BigQuery plugins

Build production-ready data engineering stacks: Airflow DAGs for orchestration, dbt models for transformations, scalable pipelines with Spark on cloud warehouses like BigQuery and Snowflake, Kafka streaming, optimized embeddings for RAG, and vector databases like Pinecone, Weaviate, and pgvector.

Empower Claude Code to handle business analyst workflows: design KPI frameworks and dashboards for sales/marketing/product, build 3-5 year startup financial models with cohort revenue and scenario analysis, calculate TAM/SAM/SOM market sizes, and optimize seed-to-Series A metrics using Python, SQL, Snowflake, and BigQuery.

Automate finance and accounting workflows by generating journal entries, reconciliations, financial statements, variance analyses, SOX compliance docs, and month-end checklists. Query BigQuery datasets, access company knowledge bases, and integrate with Gmail, Slack, Microsoft 365, and Google Calendar for seamless data retrieval and collaboration.

Build and operate AWS data lakes: create managed Iceberg tables on S3 with Glue integration, import data from S3/JDBC/Redshift/Snowflake/BigQuery/DynamoDB, execute and manage Athena SQL queries, store/query vectors, resolve assets across catalogs, audit Glue inventories, and troubleshoot connections.

Build forecasting datasets and fine-tune models with Lightning Rod SDK. Ingest data from BigQuery, local files, or web sources, apply temporal splitting and domain transforms, then train using GRPO or SFT patterns.

Query BigQuery datasets, execute SQL, and leverage AI/ML functions (forecasting, generation) to analyze multi-dimensional data and generate insights.

Autonomously draft complete USPTO, EPO, and PCT patent applications from invention disclosures: search 100M+ patents via BigQuery for prior art and patentability, analyze claims/specifications for MPEP/35 USC 112/EPC Art 84 compliance, generate Graphviz diagrams, validate formalities, and output markdown+SVG filing packages. Self-contained, no MCP server needed.

Build and orchestrate end-to-end GCP data pipelines using natural language — generate Dataform/dbt code, run Spark and BigQuery SQL notebooks, provision infrastructure, and troubleshoot Cloud Composer workflows, all from your coding agent.

Automate production performance marketing workflows: audit ad accounts, launch Google Ads/Meta campaigns, rotate creatives, diagnose underperformers, analyze search terms, and safely execute writes across Google Ads, Meta, GA4, Shopify, HubSpot, TikTok, and 20+ platforms with approval gating.

Initialize drt Reverse ETL projects with data warehouses like BigQuery, DuckDB, or Postgres; generate YAML sync configs to destinations such as Slack, Discord, Jira, REST APIs; debug failing syncs from auth errors to config issues; migrate pipelines from Census, Hightouch, or custom scripts to drt YAML.

Compile .view.yml semantic layer definitions into dialect-specific SQL for Postgres, MySQL, BigQuery, and Snowflake. Validate schemas for errors, duplicates, references, and types. Inspect views, dimensions, measures, and entities to explore structure before building and testing semantic queries.

Empower AI coding agents to build and manage Honeydew semantic data models: query/analyze warehouse data via structured/natural language queries, define entities/relations/metrics/domains from Snowflake/BigQuery, handle git-like workspace/branch workflows, create context items, and validate model integrity.

Control SAP Datasphere via natural language to explore catalogs and schemas, design semantic models and views, build and optimize ETL flows and task chains, connect diverse data sources, migrate from BW/4HANA, govern metadata and security, activate business content, automate admin via CLI, and troubleshoot pipelines.

Generate optimized SQL queries from natural language for BigQuery, PostgreSQL, MySQL, and Snowflake; perform cohort analysis on CSV/Excel user data to compute retention rates, visualize trends, and detect anomalies; evaluate A/B tests with statistical significance, confidence intervals, and launch recommendations.

Generate cost-safe geospatial SQL queries for Overture Maps data in BigQuery or Snowflake, then render results directly on interactive Dekart maps for quick visualization and analysis without high query costs.

Manage Dutch tax workflows for individuals, freelancers, and companies—from client intake and declaration preparation to compliance checks and objection drafting—by querying verified official sources through connected company knowledge bases, Notion pages/databases, Microsoft 365 emails/files/Teams, BigQuery datasets, and Slack channels.

Delegate specialized development tasks to AI subagents that architect features with Mermaid diagrams and checklists, generate PRDs and specs, query SQL/BigQuery for data analysis, implement precise code from tasks.md, debug errors with root cause fixes, proactively review git diffs for quality/security, and analyze codebases for project guidance files.

Equip AI agents to analyze event data in Altertable lakehouse: explore schemas across databases like DuckDB, Snowflake, BigQuery; execute SQL queries; build funnels, segments, retention insights; detect anomalies, forecast trends; generate visualizations; manage memories, approvals, and automated monitoring workflows.

Generate warehouse-specific Python scripts to collect and push table metadata, column lineage, and query logs from Snowflake, BigQuery, Databricks, Redshift to Monte Carlo via push ingestion API. Verify ingestion accuracy, create/update custom lineage nodes and edges, and delete assets using GraphQL commands.

Design AWS and GCP infrastructure using Terraform and Ansible patterns, build data pipelines with dbt and SQLMesh, generate and manage RFCs plus technical specs in Markdown, and automate local dev setups including direnv, git worktrees, and port allocations for Docker services.