ExamFinch.com My Study

Cheat sheet

Databricks GenAI Engineer Associate Cheat Sheet

Practice this exam

Design Applications

  • 14% of exam
  • Prompt design Task selection Chain components Business mapping Solution decomposition

Data Preparation

  • 14% of exam
  • Chunking Embeddings Retrieval quality Document extraction Delta Lake Unity Catalog

Application Development

  • 30% of exam
  • RAG chains Agents Tool calling LangChain LangGraph Guardrails

Assembling + Deploying

  • 22% of exam
  • MLflow Model Serving Vector Search Pyfunc CI/CD Foundation Model APIs

Governance

  • 8% of exam
  • Masking Guardrails Licensing Unity Catalog AI Gateway Safe input

Evaluation + Monitoring

  • 12% of exam
  • Offline eval Online monitoring LLM judge Inference tables RAGAS Cost control

Quick Facts

  • Exam Databricks GenAI
  • Credential GenAI Engineer Associate
  • Time 90 min
  • Pass 70% (32/45)
  • Questions 45 scored
  • Fee $200
  • Blueprint Mar 18 2026

Design Decisions DE

  • Problem decomposition Split to subtasks
  • Task selection Pick model type
  • Chain design Sequence steps
  • Business mapping Goal to behavior
  • Architecture choice Pick pattern
  • Cost/latency Tradeoff balance

Prompt Engineering DE

  • Zero-shot No examples
  • Few-shot Example-driven
  • Chain-of-thought Step reasoning
  • System prompt Set behavior
  • Role prompt Persona
  • Template Reusable scaffold
  • Structured output JSON/schema

Semantic vs Keyword Search DA

Semantic

  • Vector similarity
  • Meaning match
  • Needs embeddings

Keyword

  • Term match
  • BM25/SQL
  • No embeddings
  • Meaning vs terms

Chunking Strategy Picker DA

  • Uniform docs → Fixed-size ( N tokens )
  • Sentences matter → Sentence ( Split by . )
  • Topic shifts → Semantic ( Meaning bounds )
  • Nested structure → Recursive ( Hierarchy )
  • Short docs → Whole doc ( No split )
  • Need context → Overlap ( Share text )
  • Retrieve precision → Parent-child ( Child index )

Chunking Strategies DA

  • Fixed-size N tokens each
  • Sentence Split by sentence
  • Semantic Topic boundaries
  • Recursive Hierarchical split
  • Overlap Adjacent share text
  • Parent-child Index child; retrieve parent
  • Sliding window Fixed stride

Data Preparation Pipeline DA

  • Extraction Parse documents
  • Filtering Drop noise
  • Cleaning Normalize text
  • Delta Lake Versioned tables
  • Unity Catalog Data governance
  • Indexing Build vector index

RAG Pipeline AP

  • Ingest | Chunk | Embed | Index | Retrieve | Rerank | Generate
  • Ingest: parse Chunk: split Embed: vector Index: store Retrieve: fetch Rerank: reorder Generate: answer

RAG vs Fine-tuning AP

RAG

  • Inject knowledge
  • No training
  • Updates easy

Fine-tuning

  • Bake behavior
  • Needs training
  • Updates costly
  • Knowledge vs behavior

RAG vs Fine-tune vs Prompt AP

  • Need latest info → RAG ( Inject knowledge )
  • Need private data → RAG ( Vector Search )
  • Need new skills → Fine-tune ( Bake behavior )
  • Need behavior shift → Fine-tune ( LoRA/QLoRA )
  • Need format only → Prompt ( No training )
  • Quick one-shot task → Prompt ( Zero-shot )
  • Multi-step task → Agent ( Tool calling )
  • Need external tools → Agent ( MCP server )

RAG Components AP

  • Vector store Semantic index
  • Embedding Vector representation
  • Chunking Split documents
  • Retrieval Fetch relevant chunks
  • Re-ranking Reorder top results
  • Context window Max input tokens
  • Grounding Cite source facts
  • Augmentation Inject context

LLM Params AP

  • Temp=creativity | Top-p=nucleus | Top-k=pool
  • Temp: random Top-p: nucleus Top-k: candidates

LoRA vs Full Fine-tune AP

LoRA

  • Low-rank adapters
  • Few params
  • Cheap train

Full

  • All weights
  • Costly train
  • Max control
  • Adapters vs all weights

LLM Concepts AP

  • Token Subword unit
  • Context window Max input tokens
  • Temperature Randomness control
  • Top-p Nucleus sampling
  • Top-k Top candidates
  • Hallucination Unfounded output
  • Sampling Probabilistic decode

Agent Bricks vs Framework AP

Agent Bricks

  • Managed
  • Low code
  • Databricks-hosted

Framework

  • Custom code
  • LangChain
  • Full control
  • Managed vs custom

Fine-tuning Methods AP

  • Full fine-tune Update all weights
  • LoRA Low-rank adapters
  • QLoRA Quantized LoRA
  • Instruction-tune Follow directions
  • PEFT Partial tuning
  • RLHF Human feedback
  • DPO Preference optimize

Agent Patterns AP

  • ReAct Reason + act
  • Tool calling Invoke functions
  • Planning Decompose tasks
  • Reflection Self-critique
  • Multi-agent Coordinate roles
  • MCP server Tool protocol
  • Memory Persist context

Deploy Gates DE

  • Package | Register | Serve | Monitor
  • Package: pyfunc Register: MLflow Serve: endpoint Monitor: drift

Playground vs Model Serving DE

Playground

  • Interactive test
  • Prompt iterate
  • No endpoint

Model Serving

  • Deploy endpoint
  • Production API
  • Scale traffic
  • Test vs deploy

Deployment Picker DE

  • Track experiment → MLflow ( Log params )
  • Register model → MLflow register ( Version )
  • Real-time API → Model Serving ( Endpoint )
  • Async scoring → Batch inference ( No endpoint )
  • Semantic search → Vector Search ( Index )
  • Usage metering → AI Gateway ( Track )
  • Managed agents → Agent Bricks ( Low code )

Databricks Tools DE

  • Vector Search Semantic index
  • AI Playground Test prompts
  • Foundation Model APIs Hosted base models
  • MLflow Track experiments
  • Unity Catalog Governance hub
  • Model Serving Deploy endpoints
  • AI Gateway Usage tracking
  • Agent Bricks Managed agents

MLflow vs Unity Catalog DE

MLflow

  • Track experiments
  • Log params
  • Version models

Unity Catalog

  • Govern data
  • Access control
  • Lineage
  • Track vs govern

Deployment Patterns DE

  • Pyfunc Python packaging
  • MLflow register Version models
  • Model Serving Real-time endpoint
  • Batch inference Async scoring
  • CI/CD Automate release
  • Persistent state Save context
  • Streaming Real-time input

Governance Stack GO

  • UC | Masking | Guardrails | AI Gateway
  • UC: govern Masking: PII Guardrails: filter Gateway: track

Governance Controls GO

  • Masking Hide PII
  • Guardrails Input/output filters
  • Licensing Model terms
  • Unity Catalog Central governance
  • AI Gateway Track usage
  • PII detection Find sensitive
  • Audit logging Track actions

Eval Dimensions EV

  • Faithfulness | Relevance | Context | Answer
  • Faithfulness: grounded Relevance: matched Context: recall Answer: quality

Offline vs Online Eval EV

Offline

  • Pre-deploy
  • Ground truth
  • RAGAS/BLEU

Online

  • Production
  • Live metrics
  • Drift detect
  • Test vs monitor

Evaluation Metrics EV

  • BLEU N-gram overlap
  • ROUGE Recall overlap
  • RAGAS RAG eval suite
  • Human eval Gold standard
  • LLM judge Auto evaluate
  • Faithfulness Source-grounded
  • Groundedness No hallucination

Common Traps

RAG vs Fine-tune vs Prompt

  • RAG adds knowledge ≠ Fine-tune shifts behavior

Temperature vs Top-p

  • Temp scales randomness ≠ Top-p truncates nucleus

Vector vs Keyword Search

  • Semantic matches meaning ≠ Keyword matches terms

Offline vs Online Eval

  • Offline needs ground truth ≠ Online detects drift

MLflow vs Model Serving

  • MLflow tracks experiments ≠ Serving deploys endpoints

Unity Catalog vs Delta Lake

  • UC governs access ≠ Delta stores tables

Agent Bricks vs Framework

  • Bricks is managed ≠ Framework is custom code

Last Minute

  • 1. 14/14/30/22/8/12
  • 2. 45 Q / 90 min / $200
  • 3. Pass: 70% (32/45)
  • 4. RAG = retrieve + augment
  • 5. LoRA = adapters; QLoRA = quantized
  • 6. Vector Search = semantic index
  • 7. MLflow = track; Serving = deploy
  • 8. Unity Catalog = governance
  • 9. AI Gateway = usage tracking
  • 10. Agent Bricks = managed agents
  • 11. MCP = tool protocol
  • 12. March 18 2026 = blueprint update
  • 13. 14-day retake; full fee

Databricks Generative AI Engineer Associate

  • Practice Questions 250 questions Study Guide 18 topics Cheat Sheet 84 facts Flashcards 50 cards Shorts 1 short Free CE Podcast