Databricks Certified Generative AI Engineer Associate Bundle

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 — An imported policy library contains a deliberately altered obsolete security procedure mixed into current instructions. — is testing Toxic, inaccurate and adversarial corpus cleaning. 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 — An imported policy library contains a deliberately altered obsolete security procedure mixed into current instructions. — is testing Toxic, inaccurate and adversarial corpus cleaning. 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 extraction fields, masking policy, downstream embedded text and sensitive-data exposure paths. 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 — An imported policy library contains a deliberately altered obsolete security procedure mixed into current instructions. — is testing Toxic, inaccurate and adversarial corpus cleaning. 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. 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 — An Agent Framework service reports only end-to-end duration, hiding which tool call causes a 12-second delay. — is testing MLflow tracing in an Agent Framework workflow. 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 unused side-effect tools and use a plain summarization chain with bounded output. This action primarily relates to Agent tool wrappers versus direct LLM responses: A tool-using agent needs explicit callable interfaces and typed tool results, whereas plain generation requires no action execution. However, the described case — An Agent Framework service reports only end-to-end duration, hiding which tool call causes a 12-second delay. — is testing MLflow tracing in an Agent Framework workflow. 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. Isolate instructions from source text and reject cross-trust-boundary requests through policy/tool checks. 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 Agent Framework service reports only end-to-end duration, hiding which tool call causes a 12-second delay. — is testing MLflow tracing in an Agent Framework workflow. 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. Retest adversarial sources after adding new file types and tool connectors. 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 support bot incorporates competitor FAQs with usage terms that forbid automated redistribution. — is testing Training and retrieval corpus license rights. 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 human review for borderline filtering decisions so source cleaning does not silently erase important warnings. 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 support bot incorporates competitor FAQs with usage terms that forbid automated redistribution. — is testing Training and retrieval corpus license rights. 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 grant the model blanket tool permission based only on a safe-looking input text score. 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 support bot incorporates competitor FAQs with usage terms that forbid automated redistribution. — is testing Training and retrieval corpus license rights. 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. 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 internal employee portal wants a Streamlit RAG chat UI over governed policy and private team data. — is testing Databricks Apps user-facing agent interface and OAuth identities. 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 `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 — An internal employee portal wants a Streamlit RAG chat UI over governed policy and private team data. — is testing Databricks Apps user-facing agent interface and OAuth identities. 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 — An internal employee portal wants a Streamlit RAG chat UI over governed policy and private team data. — is testing Databricks Apps user-facing agent interface and OAuth identities. 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. Implement response serialization within the serving wrapper and validate the declared output schema. 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 public browser sends a long-lived PAT directly to a model serving endpoint for each chat request. — is testing Model Serving endpoint permissions and caller identity. 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 the MLflow model as a named Unity Catalog model version and grant only approved use/manage rights. 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 public browser sends a long-lived PAT directly to a model serving endpoint for each chat request. — is testing Model Serving endpoint permissions and caller identity. 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. Version the serving input schema or provide a tested compatibility adapter during migration. This action primarily relates to Deployed model dependency drift and environment compatibility: Models logged in experiments can fail in serving if Python dependencies or inference signatures differ between build and target. However, the described case — A public browser sends a long-lived PAT directly to a model serving endpoint for each chat request. — is testing Model Serving endpoint permissions and caller identity. 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. Run an unavailable-inventory case to verify the assistant checks tool output and does not fabricate stock. This action primarily relates to Agent tool wrappers versus direct LLM responses: A tool-using agent needs explicit callable interfaces and typed tool results, whereas plain generation requires no action execution. However, the described case — A customer asks about 'the previous invoice' but the agent does not carry the prior invoice ID to the next turn. — is testing Conversation context and intent routing. 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. Reproduce a slow/error case and confirm each relevant stage is observable without sensitive tokens. 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 customer asks about 'the previous invoice' but the agent does not carry the prior invoice ID to the next turn. — is testing Conversation context and intent routing. 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 data questions for correct Genie routing, SQL-backed values and denial of unauthorized tables. 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 customer asks about 'the previous invoice' but the agent does not carry the prior invoice ID to the next turn. — is testing Conversation context and intent routing. 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. 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 research bot reports outdated product prices because the indexed catalog is a quarterly snapshot. — is testing Authoritative source coverage for factual answers. 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 research bot reports outdated product prices because the indexed catalog is a quarterly snapshot. — is testing Authoritative source coverage for factual answers. 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 — A research bot reports outdated product prices because the indexed catalog is a quarterly snapshot. — is testing Authoritative source coverage for factual answers. 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 a evaluated classification model and return a bounded label with confidence/abstention handling. This action primarily relates to Task choice: classification versus generative summarization: Classification predicts a category whereas summarization compresses meaning; the desired output determines the appropriate task. However, the described case — A support bot includes retrieved pages in responses but drops the original user's question before generation. — is testing Retriever-generator chain component boundaries. 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 asynchronous batch throughput and cost targets rather than paying for interactive latency. 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 support bot includes retrieved pages in responses but drops the original user's question before generation. — is testing Retriever-generator chain component boundaries. 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 the equipment identifiers, failure observations and inventory query as required inputs, with approved part IDs as outputs. This action primarily relates to Translate use-case requirements into pipeline inputs and outputs: Business acceptance criteria must map to concrete source inputs, generated fields, correctness measures and permission constraints. However, the described case — A support bot includes retrieved pages in responses but drops the original user's question before generation. — is testing Retriever-generator chain component boundaries. 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. Check answer fidelity, citation paths and forbidden document access across test identities. This action primarily relates to Agent Bricks Knowledge Assistant suitability: A governed knowledge assistant grounds conversational responses in curated documents and access-controlled retrieval. However, the described case — A finance controller wants a one-paragraph explanation of a long audit memo, not a risk score. — is testing Task choice: classification versus generative summarization. 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 malformed inputs and inspect whether every response satisfies the parser and required field contract. 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 finance controller wants a one-paragraph explanation of a long audit memo, not a risk score. — is testing Task choice: classification versus generative summarization. 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 cases with complete and missing required input fields and verify schema, access scope and usefulness. This action primarily relates to Translate use-case requirements into pipeline inputs and outputs: Business acceptance criteria must map to concrete source inputs, generated fields, correctness measures and permission constraints. However, the described case — A finance controller wants a one-paragraph explanation of a long audit memo, not a risk score. — is testing Task choice: classification versus generative summarization. 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. Move inference calls and secrets to the server-side app, using appropriate app/user authorization. This action primarily relates to Databricks Apps user-facing agent interface and OAuth identities: Databricks Apps supports authenticated interactive frontends; app credentials and user credentials have different scopes. However, the described case — A RAG endpoint should be invoked only by the internal support group, but every workspace member can call it. — is testing Model Serving endpoint permissions and caller identity. 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. Enforce reproducible environment manifests and API compatibility checks in CI/CD. This action primarily relates to Deployed model dependency drift and environment compatibility: Models logged in experiments can fail in serving if Python dependencies or inference signatures differ between build and target. However, the described case — A RAG endpoint should be invoked only by the internal support group, but every workspace member can call it. — is testing Model Serving endpoint permissions and caller identity. 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 the prompt hierarchy, few-shot coverage, untrusted-data delimiters and observed format deviations. This action primarily relates to Instruction hierarchy and bounded prompt examples: Few-shot examples and explicit boundaries can clarify expected outputs, but embedded source documents should not become new system instructions. However, the described case — A compliance agent needs both a Unity Catalog table result and an approved policy passage for each answer. — is testing Parallel retrieval and deterministic chain postprocessing. 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 parameter contracts, identity scopes, retry semantics and side-effect logs. This action primarily relates to Agent tool schemas, least privilege and retries: Well-described tool schemas constrain parameters, and idempotent retries prevent duplicate side effects. However, the described case — A compliance agent needs both a Unity Catalog table result and an approved policy passage for each answer. — is testing Parallel retrieval and deterministic chain postprocessing. 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 the business decision, data owners, actor permissions, known inputs and success criteria. This action primarily relates to Translate use-case requirements into pipeline inputs and outputs: Business acceptance criteria must map to concrete source inputs, generated fields, correctness measures and permission constraints. However, the described case — A compliance agent needs both a Unity Catalog table result and an approved policy passage for each answer. — is testing Parallel retrieval and deterministic chain postprocessing. 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.