AIP-C01 Study Hub

Practice

92 questions across 5 domains. Includes 20 cross-domain questions.

Select Domain

Select Level

92 questions selected

Drills

Ordering Sequences

RAG Pipeline

  1. 1 Ingest
  2. 2 Chunk
  3. 3 Embed
  4. 4 Index
  5. 5 Query
  6. 6 Retrieve
  7. 7 Augment prompt
  8. 8 Generate
  9. 9 Filter output

Agent Loop

  1. 1 Receive query
  2. 2 Plan/reason
  3. 3 Select tool
  4. 4 Execute
  5. 5 Observe result
  6. 6 Decide (continue/respond)
  7. 7 Return

Security Layers

  1. 1 IAM auth
  2. 2 API Gateway validation
  3. 3 Guardrails input
  4. 4 Model invocation
  5. 5 Guardrails output
  6. 6 Response encryption

Knowledge Base Setup

  1. 1 Create S3 bucket
  2. 2 Upload docs
  3. 3 Create KB
  4. 4 Select embeddings model
  5. 5 Select vector store
  6. 6 Configure chunking
  7. 7 Sync data source
  8. 8 Test retrieval

Deployment Pipeline

  1. 1 Code
  2. 2 Build
  3. 3 Test
  4. 4 Stage
  5. 5 Canary
  6. 6 Production
  7. 7 Monitor
  8. 8 Rollback if needed

Prompt Flow Execution

  1. 1 Input
  2. 2 Pre-processing node
  3. 3 Condition check
  4. 4 Branch A (prompt chain) OR Branch B (direct response)
  5. 5 Post-processing
  6. 6 Guardrails
  7. 7 Output

Evaluation Pipeline

  1. 1 Define metrics
  2. 2 Create evaluation dataset
  3. 3 Select evaluator model
  4. 4 Run evaluation job
  5. 5 Analyze results
  6. 6 Compare models
  7. 7 Deploy winner
  8. 8 Monitor in production

Cross-Region Inference Setup

  1. 1 Enable inference profile
  2. 2 Update app to use inference profile ARN
  3. 3 Configure IAM with region conditions
  4. 4 Test failover
  5. 5 Monitor with CloudWatch

Matching Exercises

Service -> Data Type

Trigger / Pattern AWS Service / Answer
Comprehend Text entities
Transcribe Audio
Textract Documents
Rekognition Images/Video
Bedrock Data Automation Mixed/multimodal

Problem -> Solution

Trigger / Pattern AWS Service / Answer
Hallucination Contextual grounding
PII leak Sensitive info filter (ANONYMIZE)
Rate limits Circuit breaker (Step Functions)
Mathematical incorrectness Automated Reasoning
Prompt injection Prompt Attack filter

Architecture Pattern -> AWS Service

Trigger / Pattern AWS Service / Answer
Circuit breaker Step Functions
Model cascading Lambda routing
Semantic cache Vector DB (ElastiCache/DynamoDB)
Prompt governance Bedrock Prompt Management + CloudTrail
Agent deployment AgentCore Runtime

Human Review Pattern -> Service

Trigger / Pattern AWS Service / Answer
Low-confidence routing A2I (Augmented AI)
Evaluation datasets Ground Truth / Ground Truth Plus
Approval workflows Step Functions Wait-for-Callback

Guardrails Component -> Verification Type

Trigger / Pattern AWS Service / Answer
Content filter Harmful content
Contextual grounding Hallucination
Automated Reasoning Logical correctness
PII filter Data protection
Prompt Attack Jailbreak / injection

Cost Optimization -> Technique

Trigger / Pattern AWS Service / Answer
Repeated system prompts Bedrock Prompt Caching
Similar user queries Semantic caching
Mixed complexity queries Model cascading / Intelligent Prompt Routing
Non-real-time bulk processing Batch inference (50% discount)
Idle SageMaker endpoint Auto-scaling to zero

External Practice Exams