Copyright (c) 2026 MindMesh Academy. All rights reserved. This content is proprietary and may not be reproduced or distributed without permission.

8.2. High-Frequency Exam Topics Quick Reference

Service Selection Decision Trees

When to use Bedrock vs. SageMaker:
  • Invoke a managed FM via API → Bedrock
  • Fine-tune a model with your own data → Bedrock (for supported models) or SageMaker (full control)
  • Deploy your own custom model → SageMaker endpoint
  • Need custom training loop → SageMaker Training Job
When to use Bedrock Knowledge Bases vs. custom OpenSearch:
  • Standard RAG, managed pipeline, no custom preprocessing → Bedrock Knowledge Bases
  • Real-time document availability (< 1 minute from upload to query) → Custom OpenSearch
  • Complex metadata filtering with custom schema → Custom OpenSearch
  • Need full control over chunking algorithm → Custom OpenSearch
When to use Bedrock Agents vs. Strands Agents vs. Step Functions:
  • Multi-step task with dynamic tool selection, managed service → Bedrock Agents
  • Code-first agent with full programmatic control → Strands Agents
  • Deterministic workflow with many AWS service integrations → Step Functions
  • Long-running (hours+) process with durable execution → Step Functions Standard Workflow
When to fine-tune vs. use RAG:
  • Need the model to know domain facts → RAG
  • Need consistent output format or style → Fine-tuning
  • Need to reduce token cost by shortening prompts → Fine-tuning
  • Data changes frequently → RAG (re-index) not fine-tuning (retrain)

Critical Number Pairs

TopicValue AValue B
API Gateway max timeout29 secondsLambda max timeout: 15 minutes
Provisioned throughput break-even~60–70% utilizationBelow this: on-demand cheaper
HNSW default ef_search512 (high recall)Lower value = faster, worse recall
Bedrock Knowledge Bases syncMinutes–hours delayCustom OpenSearch: near real-time
Transfer question target (Associate)15–25% of questionsFoundation: 5–10%; Expert: 25–30%
Semantic cache similarity threshold0.92 typicalBelow this → too many false positives

The Safety Control Stack

Layer 1 (Earliest): Input sanitization — Comprehend PII detection + custom regex
Layer 2: Bedrock Guardrails (input evaluation) — topic denial, word filters, PII
Layer 3: FM inference — model's own RLHF safety training
Layer 4: Bedrock Guardrails (output evaluation) — content filters, grounding check
Layer 5: Lambda output validation — schema validation, semantic grounding check
Layer 6: Human review — for high-stakes irreversible decisions (waitForTaskToken)
No single layer is sufficient. Defense-in-depth requires all layers.

The Monitoring Matrix

What You're MonitoringServiceSpecific Metric
Who changed Guardrails configCloudTrailUpdateGuardrail event
What prompt was sentBedrock Model Invocation LogsRequest body
FM latencyCloudWatch (native Bedrock)InvocationLatency
Application E2E latencyX-Ray + custom CloudWatch metricCustom TotalLatencyMs
Response qualityCustom CloudWatch metricGroundingScore, FaithfulnessScore
Cost by teamCost Explorer + resource tagsFiltered by team/project tag
Knowledge Base freshnessCustom Lambda + CloudWatchDaysSinceLastSync

MCP at a Glance

  • What: Open protocol (not AWS-proprietary) for standardized AI tool connectivity
  • Who made it: Anthropic
  • Who uses it: Bedrock Agents, Strands Agents, Claude Desktop, and any MCP client
  • Servers: Stateless Lambda (lightweight) or stateful ECS (complex tools)
  • Key benefit: N clients + M servers = N+M integrations (not N×M)
  • Exam signal: "Standardized tool integration across frameworks" → MCP
Alvin Varughese
Written byAlvin Varughese
Founder15 professional certifications