Support the project
- 60 items, 4 scenarios, 120 minutes — built the way the real paper is
- Five of them, each drawing a different four from the bank of six
- Blueprint-weighted, so the domain mix matches the real exam
- A rationale for every option, not just the correct one
In the meantime, the study material and quizzes are free: browse the exam domains or try the domain quizzes.
What is in the pack
Five full-length mock exams
Each mock mirrors the real paper's shape: 60 scored items in 120 minutes, with feedback withheld until you submit. Matching the count and the clock matters — a 45-item sitting has the right pace and rehearses none of the endurance.
| Domain | Blueprint | Items per mock |
|---|---|---|
| D1 Agentic Architecture & Orchestration | 27% | 16 |
| D2 Tool Design & MCP Integration | 18% | 11 |
| D3 Claude Code Configuration & Workflows | 20% | 12 |
| D4 Prompt Engineering & Structured Output | 20% | 12 |
| D5 Context Management & Reliability | 15% | 9 |
Every option gets a reason, not just the right one. Knowing you picked B is worth little; knowing why C was tempting is the part that transfers to the real paper. The free domain quizzes are written to the same standard — try one before you decide this is worth anything to you.
Not official, and not a prediction of the real bank, which is confidential. The free material stays free: all 30 task statements, the domain quizzes and the 12 official samples. Format, fee and scoring questions are answered on how the exam works.