Databricks Certified Generative AI Engineer Associate Bundle

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 team measures 'answer correctness' with a golden-answer comparator but its evaluation data includes only user questions. — is testing Ground-truth requirement for correctness versus reference-free judges. 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 logging configuration, sampling policy, trace privacy, missing identifiers and audit destinations. This action primarily relates to Inference logging and production trace privacy: Inference logs and tracing permit diagnosis of real issues but must be sampled, retained and redacted safely. However, the described case — A team measures 'answer correctness' with a golden-answer comparator but its evaluation data includes only user questions. — is testing Ground-truth requirement for correctness versus reference-free judges. 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 team measures 'answer correctness' with a golden-answer comparator but its evaluation data includes only user questions. — is testing Ground-truth requirement for correctness versus reference-free judges. 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. 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 RAG benchmark reports fluent final answers but no evidence of whether the right passage was retrieved. — is testing Retrieval recall precision and ranking diagnostics. 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 clause and heading boundaries with a token-aware fallback to preserve the rule and exception together. 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 RAG benchmark reports fluent final answers but no evidence of whether the right passage was retrieved. — is testing Retrieval recall precision and ranking diagnostics. 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. Strip template boilerplate, repeated navigation and low-information text before embedding. 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 RAG benchmark reports fluent final answers but no evidence of whether the right passage was retrieved. — is testing Retrieval recall precision and ranking diagnostics. 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. Limit parent expansion to an appropriate token budget to avoid irrelevant context dilution. This action primarily relates to Parent-child retrieval and hierarchical structure: Parent-child retrieval indexes targeted sections but expands to their broader parent context for generation. However, the described case — A support search returns five unrelated policy pages while the correct refund clause is at rank 20. — is testing Retrieval recall precision and ranking diagnostics. 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. 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 — A support search returns five unrelated policy pages while the correct refund clause is at rank 20. — is testing Retrieval recall precision and ranking diagnostics. 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. Use `ai_query()` against a supported endpoint in a controlled batch-inference query with result checks. 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 — A product catalog has 85 million vectors with stringent p95 search latency and frequent incremental updates. — is testing Standard versus storage-optimized Vector Search index. 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. Resolve the authorized production alias at runtime using a controlled refresh strategy. 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 — A product catalog has 85 million vectors with stringent p95 search latency and frequent incremental updates. — is testing Standard versus storage-optimized Vector Search index. 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. Create a compatible AI Search/Vector Search index over the approved source and configured embedding columns. This action primarily relates to Databricks Vector Search index from governed Delta data: A vector index serves embeddings of chunked records maintained in a Unity Catalog governed Delta source table. However, the described case — A product catalog has 85 million vectors with stringent p95 search latency and frequent incremental updates. — is testing Standard versus storage-optimized Vector Search index. 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. Index child sections with links to parent passages and expand context after child retrieval. This action primarily relates to Parent-child retrieval and hierarchical structure: Parent-child retrieval indexes targeted sections but expands to their broader parent context for generation. However, the described case — A RAG benchmark reports fluent final answers but no evidence of whether the right passage was retrieved. — is testing Retrieval recall precision and ranking diagnostics. 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 assume embedding similarity alone is a security boundary or reliable exact identifier lookup. 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 RAG benchmark reports fluent final answers but no evidence of whether the right passage was retrieved. — is testing Retrieval recall precision and ranking diagnostics. 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 verify choice for this specific question. Simulate peak traffic and controlled rollback while monitoring end-to-end user outcomes. This action primarily relates to Endpoint scale concurrency and operational rollout: Serving latency and reliability depend on provisioned capacity, request concurrency, quotas and controlled rollout. However, the described case — A new model signature expects messages array but the existing app sends only a prompt string. — is testing Deployed model dependency drift and environment compatibility. 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 — A new model signature expects messages array but the existing app sends only a prompt string. — is testing Deployed model dependency drift and environment compatibility. 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. 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 — A new model signature expects messages array but the existing app sends only a prompt string. — is testing Deployed model dependency drift and environment compatibility. 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. Route numerical KPI requests to the configured Genie Space then compose an answer from 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 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. Keep the retriever as an independent runnable stage and swap model components under the same interface. 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 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 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 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. Restrict endpoint CAN QUERY access to approved principals and test permission boundaries. This action primarily relates to Model Serving endpoint permissions and caller identity: Access to a serving endpoint is governed by workspace rights and identity; caller authorization is distinct from data-source permissions. However, the described case — New policies appear in Delta but a manually managed embedding index still returns retired versions. — is testing Databricks Vector Search index from governed Delta data. 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. Benchmark a supported index type and provision for the expected vector count, latency and update pattern. 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 — New policies appear in Delta but a manually managed embedding index still returns retired versions. — is testing Databricks Vector Search index from governed Delta data. 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. Deploy synchronized index definitions and validate source freshness during production cutover. 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 — New policies appear in Delta but a manually managed embedding index still returns retired versions. — is testing Databricks Vector Search index from governed Delta data. 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. Preserve hierarchical section IDs and supply the parent definition only when relevant. This action primarily relates to Parent-child retrieval and hierarchical structure: Parent-child retrieval indexes targeted sections but expands to their broader parent context for generation. However, the described case — A crawler fetches HTML product manuals but outputs menu text instead of article content. — is testing Format-specific document extraction and OCR needs. 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. Rerank a sufficiently broad candidate pool then pass a smaller high-relevance set to the LLM. This action primarily relates to Cross-encoder reranking after candidate retrieval: A reranker scores query-document relevance over a candidate set; it improves ordering but does not add missing documents. However, the described case — A crawler fetches HTML product manuals but outputs menu text instead of article content. — is testing Format-specific document extraction and OCR needs. 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. Increase suitable chunk length and reduce unnecessary overlap while checking passage-level answer recall. 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 crawler fetches HTML product manuals but outputs menu text instead of article content. — is testing Format-specific document extraction and OCR needs. 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 both rare identifiers and paraphrased questions with strict cross-tenant non-disclosure checks. 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 — 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 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 an incremental update and verify new, changed and deleted source chunks are reflected exactly once. 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 — 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 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 hit recall and answer grounding for sample chunk sizes with a fixed query set. 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 — 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 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. Use the managed Genie connector alongside a narrowly scoped custom MCP server for ticket actions. This action primarily relates to Managed versus external versus custom MCP server integration: MCP standardizes tool discovery; managed servers reduce hosting, external services need credentials and custom servers wrap bespoke actions. However, the described case — A company must deploy a custom fine-tuned checkpoint with nonstandard preprocessing not offered by managed endpoints. — is testing Foundation Model API versus custom serving choices. 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. Run the supported index update/sync process and verify the indexed source identifiers reflect current Delta records. This action primarily relates to Databricks Vector Search index from governed Delta data: A vector index serves embeddings of chunked records maintained in a Unity Catalog governed Delta source table. However, the described case — A company must deploy a custom fine-tuned checkpoint with nonstandard preprocessing not offered by managed endpoints. — is testing Foundation Model API versus custom serving choices. 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. Register immutable prompt versions, evaluate staging and move the approved production alias. 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 — A company must deploy a custom fine-tuned checkpoint with nonstandard preprocessing not offered by managed endpoints. — is testing Foundation Model API versus custom serving choices. 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.