Article: AI Changes the Data Interface, Not the Query Engine

An AI agent that reads Parquet still depends on an execution engine; AI changes the analytical interface and interpretation layer, not the need for precise computation. Separate deterministic computation from probabilistic reasoning. Engines should filter, aggregate, and join, while agents should interpret evidence and communicate conclusions. An embedded engine such as DuckDB can be sufficient when the data volume is moderate, the primary consumer is the agent workflow, and writes are controlled. A managed lakehouse becomes valuable when data has multiple independent consumers, must join with large shared datasets, requires concurrent writes, or needs organization-wide governance. Production-grade agent analytics should retain the source data, configuration, derived facts, and model outputs so that every report can be validated and replayed. AI agents can now generate analytical code, read files from object storage, and turn operational data into structured reports. Does that make data lakes, lakehouses, and SQL engines obsolete? We encountered this question while automating the analysis of a large disaster-recovery exercise. Our first working design stored thirty-second service metrics as Parquet in S3-compatible object storage, used DuckDB for deterministic aggregation, and asked an AI agent to classify failover outcomes and explain the evidence. The prototype worked without a shared lakehouse,…