Analytics, AI, and data in plain English.

Text-to-SQL is the task of translating a natural-language question into a SQL query that runs against a database and returns the answer.

A semantic layer is a central definition store that maps human-readable business concepts (revenue, churn, MRR) to the underlying tables and SQL that compute them.

A metric definition is the exact SQL or calculation that produces a business metric, plus the documented assumptions behind it.

A data warehouse stores structured, query-ready tables for analytics. A data lake stores raw files in any format. Modern stacks usually have both.

BIRD-Interact is a text-to-SQL benchmark of 600 deliberately ambiguous business questions across 22 realistic Postgres databases, published at ICLR 2026.

RAG is a pattern where an AI system retrieves relevant context from a knowledge source before generating an answer, instead of relying only on the model's training data.

Cohort analysis groups users by when they started (or another shared trait) and measures how that group behaves over time, so trends are not muddied by mixing new and old users.

ARR is the annualized value of all active recurring subscriptions at a point in time — what you would book over the next year if nothing changed.

A retention curve plots, for a cohort of users, what fraction is still active at each point in time after they joined.

The activation funnel measures how new users progress from signup through the steps that predict long-term retention, and where they drop off.

An attribution model assigns credit for a conversion (signup, purchase, deal) to the marketing touchpoints that preceded it.

Column lineage traces, for any column in any table, the chain of upstream columns and transformations that produced it.