24 technical primitives, made scannable.
Concept pages preserve depth but lower friction with TLDR stats, diagrams, evidence badges, exam traps, and a sticky study rail. Grouped by exam domain.
Featured concept
Agentic loops: think, act, observe, decide. The mascot becomes the concept anchor.
D1 · 27% of the exam.
5 concepts in this domain.
Agentic Loops
An agentic loop turns one API response into a controlled, multi-turn system. The harness reads stop_reason, di…
Subagents
Subagents are specialized, isolated agents spawned by a coordinator to handle domain-specific tasks while pres…
Stop Reason
stop_reason is the authoritative struct field that says why Claude stopped, either end_turn (finished) or tool…
Session State & Persistence
Session state is the running message list (and any external persistence) that gives an agentic loop continuity…
Human-in-the-Loop Escalation
Escalation is the deterministic handoff path when policy thresholds, low confidence, or repeated failure condi…
D2 · 18% of the exam.
5 concepts in this domain.
Tool Calling
Tool calling is how Claude decides to invoke external functions and pass structured arguments. Tools are routi…
Tool Choice
tool_choice is the parameter that controls whether Claude can decide to use a tool ("auto"), must call any too…
Model Context Protocol
MCP is a communication standard that lets Claude access pre-built tools, resources, and prompts from specializ…
SDK Hooks (Pre/PostToolUse)
Hooks are deterministic code that runs before or after tool calls. They enforce policy that prompt-only patter…
Tool Evaluation & Testing
Evaluation is how you measure tool-call correctness against ground-truth datasets. Coverage in vault is thin; …
D3 · 20% of the exam.
4 concepts in this domain.
CLAUDE.md Hierarchy
CLAUDE.md is persistent project memory loaded automatically by Claude Code. A three-level hierarchy (user → pr…
Plan Mode
Plan Mode forces Claude Code to draft and approve a multi-step plan before executing. Use it for non-trivial c…
Skills
Skills are reusable, on-demand task workflows defined in markdown with YAML frontmatter. Unlike CLAUDE.md (alw…
Checkpoints & Session Management
Checkpoints save and restore conversation state. Vault coverage is thin; full authoring requires Phase 6 resea…
D4 · 20% of the exam.
8 concepts in this domain.
System Prompts & Instructions
System prompts establish role, constraints, format, and tool guidance. Anatomy: role, capability boundaries, s…
Prompt Caching
Prompt caching reduces cost (~90%) on repeated context like long system prompts and tool definitions. Cache br…
Batch API
Message Batches API: 50% discount for async, non-time-sensitive workloads. Vault coverage thin; needs Phase 6 …
Structured Outputs
Structured outputs guarantee Claude returns JSON matching a schema instead of natural language. Force a tool w…
Vision & Multimodal
Vision lets Claude process images alongside text. Vault coverage thin; needs Phase 6 research.…
Streaming
Streaming returns tokens as they're generated for low-latency UX. Vault coverage thin; needs Phase 6 research.…
Attention Engineering
Attention engineering is the discipline of placing critical context where the model attends most strongly, hig…
4D Framework
Delegation, Description, Discernment, Diligence, Anthropic's 4D framework for agent prompt design. Vault cover…
D5 · 15% of the exam.
2 concepts in this domain.