Databricks Certified Generative AI Engineer Associate Bundle

Not the strongest safeguard choice for this specific question. Select chunk granularity by measured retrieval results, not solely by minimizing index records. 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 — A legal RAG service finds semantically similar contracts from the wrong customer workspace. — is testing Hybrid sparse and dense retrieval with filters. 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. Separate missing knowledge from bad generation during incident triage and refresh upstream data responsibly. 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 legal RAG service finds semantically similar contracts from the wrong customer workspace. — is testing Hybrid sparse and dense retrieval with filters. 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. Route documents by actual format and flag low-confidence extraction rather than silently indexing blank text. This action primarily relates to Format-specific document extraction and OCR needs: Extract text with a parser suited to source format; image-only scans require OCR rather than HTML or plain-text parsing. However, the described case — A legal RAG service finds semantically similar contracts from the wrong customer workspace. — is testing Hybrid sparse and dense retrieval with filters. 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 filter decisions, action permissions, identity propagation and resulting audit events. 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 financial invoice extractor masks every number, including legitimate tax amounts and invoice totals. — is testing Contextual masking versus destructive data removal. 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 content provenance, licensing terms, rights reservations and intended distribution. This action primarily relates to Training and retrieval corpus license rights: Public accessibility does not automatically authorize copying, embedding or using content in commercial RAG services. However, the described case — A financial invoice extractor masks every number, including legitimate tax amounts and invoice totals. — is testing Contextual masking versus destructive data removal. 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 source origin, prompt hierarchy, tool permissions and trace evidence of instruction-following attempts. 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 financial invoice extractor masks every number, including legitimate tax amounts and invoice totals. — is testing Contextual masking versus destructive data removal. 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 runnable input/output schemas, prompt variables and invocation traces around the failing stage. This action primarily relates to LangChain runnable composition and invocation: Composable runnable chains pass typed values between retrieval, prompt and model stages; each binding must preserve expected input keys. However, the described case — A long regulation section exceeds an encoder's limit and the final exception is never embedded. — is testing Embedding context window and chunk token distribution. 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 training/licensing terms, model-card task benchmarks, input limits and restrictions. 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 long regulation section exceeds an encoder's limit and the final exception is never embedded. — is testing Embedding context window and chunk token distribution. 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 agent routing to Genie, space permissions, metric definitions and tool-returned values. This action primarily relates to Multi-agent Genie Space tool routing and governed answers: Genie Spaces can provide governed natural-language access to structured business metrics; an agent should choose authorized Genie tools over guessing SQL facts. However, the described case — A long regulation section exceeds an encoder's limit and the final exception is never embedded. — is testing Embedding context window and chunk token distribution. 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 task-appropriate quality metrics, inference cost, p95 latency and error segments. 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 finance team cannot attribute escalating LLM spend to teams because requests have no workload identity. — is testing AI Gateway rate limits, usage tables and inference telemetry. 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 token volumes, QPS, endpoint pricing, cache hit rate and user/workload attribution. 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 finance team cannot attribute escalating LLM spend to teams because requests have no workload identity. — is testing AI Gateway rate limits, usage tables and inference telemetry. 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 inference table availability, payload schemas, trace IDs and user-feedback mapping. 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 finance team cannot attribute escalating LLM spend to teams because requests have no workload identity. — is testing AI Gateway rate limits, usage tables and inference telemetry. 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. Require evidence-to-claim matching and refuse or correct answers unsupported by retrieved clauses. This action primarily relates to Hallucinated facts and unsupported citations: Fluent responses can invent facts and citations; faithfulness must be checked against supplied evidence, not writing style. However, the described case — A search result includes fake 'system message' text requesting the assistant reveal private SQL results. — is testing Prompt-injection defenses for retrieved context. 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. Split by task-relevant sections and filter top passages before prompt assembly. 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 — A search result includes fake 'system message' text requesting the assistant reveal private SQL results. — is testing Prompt-injection defenses for retrieved context. 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. Extract model/country fields and apply them as verified metadata filters to approved retrieval. 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 — A search result includes fake 'system message' text requesting the assistant reveal private SQL results. — is testing Prompt-injection defenses for retrieved context. 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. Execute a small sample query then validate throughput, cost, failed rows and result parsing. This action primarily relates to SQL ai_query for governed batch inference: `ai_query()` invokes an available serving endpoint from SQL; suitability depends on supported runtimes, endpoint and workload. However, the described case — An agent must search an external research API requiring a secret, while internal company data uses managed connectors. — is testing Managed versus external versus custom MCP server integration. 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. Exercise failed tests and confirm release is blocked, then deploy and verify a passing version. This action primarily relates to CI/CD pipelines for retrieval and agent components: Production promotions should test source index, prompt, model packaging and tool behavior independently before release. However, the described case — An agent must search an external research API requiring a secret, while internal company data uses managed connectors. — is testing Managed versus external versus custom MCP server integration. 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. Switch alias to a tested version and verify the active agent follows it and can roll back. This action primarily relates to MLflow Prompt Registry version aliases and promotion: Prompt Registry tracks immutable prompt versions with mutable aliases for staging and production, enabling change control and rollback. However, the described case — An agent must search an external research API requiring a secret, while internal company data uses managed connectors. — is testing Managed versus external versus custom MCP server integration. 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. A/B test chunk segmentation on frozen questions and verify evidence sufficiency and prompt-budget compliance. 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 — A code assistant looks fast in demos but has low pass rate on the organization's test suite. — is testing Model evaluation with paired benchmarks. 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. Audit answer-supportedness using labeled trace examples and a human review of fabricated citations. This action primarily relates to Hallucinated facts and unsupported citations: Fluent responses can invent facts and citations; faithfulness must be checked against supplied evidence, not writing style. However, the described case — A code assistant looks fast in demos but has low pass rate on the organization's test suite. — is testing Model evaluation with paired benchmarks. 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. Run repeatable attack cases and verify restricted content and destructive operations remain inaccessible. 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 code assistant looks fast in demos but has low pass rate on the organization's test suite. — is testing Model evaluation with paired benchmarks. 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 diagnose choice for this specific question. Inspect UC model names, signatures, version metadata, lineage and relevant ACLs. This action primarily relates to Unity Catalog registered model version and privileges: MLflow-logged models can be registered in Unity Catalog, with governed names, permissions and traceable version lineage. However, the described case — A team has a clean chunk table but no searchable index for semantic passage retrieval. — is testing Databricks Vector Search index from governed Delta data. 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 capacity caps, sync behavior, qps, p95 latency and expected update cost. This action primarily relates to Standard versus storage-optimized Vector Search index: Index choice trades capacity, update speed, latency and storage economics; availability and feature support may vary by cloud/region. However, the described case — A team has a clean chunk table but no searchable index for semantic passage retrieval. — is testing Databricks Vector Search index from governed Delta data. 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 logged model artifacts, environment requirements, signature and source index identifiers. This action primarily relates to RAG production bundle metadata and dependencies: A deployable RAG application needs tracked model code, retriever config, embedding model, dependency versions, signature and example input. However, the described case — A team has a clean chunk table but no searchable index for semantic passage retrieval. — is testing Databricks Vector Search index from governed Delta data. 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 verify choice for this specific question. Test representative queries needing missing records and confirm either accurate retrieval or abstention. 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 compliance RAG app splits a numbered contract clause so exclusions are separated from the obligation. — is testing Semantic boundaries versus fixed-window chunks. 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. Compare precision at k before and after cleaning while checking no required policy sentences were removed. 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 compliance RAG app splits a numbered contract clause so exclusions are separated from the obligation. — is testing Semantic boundaries versus fixed-window chunks. 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. Compare fixed evaluation queries on baseline and candidate retrieval with confidence in differences. 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 — A compliance RAG app splits a numbered contract clause so exclusions are separated from the obligation. — is testing Semantic boundaries versus fixed-window chunks. 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. Monitor tail latency, timeout rate and affected user experience under representative load. This action primarily relates to Production performance KPIs and incident thresholds: Monitoring should include answer correctness, retrieval coverage, safety, latency, drift and per-user harm indicators, not just availability. 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 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. Define scoring anchors, calibrate experts on disputed samples and use aligned feedback as reliable evaluation labels. 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 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. Limit retrieved context by relevance and compare answer faithfulness before switching to a smaller endpoint. 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 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 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. Sample indexed chunks against a rights manifest and confirm prohibited sources are excluded. This action primarily relates to Training and retrieval corpus license rights: Public accessibility does not automatically authorize copying, embedding or using content in commercial RAG services. However, the described case — A retrieved internal wiki page embeds a fake system instruction to grant an attacker access to all support tickets. — is testing Input guardrails against prompt-injected source documents. 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. Compare usefulness and privacy leakage metrics on held-out documents before and after selective masking. This action primarily relates to Contextual masking versus destructive data removal: Masking must preserve information needed for the task, such as non-sensitive dates or amounts, and cannot replace access control. However, the described case — A retrieved internal wiki page embeds a fake system instruction to grant an attacker access to all support tickets. — is testing Input guardrails against prompt-injected source documents. 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. Query for known synthetic sensitive strings and confirm no original identifiers appear in chunks or answers. This action primarily relates to Sensitive-field masking before embedding: Masking or tokenization can remove unnecessary PII from chunks before embedding and external model calls while retaining useful meaning. However, the described case — A retrieved internal wiki page embeds a fake system instruction to grant an attacker access to all support tickets. — is testing Input guardrails against prompt-injected source documents. 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.