ExamFinch.com My Study

Cheat sheet

CCAR-F Cheat Sheet

Practice this exam

Agentic Architecture

  • 27% of exam
  • Agents Routing Chaining Parallelism Subagents

Claude Code

  • 20% of exam
  • Memory Settings Permissions Hooks CI

Prompts + Output

  • 20% of exam
  • System Examples Schemas JSON Stops

Tools + MCP

  • 18% of exam
  • Schemas Tools Resources Prompts Transport

Context + Reliability

  • 15% of exam
  • RAG Caching Evals Retries Guardrails

Quick Facts

  • Credential CCAR-F
  • Issuer Anthropic
  • Access Partner network
  • Focus Production architecture
  • Users Claude architects
  • Core Claude ecosystem
  • Verify Exam portal

Simple First AG

  • Call, retrieve, chain, route, agent.
  • Call Retrieve Chain Route Agent

Workflow vs Agent AG

Workflow

  • Predictable sequence
  • Easier control

Agent

  • Dynamic path
  • Higher autonomy
  • Prefer simplest control

Pattern Picker AG

  • Task is simple → Single call
  • Needs facts → RAG call
  • Steps known → Prompt chain
  • Input classes known → Router
  • Subtasks independent → Parallel calls
  • Steps unknown → Agent loop
  • Quality measurable → Evaluator optimizer
  • Risk high → Human review

Architecture Patterns AG

  • Single call Best baseline
  • RAG call Retrieve then answer
  • Prompt chain Ordered model steps
  • Router Classify then dispatch
  • Parallel Independent subtasks
  • Orchestrator Plan then delegate
  • Evaluator Judge then improve

Agent Controls AG

  • Loop limit Bound tool cycles
  • Role scope Narrow responsibility
  • Tool scope Least privilege
  • State Track decisions
  • Handoff Define output contract
  • Escalation Ask human
  • Trace Log key steps

Claude Code CO

  • CLAUDE.md Project memory
  • settings.json User or shared project settings
  • Permissions Gate risky actions
  • Slash command Reusable workflow
  • Hook Run workflow action
  • Subagent Specialized helper
  • Headless Noninteractive run

Schema vs Prose PR

Schema

  • Machine parsed
  • Validated fields

Prose

  • Human read
  • Flexible wording
  • Parsing needs schema

Prompt Basics PR

  • System Durable constraints
  • Task Goal and inputs
  • Criteria Success definition
  • Examples Show desired shape
  • Context Relevant facts
  • Delimiters Separate content
  • Refusal Handle unsafe asks

Structured Output PR

  • Schema Constrain fields
  • Enum Limit choices
  • Required Prevent omissions
  • Type Protect parsing
  • Stop sequence End generation
  • Parser Validate output
  • Repair Retry invalid JSON

Tool Safety TO

  • Name, schema, scope, auth, errors.
  • Name Schema Scope Auth Errors

Tool vs Resource TO

Tool

  • Performs action
  • Needs arguments

Resource

  • Provides context
  • Read oriented
  • Action needs tool

MCP Primitives TO

  • Tool Callable action
  • Resource Readable context
  • Prompt Reusable template
  • Server Expose capabilities
  • stdio Local subprocess
  • HTTP Remote service
  • Auth Protect access

stdio vs HTTP TO

stdio

  • Local process
  • Developer workflow

HTTP

  • Remote service
  • Network access
  • Match deployment boundary

Production Ready RE

  • Eval, retry, timeout, monitor, fallback.
  • Eval Retry Timeout Monitor Fallback

Eval vs Monitor RE

Eval

  • Predeployment test
  • Known cases

Monitor

  • Production signal
  • Live outcomes
  • Use both

Reliability Picker RE

  • Output must parse → Schema validation
  • Facts may change → Retrieve current source
  • Latency matters → Smaller model
  • Cost matters → Cache prefix
  • Tool may fail → Structured error
  • Safety matters → Guardrails
  • Behavior drifts → Regression evals
  • Ambiguity remains → Ask user

Context + Retrieval RE

  • Context window Token budget
  • Compression Keep essentials
  • Retrieval Fetch relevant facts
  • Chunking Split documents
  • Citation Expose provenance
  • Caching Reuse static prefix
  • Freshness Check current facts

Production Reliability RE

  • Eval Measure behavior
  • Golden set Known examples
  • Regression Catch drift
  • Retry Handle transient failure
  • Timeout Bound latency
  • Fallback Degrade gracefully
  • Monitor Track outcomes

Common Traps

Overagenting

  • Simple call works ≠ Avoid needless loops

Broad Tools

  • Scope permissions ≠ Constrain inputs

Unparsed Output

  • Validate schemas ≠ Repair failures

Stale Context

  • Retrieve current facts ≠ Cite sources

No Evaluation

  • Define success ≠ Track regressions

Last Minute

  • 1. Start with baseline
  • 2. Pick pattern deliberately
  • 3. Scope tool access
  • 4. Validate structured output
  • 5. Handle tool errors
  • 6. Budget context tokens
  • 7. Add eval coverage
  • 8. Plan fallback behavior