A lot of the useful agent infrastructure right now is being built below the model, in the data layer.

Agents query the same tables all day, and every request needs the newest rows plus the full history.

@Eon_io_ built Eon Yukon for that pattern. It ingests, cleans and compacts events into open Iceberg tables in your own bucket, and agents read each table’s context over MCP.
In Eon’s public benchmark, it used 4x less compute than Spark and 7x less than Flink.

Thats expected because, an agent that knows what a table holds before it queries it can skip a lot of wasted scans.