Databricks Certified Generative AI Engineer Associate Bundle

Not the strongest diagnose choice for this specific question. Inspect token distribution, overlap proportion, expected retrieval granularity and vector count. 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 troubleshooting guide's symptom and resolution are in separate sections when cut every 400 characters. — is testing Semantic boundaries versus fixed-window chunks. It does not directly establish the 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 most frequent n-grams, extracted layout artifacts and top retrieved false positives. This action primarily relates to Boilerplate and navigation filtering in source corpora: Duplicated headers, disclaimers and navigation menus contaminate embeddings and cause irrelevant hits. However, the described case — A troubleshooting guide's symptom and resolution are in separate sections when cut every 400 characters. — is testing Semantic boundaries versus fixed-window chunks. It does not directly establish the 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. Compare intended answer fields to current indexed sources and freshness requirements. This action primarily relates to Authoritative source coverage for factual answers: A RAG model cannot answer accurately if the required authoritative record is missing or stale in its index. However, the described case — A troubleshooting guide's symptom and resolution are in separate sections when cut every 400 characters. — is testing Semantic boundaries versus fixed-window chunks. It does not directly establish the 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. 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 knowledge assistant embeds HR leave requests containing national IDs not needed for policy answers. — is testing Sensitive-field masking before embedding. 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. 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 knowledge assistant embeds HR leave requests containing national IDs not needed for policy answers. — is testing Sensitive-field masking before embedding. 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. Maintain an auditable source-rights register and recheck rights when a corpus is refreshed. 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 knowledge assistant embeds HR leave requests containing national IDs not needed for policy answers. — is testing Sensitive-field masking before embedding. 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 place MCP API keys in prompts or browser code, and review third-party tool trust boundaries. 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 chat frontend embeds a service-principal secret directly into JavaScript to call the agent endpoint. — is testing Databricks Apps user-facing agent interface and OAuth identities. 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. Rotate credentials and separately verify caller identity and underlying data permission scopes. 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 — A chat frontend embeds a service-principal secret directly into JavaScript to call the agent endpoint. — is testing Databricks Apps user-facing agent interface and OAuth identities. 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 budget limits and retry semantics when applying per-row model calls to large tables. 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 chat frontend embeds a service-principal secret directly into JavaScript to call the agent endpoint. — is testing Databricks Apps user-facing agent interface and OAuth identities. 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 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 startup scrapes a paid technical manual site into its product RAG index despite restrictive subscription terms. — is testing Training and retrieval corpus license rights. It does not directly establish the 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 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 startup scrapes a paid technical manual site into its product RAG index despite restrictive subscription terms. — is testing Training and retrieval corpus license rights. It does not directly establish the 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 — A startup scrapes a paid technical manual site into its product RAG index despite restrictive subscription terms. — is testing Training and retrieval corpus license rights. It does not directly establish the 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. Run adversarial quoted-text tests and compare output structure on representative and edge inputs. 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 shipping chatbot returns a list with inconsistent property names, breaking the downstream parcel status renderer. — is testing Structured JSON schema prompt and format compliance. 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. Withhold one source during testing and confirm the chain degrades safely rather than inventing a missing record. This action primarily relates to Parallel retrieval and deterministic chain postprocessing: Combining structured lookup and semantic retrieval requires explicit routing, result joining, and downstream schema checks. However, the described case — A shipping chatbot returns a list with inconsistent property names, breaking the downstream parcel status renderer. — is testing Structured JSON schema prompt and format compliance. 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. Inspect a full trace to confirm retrieved evidence and user intent reach the model and that citations point to real chunks. This action primarily relates to Retriever-generator chain component boundaries: A basic RAG chain separates user input, query transformation, retrieval, prompt assembly, model generation and output validation. However, the described case — A shipping chatbot returns a list with inconsistent property names, breaking the downstream parcel status renderer. — is testing Structured JSON schema prompt and format compliance. 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 allowed and denied principals against both endpoint invocation and protected retrieval data. 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 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 session resume for the same user and deny cross-user recall of private ticket details. This action primarily relates to Persistent conversation memory with authorized datastore: Transient prompt context differs from persistent user state; durable memory needs explicit storage, identity scope and retention. 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 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. Validate tool discovery and a permitted request for both services, including denied action testing. 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 — 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 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. 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 — A customer helpdesk agent loses the selected ticket ID whenever a user starts a new session, despite needing session continuity. — is testing Persistent conversation memory with authorized datastore. 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. Route calls through an authenticated backend with scoped credentials and remove tokens from client code. 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 — A customer helpdesk agent loses the selected ticket ID whenever a user starts a new session, despite needing session continuity. — is testing Persistent conversation memory with authorized datastore. 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. Package preprocessing, inference and postprocessing in an MLflow pyfunc model with required dependencies and signature. 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 customer helpdesk agent loses the selected ticket ID whenever a user starts a new session, despite needing session continuity. — is testing Persistent conversation memory with authorized datastore. 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 malicious requests with valid JSON tool calls and confirm the tool rejects unauthorized actions. This action primarily relates to Prompt safety filtering and tool allowlists: Content filters and action allowlists are complementary; a moderation score is not a substitute for authorization of external effects. However, the described case — A knowledge assistant embeds HR leave requests containing national IDs not needed for policy answers. — is testing Sensitive-field masking before embedding. It does not directly establish the verify outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest verify choice for this specific question. Inject the hostile PDF and verify no secret leaves the backend and no unauthorized tool is invoked. This action primarily relates to Input guardrails against prompt-injected source documents: A document that says 'ignore your rules' is untrusted data; a robust agent must enforce instruction and tool boundaries independently. However, the described case — A knowledge assistant embeds HR leave requests containing national IDs not needed for policy answers. — is testing Sensitive-field masking before embedding. 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 knowledge assistant embeds HR leave requests containing national IDs not needed for policy answers. — is testing Sensitive-field masking before embedding. 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. 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 — After an ingestion rerun, duplicate chunks multiply because the pipeline only appends without source identity. — is testing Delta and Unity Catalog pipeline for chunk tables. 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. Ingest a current price source with source timestamps and governed refresh frequency. 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 — After an ingestion rerun, duplicate chunks multiply because the pipeline only appends without source identity. — is testing Delta and Unity Catalog pipeline for chunk tables. 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 most frequent n-grams, extracted layout artifacts and top retrieved false positives. This action primarily relates to Boilerplate and navigation filtering in source corpora: Duplicated headers, disclaimers and navigation menus contaminate embeddings and cause irrelevant hits. However, the described case — An internal parts bot misses exact serial number ZX-410 because embeddings match only conceptual part descriptions. — is testing Hybrid sparse and dense retrieval with 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 heading structure, sentence breaks, table boundaries and parent document identifiers. This action primarily relates to Semantic boundaries versus fixed-window chunks: Headings, paragraphs and tables can require structure-aware splitting rather than arbitrary token windows. However, the described case — An internal parts bot misses exact serial number ZX-410 because embeddings match only conceptual part descriptions. — is testing Hybrid sparse and dense retrieval with 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 labeled query/chunk relevance, false positive hits, top-k settings and evaluation coverage. This action primarily relates to Retrieval recall precision and ranking diagnostics: Measure hit recall, precision, MRR or nDCG on labeled query-to-relevant-chunk pairs before tuning retrieval. However, the described case — An internal parts bot misses exact serial number ZX-410 because embeddings match only conceptual part descriptions. — is testing Hybrid sparse and dense retrieval with 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. Do not assert every index feature or hybrid/rerank option exists in every SKU, workspace or region. 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 production team passes around unversioned notebook checkpoints and cannot reproduce the active agent package. — is testing Unity Catalog registered model version and privileges. 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 production team passes around unversioned notebook checkpoints and cannot reproduce the active agent package. — is testing Unity Catalog registered model version and privileges. It does not directly establish the safeguard outcome or constraint that the question requires; it may still be useful in a different stage or incident.

Not the strongest safeguard choice for this specific question. Treat 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 — A production team passes around unversioned notebook checkpoints and cannot reproduce the active agent package. — is testing Unity Catalog registered model version and privileges. 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.