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?
Select an answer to reveal the explanation.
Short Explanation
You can give the housing assistant session consistency so a resident’s multi-turn reads stay aligned within that session. This avoids requiring strong consistency for every regional operation.
Full Explanation
Azure Cosmos DB session consistency gives a consistent view within a client session, fitting a housing assistant’s multi-turn retrieval: the resident’s session can read its own latest writes without requiring strong consistency for every regional operation. It is a practical middle ground for conversational municipal AI that needs per-user read-your-writes behavior. Eventual consistency can keep regional reads low-latency, but a resident’s newest update may remain invisible until replication catches up, disrupting continuity when the session needs that update. Strong consistency for every operation across all regions regardless of session needs imposes latency and availability tradeoffs even when only session-scoped consistency is required. Disabling consistency guarantees and caching random replicas in the browser abandons Cosmos consistency behavior and risks unreliable civic answers. Exam caveat: session consistency is scoped to a session token or client session, not a global guarantee across all users and regions; strong consistency may still suit cross-region conflict-critical writes. Practical check: configure the Cosmos client for session consistency, test a multi-turn retrieve/update flow as one resident session, verify read-your-writes behavior, and compare latency and RU against a strong-consistency pilot. Ensure new browser tabs or devices start sessions intentionally so operators understand session boundaries.