Herramientas

Creates, edits and validates reproducible Python and SQL Jupyter notebooks: organizes cells as reports or tutorials, checks conclusions against actual output and reruns top to bottom before handoff. Maintained by OpenAI in the Data Analytics plugin of openai/plugins.

Helps agents write geospatial SQL for PostGIS, DuckDB, BigQuery and Snowflake: inspect schemas and keep query costs in check, then render results as interactive maps to review and correct. Needs Python and your own database or warehouse; maps use Dekart, which can run locally in Docker.

Official Databricks skills guiding agents to build Lakeflow pipelines and jobs, Apps, Lakebase, Vector Search, Model Serving and AI/BI dashboards on the lakehouse. Needs the Databricks CLI.

Beancount's official query tool, bean-query: run SQL-like queries on plain-text double-entry ledgers to get balances, income and expense summaries and account details, for agent-assisted bookkeeping. Needs uv or Python 3.8+ and a Beancount ledger; have an accountant review reports.

From TUM's Chair of Geoinformatics (a 3DCityDB co-developer): query CityGML 3D city models in 3DCityDB v5 in plain language, covering both spatial and semantic attributes, with read-only SQL. Needs a deployed 3DCityDB database and Python; register it from the folder with your .env config.