Develop AI solutions by using Azure data management services (25–30%)

Microsoft Certified: Azure AI Cloud Developer Associate · 55 questions

• A city RAG store keeps ordinance chunk embeddings in Azure Cosmos DB for NoSQL for the permits bot. How should the back end retrieve nearest neighbors?
• County 311 knowledge items in Cosmos DB experience hot partitions around popular resident topics. What should the data design prioritize?
• A public-health FAQ assistant must look up grounding documents in Cosmos DB for NoSQL from its Azure back end. What is the appropriate access approach?
• A courts exhibit-metadata store in Cosmos DB needs lower RU cost for queries filtering on caseType and filedDate. What should the team optimize?
• A housing assistant needs consistent reads across a resident’s multi-turn retrieval session without paying for strong consistency on every regional operation. Which Cosmos consistency choice fits best?
• A transit agency stores alert embeddings in Cosmos DB for NoSQL and must meet semantic retrieval SLAs for the rider-info bot. What should the team configure?
• A library open-data bot needs grounded answers from Cosmos DB items that include both chunk text and embeddings. How should each item be modeled?
• Whenever permitting rules documents change in Cosmos DB, a search projection used by the city permits assistant must refresh. Which approach fits?
• Emergency management SOPs stored in Cosmos DB must be re-embedded when they are updated so the ops assistant stays current. What should drive the refresh?
• A parks FAQ generative workload hits Cosmos DB 429 responses during seasonal tourism spikes. What should the team do?
• An ordinance assistant already knows the id and partition key of a chunk it must load, while admins sometimes run ad hoc cross-partition searches. Which access pattern should the service prefer for the known chunk?
• A 311 agent stores short-lived conversation memory in Cosmos DB alongside long-lived knowledge chunks. How should TTL be applied?
• An assessor’s RAG assistant must join parcel attributes to embedding rows in Azure Database for PostgreSQL. What schema approach fits?
• A city complaint assistant stores embeddings with the pgvector extension in Azure Database for PostgreSQL. What must align for correct similarity search?
• County IT must support vector index builds on a large code-enforcement corpus in Azure Database for PostgreSQL. What should sizing prioritize?
• A housing casework assistant uses pgvector in Azure Database for PostgreSQL but must limit results by district and case status. What pattern should it use?
• A Container Apps RAG API calling Azure Database for PostgreSQL shows high connection latency under load. What should the team apply?
• A municipal code-search service on Azure Database for PostgreSQL filters by foreign keys and ranks by vector similarity. How should indexes be designed?
• Python civic services must query Azure Database for PostgreSQL under load for a permitting RAG back end. What is the appropriate approach?
• An active-permits chatbot queries Azure Database for PostgreSQL mostly against non-archived rows. How can indexing cut latency?
• A city wants to cut token spend on repeated 311 FAQ answers. Which Azure Managed Redis use fits?
• Ordinance answers cached in Azure Managed Redis become stale when the prompt or model version changes. What should cache keys include?
• Transit disruption summaries in Azure Managed Redis change quickly during incidents. Which expiration approach fits?
• A lightweight parks recommender needs fast nearest-neighbor lookup. How can Azure Managed Redis help?
• Clerk form-help snippets are generated by an LLM and reused through Azure Managed Redis. Which caching pattern is typically preferred for this side data?
• Top resident questions in Cosmos DB should warm an Azure Managed Redis cache used by the 311 assistant. What integration pattern fits?
• A municipal code-search assistant must apply keyword filters then rank by semantic similarity across Azure data services. What approach fits?
• An agent tool layer nearly stored raw API keys inside Cosmos DB documents used for municipal workflows. What should the team do instead?
• A city must re-embed outdated rows when the embedding model changes. What should be stored with each vector?
• Historical meeting-minute chunks must be loaded into Cosmos DB for AI retrieval at city scale. What ingest approach fits?
• After a large parks program corpus is loaded into Azure Database for PostgreSQL with pgvector, vector query plans degrade. What maintenance step should the city take?
• Azure Managed Redis filling with seasonal event Q&A cache entries risks out-of-memory errors for the city FAQ bot. Which eviction approach fits?
• A statewide emergency FAQ assistant needs high availability for Cosmos DB writes, but cost still matters. What tradeoff should the architect evaluate?
• Civic staff admin tools query Cosmos DB for NoSQL using filters from UI fields. How should those queries be written?
• A city AI platform stores bulky ordinance PDFs and high-churn embedding items in Cosmos DB. How should containers be designed?
• A multi-department RAG app on Azure Database for PostgreSQL must keep HR-adjacent public-records rows scoped by department. What approach fits?
• A permitting RAG query on Azure Database for PostgreSQL should avoid computing vector distance across the entire corpus. What should the service do first?
• Multiple RAG indexer instances across environments process a Cosmos DB change feed for permitting rules. How should leases be handled?
• Many 311 API pods miss Azure Managed Redis simultaneously during an outage recovery. What problem should the team prevent?
• A parks RAG design wants a Redis vector index for speed but durable full chunk text elsewhere. What split fits Azure data services?
• A shared city AI platform in Cosmos DB must partition by city, department, and document type together. What feature helps?
• After changing PostgreSQL pgvector lists/probes-style settings for a code-enforcement corpus, what should county IT measure?
• A reprocessing job may embed the same ordinance version more than once. How should writes be handled?
• Citywide semantic cache traffic on Azure Managed Redis exceeds a single-node comfort zone. What should the platform team evaluate?
• Structured permit fields must remain the system of record while also feeding RAG. Which data-service choice fits?
• Withdrawn public comments must stop appearing in RAG without hard-deleting audit history in PostgreSQL. What model fits?
• A multi-tenant civic Cosmos DB AI store must understand which department partitions consume the most RU. What should ops monitor?
• Azure Functions repeatedly look up the same RAG metadata shapes in Azure Database for PostgreSQL. How can throughput improve?
• A municipal agent caches structured tool-step results in Azure Managed Redis. Which data-structure approach fits?
• After an embedding model upgrade, some Cosmos DB ordinance items still have null vector fields. What job should run?
• An emergency agent must read SOP chunks that were just written to Cosmos DB. Which consistency concern applies?
• Azure Database for PostgreSQL stores large binary attachments beside searchable municipal text used for RAG. How should indexing treat those binaries?
• Chatty RAG clients threaten the shared Cosmos DB RU budget during council-meeting nights. What client-side protection fits?
• Before inserting into a pgvector column for a municipal corpus, what must the pipeline validate?
• Cold meeting transcripts should leave Azure Managed Redis while hot FAQ vectors stay warm. What tiering approach fits?