Knowledge Tracing maps every skill the exam rewards, writing a fully specified prompt, judging an output before you trust it, choosing the right product surface and model, configuring a Project, and using Claude within your organisation's rules, to a live probability of mastery. We show you exactly what's shaky and drill it until it isn't.
- Concepts
- 164
- Mastery threshold
- 0.90
- Domains
- 7
Domain mastery
Your live mastery map
Updated after every answer. Threshold to retire a concept: 0.90.
Claude Certified Associate - Foundations
The Claude associate certification, officially the Claude Certified Associate - Foundations (CCAO-F), is Anthropic's entry-level exam for professionals who use Claude as a productivity tool, across operations, marketing, project management, education, and communications, rather than building on the API. It assumes limited-to-moderate technical expertise and covers 7 weighted domains, from prompting and output evaluation to configuration, governance, and troubleshooting, across 60 questions scored 100 to 1000 with 720 to pass. This is the entry-level exam our adaptive engine now preps end to end.
- $99
- exam fee
- 60
- questions
- 120 min
- time limit
- 720
- to pass (of 1000)
- 12 mo
- valid for
Official resources
Book the exam and read the official guide
The official exam guide and registration live with Anthropic and Pearson VUE. Start there, then use our adaptive engine to get exam-ready.
Official Anthropic resources · AI Skill Certs is an independent prep platform, not affiliated with Anthropic.
The exam for Claude practitioners
to pass.In 4 weeks.
The exam tests how well you actually operate Claude at work: prompting and task breakdown, evaluating and validating output, choosing the right product and model, designing Claude into a workflow, configuring Projects and knowledge, and using it responsibly. So that's exactly what we drill, until your readiness score clears 720. Below it after four weeks? Your next month is on us.
Diagnostic in 20 minutes. No credit card to start.
How we get you there
Diagnostic in 20 minutes. Plan in 1 hour. Pass in 4 weeks.
720 to pass · we don't release you below 800 in mock
Diagnostic and plan
- 20-minute scenario diagnostic across all five domains
- Initial mastery probability for each of 175 production patterns
- Daily plan locked onto your weakest 30 patterns first
Drill the build patterns
- MCP tool design, model routing, hooks, structured outputs
- Concepts retire only at 0.90 probability
- First scenario-based mock at end of week
Transfer to scenarios
- Archie sessions on every fragile pattern
- Cross-domain scenarios: agent loops + hooks + JSON in one question
- Mid-course mock targeting 700+
Mock until 800+
- Full-length scenario mocks every 48 hours
- We don't release you below 800 in mock
- Sit the exam with confidence, not hope
Mastery proof
Every skill, ordered by the graph.
Two artefacts every learner sees from day one: a live concept heatmap and the prerequisite graph that decides what you study next. The engine below is drawn from our live architect track; the associate graph runs on exactly the same machinery.
Concept space
175 concepts. One probability each.
Knowledge graph fragment
Prerequisites are non-negotiable
Domain 1: Agentic Architecture, 12 of 36 concepts shown
Mapped to the official exam
Seven domains. Weighted to how professionals use Claude.
The Claude Certified Associate - Foundations exam (CCAO-F) validates that you can get reliable, responsible results from Claude across everyday professional work. The breakdown below comes straight from Anthropic's exam guide. We drill every objective under every domain, in prerequisite order.
Prompting and Task Execution
The five-component prompt, the context most people forget to give, and breaking a large ask into checkable steps, then adapting your approach across analysis, research, drafting, and brainstorming.
4 task statements
Output Evaluation and Validation
The largest slice of the exam: judging output for accuracy and completeness, spotting hallucinations and fabricated specifics, fact-checking and demanding traceable citations, and knowing when a result must go to a human before it ships.
6 task statements
Product and Model Selection
Choosing between chat, Projects, research mode, and artifacts, matching Haiku, Sonnet, or Opus to the task's stakes, cost, and speed, and managing the context window as a finite budget.
4 task statements
Workflow Integration and Solution Design
Turning vague business needs into clear task definitions, using Claude for research, planning, and prototyping, deciding what is safe to delegate, and describing its value and limits honestly to stakeholders.
5 task statements
Configuration and Knowledge Management
Configuring Projects with instructions and knowledge, wiring connectors like Google Drive and Gmail, writing system-level instructions that hold up under the two-reader test, and keeping configurations current as they drift.
4 task statements
Governance, Risk, and Responsible Use
Screening appropriate from inappropriate use cases, handling data by sensitivity tier, applying least privilege and your organisation's AI policy, and reasoning through the ethics and disclosure of AI-assisted work.
4 task statements
Troubleshooting and Optimization
Diagnosing why a prompt underperforms with the cheapest fix first, telling a wrong-model problem from a wrong-prompt one, promoting a working fix into a standing instruction, and optimising workflows against the metric that matters.
3 task statements
The exam, in numbers.
- Domains
- 7
- Task statements
- 30
- Scenarios
- 0
- Pass score
- 720
Scaled 100 to 1000. Scenario-based multiple choice. Source: Anthropic's official exam guide.
How it works
Three layers, one job: get you to 0.90 on every pattern you'll ship.
They run as a closed loop. The graph decides what you study, the engine measures whether it stuck, and Archie teaches the gap, then every answer flows back into the engine and re-orders tomorrow's plan. You never study the wrong thing twice.
Knowledge graph
164 concepts. Every one a thing you'll do at the keyboard, not just on the test.
MCP tool schemas, hook ordering, subagent context-passing, model-routing trade-offs, JSON repair patterns: every exam concept is mapped to the production pattern it represents and locked behind its prerequisites. No skipping ahead, no reasoning about hooks before you've nailed the agent loop.
DAG · 164 concepts · 30 task statements · 7 domains
Threshold 0.90
BKT engine
Mastery threshold 0.90. No shipping with a 0.7 on hooks.
Bayesian Knowledge Tracing keeps a live probability that you have actually mastered each pattern. We retire a concept at 0.90 and bring it back the instant a downstream scenario reveals regression. The exam catches a 0.7. So does production.
BKT · per-learner parameters · regression detection
Archie
A Socratic tutor that pressure-tests build decisions.
Archie is built on Claude and constrained to certification content. He never gives the answer. He asks the next question, about your routing decision, your tool schema, your loop termination logic. Every exchange feeds back into the BKT layer, so tomorrow's drills target what you actually struggled to ship.
Claude · graduated hints · misconception detection
Graph orders → engine measures → Archie teaches → engine updates → graph re-orders. The loop never opens.
Built around how you learn
One concept. Three ways in.
Some patterns land as prose. Some only make sense as a diagram. Some you have to watch someone build. So every concept comes three ways: read it, see it, or watch it. You pick the format that clicks for you when you start; it leads every topic. The other two stay one tap away.
The agent loop
An agent runs a loop: the model proposes a tool call, the harness executes it, the result is fed back, and the loop repeats until a stopping condition is met. Your job is to define that stopping condition precisely.
Key concepts
- Tool-call → execute → observe cycle
- Loop termination logic
- Context accumulation per turn
Rendered from the knowledge point's summary + key concepts
Set your default in onboarding · change it any time in settings · every format logs back to the engine
Browse every CCAO-F concept
Open the concept library filtered to this exam - every knowledge point with worked examples, diagrams, official Academy lessons, and practice questions.
Tutor in the loop
Every Archie exchange writes back to the engine.
You won't see the BKT update in real time, but it's happening on every reply. A clean reasoning chain pushes the concept's probability up. A near-miss marks the concept fragile and schedules a return.
- Avg. exchanges per concept
- 2.3
- Hint levels available
- 3
Live in the engine
Concept KP-042 just updated your mastery probability for Prompt Hierarchy from 0.62 to 0.71.
Frequently asked
The questions practitioners ask before they buy.
Professionals who put Claude to work in their day job, analysts, project managers, consultants, marketers, and operations people, rather than engineers building on the API. If you draft, research, analyse, or plan with Claude and want to do it with real discipline, you are the target. We assume no coding; we drill the judgment the exam tests, in the order that builds correctly.
The Claude Certified Associate - Foundations exam (CCAO-F) runs seven domains, scored 100 to 1000 with 720 to pass. It has 60 questions in 120 minutes. It has no fixed scenario bank; items are written directly against the domain objectives. Most items are single-answer, and a few ask you to select more than one option, with each item stating how many responses to pick.
Archie is a Socratic tutor built on Claude. He does not quiz you on definitions. He interrogates the decisions you would make at work: how to specify a prompt, whether an output is safe to send, which model and surface fit the task, and when a result needs a human. Every exchange is grounded in a concept ID and an objective, and feeds back into the engine that picks tomorrow's drill.
BKT keeps a live probability that you have actually mastered each concept, between 0 and 1. Every answer nudges that probability. Once a concept clears 0.90 we stop drilling it and shift attention to your weak areas. It is the same model used by some of the best adaptive systems in education.
The CCAO-F exam costs $99, booked through Pearson VUE and the most affordable of Anthropic's four tracks. We are prep only and not affiliated with Anthropic: you book the official sitting yourself. What we do is get you exam-ready, with a readiness score that maps tightly to actual performance.
Plan for 30 to 45 minutes a day across four weeks. We track your time and adjust the daily plan if you fall behind. The engine retires a concept only when your mastery probability clears 0.90, so the plan ends when you are ready, not on a fixed date.
Yes. Because we track mastery per concept rather than per course, the concepts this exam shares with the developer and architect tracks, prompting, model selection, and responsible use, count towards them too. Time spent here is never wasted when you move up a track.
Your study history stays yours. We use it to personalise your plan and aggregate it anonymously to improve the question bank. We do not sell data, we do not train external models on it, and you can export or delete your account at any time.
Start your diagnostic
Stop studying. Start shipping.
20 minutes to your first mastery map. From there, the engine drills you on the skills the exam actually rewards: sharp prompting, disciplined output evaluation, the right product and model, and responsible use at work.