Databricks Certified Generative AI Engineer Associate Bundle

Not the strongest implement choice for this specific question. Connect the authorized live shipment-tracking record keyed by order ID rather than guessing arrival from policy. This action primarily relates to Authoritative source coverage for factual answers: A RAG model cannot answer accurately if the required authoritative record is missing or stale in its index. However, the described case — A troubleshooting guide's symptom and resolution are in separate sections when cut every 400 characters. — is testing Semantic boundaries versus fixed-window chunks. It does not directly establish the implement outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest implement choice for this specific question. Combine keyword matching and vector similarity with model/tenant filters and calibrated score fusion. This action primarily relates to Hybrid sparse and dense retrieval with filters: Hybrid search combines lexical exact-match and semantic similarity; metadata filtering narrows authorized relevant content. However, the described case — A troubleshooting guide's symptom and resolution are in separate sections when cut every 400 characters. — is testing Semantic boundaries versus fixed-window chunks. It does not directly establish the implement outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest implement choice for this specific question. Remove repeated footer noise while preserving meaningful classification metadata separately. This action primarily relates to Boilerplate and navigation filtering in source corpora: Duplicated headers, disclaimers and navigation menus contaminate embeddings and cause irrelevant hits. However, the described case — A troubleshooting guide's symptom and resolution are in separate sections when cut every 400 characters. — is testing Semantic boundaries versus fixed-window chunks. It does not directly establish the implement outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest verify choice for this specific question. Test harmful queries and verify contaminated passages are blocked without discarding legitimate safety instructions. This action primarily relates to Toxic, inaccurate and adversarial corpus cleaning: Unreliable source text can teach unsafe behavior through retrieval; quarantine and source review matter before embeddings. However, the described case — A startup scrapes a paid technical manual site into its product RAG index despite restrictive subscription terms. — is testing Training and retrieval corpus license rights. It does not directly establish the verify outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest verify choice for this specific question. Test malicious requests with valid JSON tool calls and confirm the tool rejects unauthorized actions. This action primarily relates to Prompt safety filtering and tool allowlists: Content filters and action allowlists are complementary; a moderation score is not a substitute for authorization of external effects. However, the described case — A startup scrapes a paid technical manual site into its product RAG index despite restrictive subscription terms. — is testing Training and retrieval corpus license rights. It does not directly establish the verify outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest verify choice for this specific question. Inject the hostile PDF and verify no secret leaves the backend and no unauthorized tool is invoked. This action primarily relates to Input guardrails against prompt-injected source documents: A document that says 'ignore your rules' is untrusted data; a robust agent must enforce instruction and tool boundaries independently. However, the described case — A startup scrapes a paid technical manual site into its product RAG index despite restrictive subscription terms. — is testing Training and retrieval corpus license rights. It does not directly establish the verify outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest implement choice for this specific question. Build a compatible new index and re-embed the corpus, then test cutover against representative queries. This action primarily relates to Embedding model swap and reindex compatibility: Changed embedding dimensions or model semantics typically require re-embedding and index consistency before comparing search quality. However, the described case — A medical summarization product considers a model evaluated only on short English news articles. — is testing Model cards and task-specific limitations. It does not directly establish the implement outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest implement choice for this specific question. Reject unauthorized tool requests through server-side permissions even if the model produces a valid tool call. This action primarily relates to Unsafe model output and jailbreak response diagnosis: User-provided instructions may attempt to bypass agent policies or cause data leakage; classification and tool boundaries need separate tests. However, the described case — A medical summarization product considers a model evaluated only on short English news articles. — is testing Model cards and task-specific limitations. It does not directly establish the implement outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest implement choice for this specific question. Pin the retrieval index version and trace reference set in experiments before comparing runs. This action primarily relates to Experiment tracking and version reproducibility: MLflow experiments should retain prompt, model, dataset, parameters and evaluation outputs to support a defensible comparison. However, the described case — A medical summarization product considers a model evaluated only on short English news articles. — is testing Model cards and task-specific limitations. It does not directly establish the implement outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest diagnose choice for this specific question. Inspect the most frequent n-grams, extracted layout artifacts and top retrieved false positives. This action primarily relates to Boilerplate and navigation filtering in source corpora: Duplicated headers, disclaimers and navigation menus contaminate embeddings and cause irrelevant hits. However, the described case — A parts catalog stores component numbers as strings while retrieval loses manufacturer and model columns. — is testing Table-aware chunking and metadata-rich retrieval. It does not directly establish the diagnose outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest diagnose choice for this specific question. Inspect heading structure, sentence breaks, table boundaries and parent document identifiers. This action primarily relates to Semantic boundaries versus fixed-window chunks: Headings, paragraphs and tables can require structure-aware splitting rather than arbitrary token windows. However, the described case — A parts catalog stores component numbers as strings while retrieval loses manufacturer and model columns. — is testing Table-aware chunking and metadata-rich retrieval. It does not directly establish the diagnose outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest diagnose choice for this specific question. Inspect lexical token overlap, dense distance, metadata predicates and index access control. This action primarily relates to Hybrid sparse and dense retrieval with filters: Hybrid search combines lexical exact-match and semantic similarity; metadata filtering narrows authorized relevant content. However, the described case — A parts catalog stores component numbers as strings while retrieval loses manufacturer and model columns. — is testing Table-aware chunking and metadata-rich retrieval. It does not directly establish the diagnose outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest safeguard choice for this specific question. Do not assume an instruction to 'respond in JSON' replaces actual schema validation and error handling. This action primarily relates to Structured JSON schema prompt and format compliance: A model can produce plausible prose rather than machine-readable JSON unless the output contract and validation are explicit. However, the described case — A travel agent books a flight before checking ticket rules and traveler approval. — is testing Tool ordering and error isolation in multi-stage reasoning. It does not directly establish the safeguard outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest safeguard choice for this specific question. Revisit cost/latency budgets whenever context window or retrieval size changes significantly. This action primarily relates to Latency, cost and retrieval targets as design requirements: A valid pipeline design has measurable quality, latency, token and throughput constraints before model selection. However, the described case — A travel agent books a flight before checking ticket rules and traveler approval. — is testing Tool ordering and error isolation in multi-stage reasoning. It does not directly establish the safeguard outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest safeguard choice for this specific question. Treat absence of relevant retrieved evidence as an abstention condition, not a reason to invent missing facts. This action primarily relates to Retriever-generator chain component boundaries: A basic RAG chain separates user input, query transformation, retrieval, prompt assembly, model generation and output validation. However, the described case — A travel agent books a flight before checking ticket rules and traveler approval. — is testing Tool ordering and error isolation in multi-stage reasoning. It does not directly establish the safeguard outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest safeguard choice for this specific question. Keep monitoring schemas and retention governance versioned across model deployment changes. This action primarily relates to Inference tables and Agent Monitoring feedback loop: Inference tables and agent monitoring capture production request/response signals and traces for quality investigations. However, the described case — A deployed claims assistant has 99.99% uptime but increasing incorrect eligibility advice. — is testing Production performance KPIs and incident thresholds. It does not directly establish the safeguard outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest safeguard choice for this specific question. Use usage monitoring and budgets to detect regressions when prompts, indexes or models change. This action primarily relates to Databricks usage and token cost controls: Reduce LLM spend through token budgets, caching, smaller appropriate models and AI Gateway quotas while preserving acceptance quality. However, the described case — A deployed claims assistant has 99.99% uptime but increasing incorrect eligibility advice. — is testing Production performance KPIs and incident thresholds. It does not directly establish the safeguard outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest safeguard choice for this specific question. Revisit the choice as workload and evaluation data change instead of permanently trusting benchmark ranking. This action primarily relates to Model selection from quantitative task metrics: Select candidate LLMs by measured task success, latency, safety and token cost, not parameter count or leaderboard rank. However, the described case — A deployed claims assistant has 99.99% uptime but increasing incorrect eligibility advice. — is testing Production performance KPIs and incident thresholds. It does not directly establish the safeguard outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest diagnose choice for this specific question. Inspect parsed intent, extracted keys, authorization check and actual query filter predicates. This action primarily relates to Query-field driven prompt and retrieval filters: User intent and structured fields such as account_id should drive authorized SQL lookups or retrieval filters, not be ignored in free text. However, the described case — An engineer changes the source chunking but keeps old stored embeddings and assumes retrieval reflects the new boundaries. — is testing Embedding model swap and reindex compatibility. It does not directly establish the diagnose outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest diagnose choice for this specific question. Inspect trace context passages, token distribution, coverage of necessary conditions and retrieval rank. This action primarily relates to Chunk quality evaluation and boundary splitting: Retrieval failure can arise from overly small chunks that omit needed context or overly large chunks that dilute relevance. However, the described case — An engineer changes the source chunking but keeps old stored embeddings and assumes retrieval reflects the new boundaries. — is testing Embedding model swap and reindex compatibility. It does not directly establish the diagnose outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest diagnose choice for this specific question. Inspect vector count, dimension, encoder throughput, per-query latency and measured quality curves. This action primarily relates to Embedding dimensions latency and index storage: Embedding width affects index storage and computation, and larger dimensions do not automatically improve task relevance. However, the described case — An engineer changes the source chunking but keeps old stored embeddings and assumes retrieval reflects the new boundaries. — is testing Embedding model swap and reindex compatibility. It does not directly establish the diagnose outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest implement choice for this specific question. Parse and chunk documents, write keyed chunk rows with provenance to a governed Delta table, then index them. This action primarily relates to Delta and Unity Catalog pipeline for chunk tables: A governed retrieval corpus stores chunk text, IDs, source lineage and metadata in managed Delta/Unity Catalog tables before indexing. However, the described case — PDF extraction repeats a footer classification notice inside every employee policy chunk. — is testing Boilerplate and navigation filtering in source corpora. It does not directly establish the implement outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest implement choice for this specific question. Turn each relevant table row into a header-aware text/metadata record with original page citation. This action primarily relates to Table-aware chunking and metadata-rich retrieval: Tabular rows need headers, units and column semantics preserved when transformed into retrieval documents. However, the described case — PDF extraction repeats a footer classification notice inside every employee policy chunk. — is testing Boilerplate and navigation filtering in source corpora. It does not directly establish the implement outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest implement choice for this specific question. Choose coherent chunks large enough to keep cause and remedy together without exceeding embedding limits. This action primarily relates to Chunk size and overlap tradeoffs: Chunk size determines the number of vectors and coherence; overlap reduces boundary loss but increases index size and cost. However, the described case — PDF extraction repeats a footer classification notice inside every employee policy chunk. — is testing Boilerplate and navigation filtering in source corpora. It does not directly establish the implement outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest safeguard choice for this specific question. Version preprocessing rules and sample exceptions so cleansing never strips legal requirements. This action primarily relates to Boilerplate and navigation filtering in source corpora: Duplicated headers, disclaimers and navigation menus contaminate embeddings and cause irrelevant hits. However, the described case — An employee policy question needs a short deductible clause plus the adjacent exception paragraph. — is testing Parent-child retrieval and hierarchical structure. It does not directly establish the safeguard outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest safeguard choice for this specific question. Use a frozen relevance dataset to prevent tuning to a single cherry-picked query. This action primarily relates to Retrieval recall precision and ranking diagnostics: Measure hit recall, precision, MRR or nDCG on labeled query-to-relevant-chunk pairs before tuning retrieval. However, the described case — An employee policy question needs a short deductible clause plus the adjacent exception paragraph. — is testing Parent-child retrieval and hierarchical structure. It does not directly establish the safeguard outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest safeguard choice for this specific question. Retain source offsets and section IDs so citations remain traceable after rechunking. This action primarily relates to Semantic boundaries versus fixed-window chunks: Headings, paragraphs and tables can require structure-aware splitting rather than arbitrary token windows. However, the described case — An employee policy question needs a short deductible clause plus the adjacent exception paragraph. — is testing Parent-child retrieval and hierarchical structure. It does not directly establish the safeguard outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest implement choice for this specific question. Reject unauthorized tool requests through server-side permissions even if the model produces a valid tool call. This action primarily relates to Unsafe model output and jailbreak response diagnosis: User-provided instructions may attempt to bypass agent policies or cause data leakage; classification and tool boundaries need separate tests. However, the described case — A helpdesk bot sends full payment card numbers to an external model for a simple FAQ answer. — is testing PII masking and output moderation as complementary guardrails. It does not directly establish the implement outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest implement choice for this specific question. Select a candidate with measured language coverage and document residual risk on target-language samples. This action primarily relates to Model cards and task-specific limitations: A model card records intended uses, supported language/context, safety limitations and evaluation scope relevant to selection. However, the described case — A helpdesk bot sends full payment card numbers to an external model for a simple FAQ answer. — is testing PII masking and output moderation as complementary guardrails. It does not directly establish the implement outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest implement choice for this specific question. Enable supported MLflow GenAI tracing around each model, retriever and tool operation with secret redaction. This action primarily relates to MLflow tracing in an Agent Framework workflow: MLflow tracing records agent steps, tool calls and latency; integration must retain child spans and inputs without leaking secrets. However, the described case — A helpdesk bot sends full payment card numbers to an external model for a simple FAQ answer. — is testing PII masking and output moderation as complementary guardrails. It does not directly establish the implement outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest safeguard choice for this specific question. Revisit the choice as workload and evaluation data change instead of permanently trusting benchmark ranking. This action primarily relates to Model selection from quantitative task metrics: Select candidate LLMs by measured task success, latency, safety and token cost, not parameter count or leaderboard rank. However, the described case — A production team logs raw access tokens and complete customer chats when adding observability. — is testing Inference logging and production trace privacy. It does not directly establish the safeguard outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest safeguard choice for this specific question. Never label judge outputs as factual correctness when the required reference evidence is absent. This action primarily relates to Ground-truth requirement for correctness versus reference-free judges: A correctness comparison often needs an expected answer; other judges such as format or safety can operate without a reference. However, the described case — A production team logs raw access tokens and complete customer chats when adding observability. — is testing Inference logging and production trace privacy. It does not directly establish the safeguard outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest safeguard choice for this specific question. Do not hide expert disagreement by excluding difficult cases or averaging away severe failures. This action primarily relates to Human SME feedback rubric and reviewer calibration: Domain experts should use a shared rubric, calibrate disagreements and maintain adjudicated examples to improve model evaluation. However, the described case — A production team logs raw access tokens and complete customer chats when adding observability. — is testing Inference logging and production trace privacy. It does not directly establish the safeguard outcome or constraint that the question requires; it may still be useful in a different stage or incident.