bigquery-expert

Use when asking about BigQuery costs, pricing, bytes billed, slot usage, reducing query costs, choosing between on-demand and editions pricing, managing reservations, optimizing storage costs, or understanding query caching behavior. Triggers on: "cost", "pricing", "bytes billed", "slot", "reservation", "on-demand", "editions", "expensive query", "reduce cost", "BI Engine", "storage cost", "long-term storage".

Use when designing BigQuery table schemas, choosing partitioning or clustering strategies, deciding between nested/repeated fields vs flat schemas, selecting table types (native, external, views, materialized views), choosing data types, or planning denormalization. Triggers on: "partition", "cluster", "STRUCT", "ARRAY", "nested fields", "table design", "schema", "materialized view", "external table", "denormalize", "data type", "TIMESTAMP vs DATETIME".

Use when asking about BigQuery-specific features, syntax, or capabilities including: STRUCT/ARRAY/UNNEST patterns, MERGE statements, BigQuery scripting (DECLARE, IF, LOOP, BEGIN/END), scheduled queries, remote functions, JSON functions, approximate aggregation (APPROX_COUNT_DISTINCT, HLL_COUNT), geography/GIS functions, BigQuery ML (CREATE MODEL), search indexes, vector search, or BI Engine. Triggers on: "UNNEST", "STRUCT", "ARRAY", "MERGE", "DECLARE", "scripting", "scheduled query", "remote function", "JSON_EXTRACT", "APPROX_COUNT", "HLL", "ST_", "CREATE MODEL", "BQML", "search index", "vector search", "BI Engine".

Use when generating BigQuery SQL from natural language descriptions, converting queries from other SQL dialects to BigQuery, writing new BigQuery queries from scratch, or when the user describes what data they need and expects SQL output. Triggers on: "write me a query", "generate SQL", "how do I query", "convert this to BigQuery", "I need to get data from", "create a query".

Use when writing, reviewing, or optimizing BigQuery SQL, asking about BigQuery best practices, working with .sql files targeting BigQuery, or troubleshooting slow/expensive BigQuery queries. Symptoms: high slot consumption, full table scans, expensive joins, slow queries, high bytes billed.