Question

A logistics company wants an agent to predict optimal delivery routes based on their unique fleet constraints, historical delivery patterns, and regional traffic behavior specific to their operations. As the solution architect, you are assessing whether their data is suitable for grounding before committing to a design. You discover that route history exists but is spread across three legacy systems, contains duplicate records, uses inconsistent address formats, and the most recent six months of data has not yet been ingested. Which data-readiness dimension represents the MOST critical gap to resolve before this predictive agent can produce reliable outputs?

Accepted Answer

Cleanliness and timeliness — the duplicate records, inconsistent formatting, and stale six-month gap must be remediated so the agent grounds on accurate, current data

Answer

Relevance — the route history is unrelated to the prediction task and should be replaced with a public traffic dataset

Answer

Availability — the data cannot be accessed at all and must first be migrated to a single cloud store before any other concern

Answer

Volume — there is insufficient total data to train any model regardless of quality