Databricks Certified Generative AI Engineer Associate Bundle

Not the strongest safeguard choice for this specific question. Never rely on interactive notebook state or unpinned runtime packages when promoting a served model. This action primarily relates to MLflow pyfunc packaging for pre- and post-processing: A custom MLflow pyfunc model wraps request parsing, retriever/model invocation and output formatting inside a reproducible predict interface. However, the described case — A deployed chatbot silently uses a different embedding model from the retrieval index built in development. — is testing RAG production bundle metadata and dependencies. 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 equate registering a model with approving its business safety or access to all governed tables. 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 deployed chatbot silently uses a different embedding model from the retrieval index built in development. — is testing RAG production bundle metadata and dependencies. 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. Require approval/rollback for prompt and index changes that alter user-facing model behavior. 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 — A deployed chatbot silently uses a different embedding model from the retrieval index built in development. — is testing RAG production bundle metadata and dependencies. 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 request/response sensitive spans, redaction logs, moderation findings and business exceptions. This action primarily relates to PII masking and output moderation as complementary guardrails: Input redaction and output checks serve distinct purposes; retain only necessary identifiers and validate actions separately. However, the described case — An order assistant answers shipping questions without using the provided account_id, mixing orders across customers. — is testing Query-field driven prompt and retrieval filters. 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 order assistant answers shipping questions without using the provided account_id, mixing orders across customers. — is testing Query-field driven prompt and retrieval filters. 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 tool-call traces, retrieved source text and permission decisions for instruction-origin confusion. This action primarily relates to Prompt-injection defenses for retrieved context: Retrieved content is lower-trust data; embedded instructions must not trigger privileged tool calls or override assistant rules. However, the described case — An order assistant answers shipping questions without using the provided account_id, mixing orders across customers. — is testing Query-field driven prompt and retrieval filters. 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. Evaluate capable long-context models on legal clauses and latency/cost acceptance thresholds. This action primarily relates to Model selection by quality latency and budget: Select the smallest suitable model that meets a task's accuracy and latency constraints under realistic workload, not marketing rank. However, the described case — A LangChain workflow sends a dictionary of question and context to a prompt that expects only input, raising a key error. — is testing LangChain runnable composition and invocation. 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 component roles explicit so updates to a generation model do not silently alter retrieval vectors. This action primarily relates to Specialized model versus general LLM: Embedding, reranking, extraction and generative models solve different stages and should be evaluated for their actual role. However, the described case — A LangChain workflow sends a dictionary of question and context to a prompt that expects only input, raising a key error. — is testing LangChain runnable composition and invocation. 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 a sampling and redaction policy for traces rather than logging raw secrets in production. 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 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 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 tune chunk length on one successful demo; measure evidence recall and grounded answer performance. 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 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 trust an LLM-extracted customer identifier without server-side permission validation. 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 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. 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 LangChain pipeline returns an SDK message object while its API gateway expects a plain answer string. — is testing Simple prompt-retrieval-generation chain assembly. 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 model invocation under realistic throughput and verify output schema, quota and governance constraints. This action primarily relates to Foundation Model API versus custom serving choices: Databricks Foundation Model APIs offer managed access to supported models; custom serving is suitable for specialized models or control needs. However, the described case — A LangChain pipeline returns an SDK message object while its API gateway expects a plain answer string. — is testing Simple prompt-retrieval-generation chain assembly. 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. Load the registered bundle in a clean environment and validate retrieval-to-generation behavior end to end. 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 LangChain pipeline returns an SDK message object while its API gateway expects a plain answer string. — is testing Simple prompt-retrieval-generation chain assembly. 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 paired representative requests and record quality versus p95 latency and cost tradeoffs. This action primarily relates to Model selection by quality latency and budget: Select the smallest suitable model that meets a task's accuracy and latency constraints under realistic workload, not marketing rank. However, the described case — A low-cost support search uses short chunks but the proposed model multiplies embedding dimensions by eight. — is testing Embedding dimensions latency and index storage. 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. Verify matched query and document vectors use the approved version and retrieval improves on held-out examples. 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 low-cost support search uses short chunks but the proposed model multiplies embedding dimensions by eight. — is testing Embedding dimensions latency and index storage. 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. Check embedding dimensions or extracted-field validation against task-specific acceptance tests. This action primarily relates to Specialized model versus general LLM: Embedding, reranking, extraction and generative models solve different stages and should be evaluated for their actual role. However, the described case — A low-cost support search uses short chunks but the proposed model multiplies embedding dimensions by eight. — is testing Embedding dimensions latency and index storage. 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 safeguard choice for this specific question. Treat index freshness as a monitored dependency of source-document correctness. 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 — An analyst must classify millions of rows overnight inside a governed Databricks SQL pipeline. — is testing SQL ai_query for governed batch inference. 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. Compare storage-optimized versus standard options, supported limits and actual query latency before selection. 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 — An analyst must classify millions of rows overnight inside a governed Databricks SQL pipeline. — is testing SQL ai_query for governed batch inference. 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. 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 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 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 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. 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 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 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 mismatched user and account values and confirm zero unauthorized retrieval and correct contextual answers. 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 troubleshooting assistant retrieves a part number but omits the note that the part is discontinued. — is testing Chunk quality evaluation and boundary splitting. 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. Use the same quality rubrics for pre-release gates and production monitoring with separate datasets. This action primarily relates to Offline evaluation versus ongoing production monitoring: Offline test datasets catch regressions pre-release; production monitoring detects drift, real-user failures and evolving prompts. However, the described case — A troubleshooting assistant retrieves a part number but omits the note that the part is discontinued. — is testing Chunk quality evaluation and boundary splitting. 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. Rerun a controlled experiment and confirm metrics match within expected stochastic tolerance. 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 troubleshooting assistant retrieves a part number but omits the note that the part is discontinued. — is testing Chunk quality evaluation and boundary splitting. 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. Benchmark per-answer cost and quality on representative traffic before promoting optimizations. 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 policy assistant begins making incorrect claims after the source index updates, but no live records show which index answered. — is testing Inference tables and Agent Monitoring feedback loop. 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. Re-evaluate previously disputed cases and confirm inter-rater agreement improves after calibration. 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 policy assistant begins making incorrect claims after the source index updates, but no live records show which index answered. — is testing Inference tables and Agent Monitoring feedback loop. 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 paired experiments with consistent evaluation data and evaluate cost-quality Pareto tradeoffs. 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 policy assistant begins making incorrect claims after the source index updates, but no live records show which index answered. — is testing Inference tables and Agent Monitoring feedback loop. 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. 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 — An analyst must classify millions of rows overnight inside a governed Databricks SQL pipeline. — is testing SQL ai_query for governed batch inference. 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. Use an available Foundation Model API endpoint with compatible authentication, task API and quotas. This action primarily relates to Foundation Model API versus custom serving choices: Databricks Foundation Model APIs offer managed access to supported models; custom serving is suitable for specialized models or control needs. However, the described case — An analyst must classify millions of rows overnight inside a governed Databricks SQL pipeline. — is testing SQL ai_query for governed batch inference. 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 semantic index search with model/tenant metadata filters and select source chunks for grounding. This action primarily relates to Vector Search retrieval workflow and query integration: Semantic retrieval uses an embedding model to query a compatible index, returns ranked passages and metadata for grounded generation. However, the described case — An analyst must classify millions of rows overnight inside a governed Databricks SQL pipeline. — is testing SQL ai_query for governed batch inference. 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.