Cube

@the_cube_dev

Agentic Analytics powered by Semantic Layer.

Pinned
Cube
@the_cube_dev
Sep 24
New in Cube: agentic analytics, one connector away from Claude. Agents don't need a better prompt. They need a harness — tools, context, checks, and a semantic layer that keeps every answer governed. cube.dev
Cube
@the_cube_dev
14h
Warehouse-native serving can fit a single-warehouse stack. Across multiple data sources, its tuning knobs and failure modes do not travel with you. Cube Store gives those workloads a portable serving layer.
Query Latency in the Age of AI Agents - Cube Blog
From cube.dev
Cube
@the_cube_dev
Nov 4
Apache Ossie makes semantic models portable. It doesn’t execute queries, cache results, or enforce access. Cube’s converter also flags sums made unsafe by join fan-out instead of quietly exporting wrong numbers. cube.dev/blog/introduci…
Cube
@the_cube_dev
Nov 4
Hear from @BetterUp and Jeff Sato: "It allows end users to consume the data using the AI tool of their choice, and giving us that governance layer on top." One semantic layer under Claude, the Cube agent and every dashboard. Full video and story in the reply.
1
Cube
@the_cube_dev
Nov 3
Cube Store’s query path is more than pre-aggregation: a router prunes partitions and selects indexes before workers run DataFusion over cached Parquet and in-memory Arrow. Object storage stays the source of truth.
Query Latency in the Age of AI Agents - Cube Blog
From cube.dev

Cube’s posts