The hard part of AI data analysis is knowing when it’s correct

In practice, most of the difficulty isn’t in generating analysis steps/transformations, but in verifying that the result is correct.

Our current approach includes:

• Sandboxed / sample runs on smaller datasets before full execution

• Step-level transparency: summaries, intermediate tables, and generated code are visible

• Parallel and sequential test-time execution to surface inconsistencies

• dbt-style pipelines for reproducibility and explicit dependencies

• Decomposing analyses into small, verifiable steps to avoid error compounding (e.g. MAKER-style approaches)

• Online validation checks that trigger re-analysis when assumptions are violated

• A gradually evolving semantic layer to improve consistency and governance over time

Curious to hear from others: what would make you trust an AI-driven data platform?