Adaptive prep · Claude certifications

Master the exam,
one concept at a time.

AI Skill Certs runs a Bayesian Knowledge Tracing engine over every Claude certification. It maps each exam to a graph of atomic concepts, tracks your mastery of each to a live 0.90 probability, and hands the weak ones to Archie, a Socratic AI tutor built on Claude. You study exactly what has not stuck yet, in the order that builds correctly.

Certification tracks
4
Task statements mapped
123
Mastery threshold
0.90

The engine · one loop

Knowledge graph

Orders every concept by prerequisite

01

Mastery engine

Live 0.90 probability per concept

02

Archie, the tutor

Socratic, never gives the answer

03

Every answer flows back and re-orders tomorrow's plan.

The engine

A concept graph and a mastery signal, for every track.

Two artefacts every learner sees from day one: a live concept heatmap that shows exactly where you stand across the exam, and the prerequisite graph that decides what you study next. The engine is the same on every certification; only the concepts change.

Concept space

175 concepts. One probability each.

Sample · Architect Foundations track

live
01 · Agentic Architecture27% · 47 concepts
02 · Tool & MCP18% · 32 concepts
03 · Claude Code20% · 35 concepts
04 · Prompt & Output20% · 35 concepts
05 · Context & Reliability15% · 26 concepts
concepts mastered94/175
readiness703
weakest domainContext
mastered ≥ 0.90strongfragilelockedregression

Knowledge graph fragment

Prerequisites are non-negotiable

DAG
Loading diagram...
mastered ≥ 0.90in flightweaklocked

Domain 1: Agentic Architecture, 12 of 36 concepts shown

Sample · Architect Foundations track

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.

Layer 01 · DAG
looptoolresultsubagenthookstop
Layer 01
Orders what you study

Knowledge graph

Every track gets its own graph: 616 concepts across the live tracks, each 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 · 616 concepts · prerequisite-ordered · 4 live tracks

Layer 02 · BKT
KP-042
0.71
KP-118
0.94
KP-073
0.58
KP-091
0.86

Threshold 0.90

Layer 02
Measures what you've mastered

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

Layer 03 · Claude
How do I stop the agent loop?
What does stop_reason return when the model still wants a tool?
tool_use, so I keep looping.
Right. And when it's end_turn?
Layer 03
Teaches what you're missing

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.

Learn · the agent loop

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

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

Sample · Architect Foundations track

ArchieSocratic tutor · Claude
session · live
hint level 2 of 3·concept KP-042 prompt hierarchy·linked to domain 4

Live in the engine

Concept KP-042 just updated your mastery probability for Prompt Hierarchy from 0.62 to 0.71.

From the journal

Notes on the exam, the method, and the model

Frequently asked

The questions people ask before they start.

AI Skill Certs is an adaptive prep platform for Anthropic's Claude certifications. Instead of a static course, it runs a Bayesian Knowledge Tracing engine over each exam: it breaks the exam into a graph of atomic concepts, tracks how well you have mastered each one, and spends your study time on the concepts that are not yet stuck. A Socratic AI tutor, Archie, teaches the gaps.

Every exam is mapped to a directed graph of concepts, each locked behind its prerequisites. As you answer questions and work with Archie, Bayesian Knowledge Tracing keeps a live probability, between 0 and 1, that you have genuinely mastered each concept. Once a concept clears 0.90 we retire it and shift attention to your weak areas, bringing anything back the moment a later scenario shows it has regressed. You never study the wrong thing twice.

Two tracks are live today: Claude Certified Architect - Foundations (CCAR-F) and Claude Certified Developer - Foundations (CCDV-F). Two more are under development: Claude Certified Associate - Foundations (CCAO-F), the entry-level track for professionals using Claude at work, and Claude Certified Architect - Professional (CCAR-P), the senior architect tier. Each track is a full adaptive experience with its own concept graph, question bank, and exam-accurate scoring. New tracks are added as Anthropic's Claude certification program grows.

Archie is a Socratic tutor built on Claude and constrained to certification content. He never hands you the answer. He asks the next question, about your routing decision, your tool schema, your loop termination logic, so you have to reason it through yourself. Every exchange is grounded in a specific concept and feeds back into the engine that picks tomorrow's drill.

Yes. Because progress is tracked per concept rather than per course, the concepts shared across tracks, prompt engineering, tool design, context management, carry their mastery with you. Clear a concept on the Developer track and you start ahead on the Architect track wherever the two exams overlap.

One flat fee per track gives you full access until you sit the exam: no per-question paywalls, no caps on Archie, no separate charge for mock exams. You can start with a diagnostic before you decide. See each certification's page for its current price.

No. AI Skill Certs is an independent prep platform and is not affiliated with Anthropic. We do not administer the exams or sell exam seats; you book the official sitting yourself. What we do is get you exam-ready, with a readiness score that maps tightly to actual performance.

Start free

Pick a certification. Start mastering it today.

Twenty minutes to your first mastery map. From there the engine drills the concepts you haven't locked yet, and Archie teaches the ones you're missing, across whichever Claude certification you're chasing.

Get started