⚡ Claude Certified Architect – Foundations — Cram Jam

Last-minute dense recall sheet · read fast, stash in memory. Not a substitute for the full guide.
$125 · 4 core areas: Code / SDK / API / MCP
Official: 60 items · 120 min · pass 720/1000 · 12-mo valid
Official: 4 of 6 scenarios · proctored (online and/or test center) · closed book
Full guide

Official Exam Facts (CCAR-F Exam Guide)

  • Cert page: $125 · four core areas (Code, Agent SDK, API, MCP) · must review Exam Guide + Terms + Cert Policy first.
  • Exam Guide: 60 items/120min · multi-choice & multi-response (each states how many to pick) · scaled 720/1000 pass · 12-mo valid · 4 of 6 scenarios · proctored (online and/or test center) · pass/fail + percent-correct by domain.
  • Guide itself can change — re-check before booking. ~6mo hands-on experience is a community rule of thumb, not an official figure.

Four Core Areas

  • Claude Code — agentic coding CLI.
  • Claude Agent SDK — build custom agent apps.
  • Claude API — messages, tools, streaming, caching…
  • MCP — standard protocol for tools/data/prompts.

5 Domains (official weights)

DomainWt
Agentic Architecture & Orchestration27%
Tool Design & MCP Integration18%
Claude Code Configuration & Workflows20%
Prompt Engineering & Structured Output20%
Context Management & Reliability15%

Scenario Bank (4 of 6 drawn)

  • 1. Customer Support Resolution Agent — Agent SDK, MCP tools (get_customer/lookup_order/process_refund/escalate_to_human), 80%+ first-contact resolution.
  • 2. Code Generation with Claude Code — CLAUDE.md, permission modes, subagent handoff.
  • 3. Multi-Agent Research System — lead agent + subagents, fan-out, synthesis.
  • 4. Developer Productivity with Claude — review/docs/refactor automation vs human control.
  • 5. Claude Code for CI — non-interactive mode, hooks as gates, rate-limit/cost discipline.
  • 6. Structured Data Extraction — tool-schema forced output, field validation.

Agent Loop Anatomy

  • Gather context → act → verify → repeat, until stop.
  • API mechanics: send messages+tools → model emits tool_use → you execute → return tool_result → repeat until end_turn.
  • Always define a stop condition: turns, tokens, or human interrupt.

Prompt vs Agent vs Multi-Agent

SignalUse
Everything's in the input, one passPrompt
Needs live data/action, boundedTool-using agent
Decomposes / parallelizableMulti-agent

Default rule: start simplest, escalate only as needed. Every step up = more cost/latency/failure surface.

MCP Primitives

PrimitiveDriven by
ToolsModel-controlled
ResourcesApplication-controlled
PromptsUser-controlled
SamplingServer-initiated (asks client's model)

MCP Transports

  • stdio — local subprocess, simple, no network. Claude Code default for local servers.
  • Streamable HTTP — remote/shared servers, multiple clients, streaming.

Host = app (Claude Code). Client = 1:1 connection inside host. Server = exposes tools/resources/prompts.

Tool Schema Design Rules

  • Description is a prompt — vague description → wrong tool / bad args.
  • Explicit types, constraints, enums over free text.
  • Granularity: not too narrow (tool-selection + context overhead), not too broad (ambiguous args).
  • Document idempotency & side effects; gate non-idempotent/destructive tools.

Claude Code Features

FeatureOne-liner
CLAUDE.mdproject instructions, auto-loaded
Subagentsseparate context, bounded subtask
Hooksdeterministic shell cmds at loop points
Skillson-demand packaged instructions
Slash commandsreusable custom workflows
MCP integrationClaude Code = MCP host

Permission Modes

  • Interactive (default) — approve each sensitive action.
  • Plan mode — research/propose only, no edits until approved.
  • Auto-accept edits — edits auto-approved, other sensitive actions still gated.
  • Autonomous/bypass — no prompts; sandboxed/CI use only, not a production default.

Prompt Engineering Ladder

  1. Clear direct instructions
  2. System prompt for standing context
  3. Examples (few-shot)
  4. Chain-of-thought / extended thinking
  5. Structured sections (XML tags)
  6. Prefill / constrained (tool-schema) output

Prompt → retrieval → fine-tune, in that cost order. Try cheapest fix first.

Context Budget — What Consumes It

  • System prompt + every tool def (costs tokens even unused) + history + retrieved docs + tool results.
  • Context rot: quality degrades as window fills, before hitting the hard limit.
  • Fix: trim stale tool output, summarize/compact, scope tools to the task.

Prompt Caching Rules of Thumb

  • Mark a stable prefix (system prompt, tools, big doc) cacheable → cuts cost+latency on reuse.
  • Best fit: long stable content reused across many requests, fast (cache expires after inactivity, ~minutes by default).
  • Stable content first, variable content last — cache matches a prefix.

Retrieval vs Long Context

Long contextRetrieval
Fitsmall/bounded, reused oftenlarge/changing/huge corpora
Costcaching helpspay per fetch + infra
Complexitysimpleindex/retriever needed

Model Selection

TierFit
Opushardest reasoning, highest cost/latency
Sonnetbalanced default workhorse
Haikufast/cheap, high-volume simple tasks

Mixing tiers within one architecture (cheap for bulk, top tier for the hard step) is expected, not a shortcut.

Streaming vs Batch vs Sync

  • Streaming — interactive user waiting; improves perceived latency only.
  • Sync — short programmatic call, no one watching it stream.
  • Batch — high volume, non-urgent, discounted; trades latency for cost.

Evaluation & Guardrails

  • Evals = held-out task set, run on prompt/tool/model change → catch systemic regressions.
  • Guardrails = runtime layers: input classify, tool-level constraints, output validation → catch bad individual outcomes.
  • Complementary, not substitutes.

Cost Levers

  • Model-tier mixing · prompt caching · batch for non-urgent volume · shorten prompts before adding infra.
  • Per-task token/turn/dollar budgets; alert on anomalous spend.

Failure Modes & Fixes

FailureFix
Looping/thrashingstep/retry budget
Context rotcompaction/context editing
Tool misusebetter schema/description
Ungrounded claimscitations, verification
Runaway costexplicit budgets
Unsafe autonomous actionhuman checkpoint, least privilege

Keyword → Answer

  • "needs live data/action" → tool-using agent
  • "decomposes / parallel" → multi-agent
  • "repo conventions repeated every session" → CLAUDE.md
  • "before this runs it must be approved" → human-in-the-loop / plan mode
  • "same tool needed by many apps" → MCP server
  • "answers get worse the longer it runs" → context rot → compact
  • "huge / changing corpus" → retrieval
  • "same big prompt reused often, fast" → prompt caching
  • "high volume, no one waiting" → batch
  • "guaranteed parseable output" → structured output / tool schema

Top Traps

Tools(model) vs Resources(app) vs Prompts(user) · retrieval vs caching-eligible long context · multi-agent as default overkill · agent with no human checkpoint before irreversible action · caching used to mask a bloated prompt instead of shortening it · assuming the Exam Guide can't change between now and your booking
Ask what the scenario optimizes for — cost / latency / accuracy / autonomy&safety / simplicity — then pick the simplest architecture that satisfies it.
Cram Jam · Claude Certified Architect – Foundations · pairs with the full study guide · figures sourced from Anthropic's official CCAR-F Exam Guide PDF, which can change — re-check before booking · not affiliated with Anthropic.