Portfolio
Projects
What I have built, as cases: the problem, the build, the stack and where it stands. Most of this code is private; the Coabana site tells the rest.
In production
AI agent for Looker developers on BigQuery
Coabana · 2025–present
An agent that lives inside Looker as an extension. From a request in plain language it produces a complete LookML project — views, explores, models, Looks and dashboards — validating every step against Looker and BigQuery, diagnoses existing dashboards and answers questions over the semantic layer, acting with the permissions of the user who asks. A Python agent on Google ADK on Cloud Run, the MCP server of the next card, and a React extension served by Looker; in production at a reference installation.
Google ADKMCPLookMLBigQueryCloud RunReact
Coabana ↗
In production
MCP server for the Looker API
Coabana · 2025–present
A Model Context Protocol server for the Looker API, open to any MCP client — an agent, Claude, Gemini or a developer's IDE — built for production rather than for a demo. Ten tool groups, from queries and explores to LookML, git and administration; per-user sessions that keep each developer's dev mode where they left it; the same tool names and capabilities as Google's MCP Toolbox for Looker, with folders, administration and content updates and deletes on top; and gates that refuse the irreversible operations unless they are explicitly enabled. It is the Looker arm of the agent above and runs beside it on Cloud Run.
PythonFastMCPLooker APICloud Run
In use
Looker administration toolkit
Coabana · 2025–present
Plan-then-apply administration of a Looker instance: users, groups, roles, folder permissions, user attributes, schedules and content. Every write is previewed as a plan before it is applied, every write command has a real dry run, and the same operations are exposed as a CLI and as an MCP server for agents.
PythonLooker APIMCP
In development
Cost audit agent for Google Cloud
Coabana · 2026
A Google ADK agent that explains a change in Google Cloud spend from the billing export: trend, breakdown by service, SKU and project, gross and net of credits, whether an anomaly is price or volume, and the evidence behind it, down to the BigQuery job or the dbt commit that changed a model's cost. Every figure in its report is labeled real, validated price or estimate.
Google ADKBigQueryCloud BillingGemini
In production
Looker at scale on BigQuery
Viajes El Corte Inglés · 2022–present
Organization-wide adoption of Looker on a BigQuery data platform: semantic models and governed metrics, access and cost control, data quality, and AI agents that let business teams explore their data in natural language. Google Cloud end to end.
BigQueryLookerCloud ComposerDataflowTerraform
Delivered
BI tools platform at PedidosYa (Delivery Hero)
2020–2021
Led the team of five behind the company's BI tools, Looker and Tableau, and built the data layer powering its business KPIs on a Google Cloud stack: Composer, BigQuery, Dataproc, Cloud Build and Cloud Storage.
LookerTableauBigQueryCloud ComposerDataproc
Delivered
Enterprise data warehouse for travel-tech
Bluekiri · 2019–2020
Built the organization's data warehouse and data marts and set the standards, best practices and methodology behind them: MicroStrategy for analytics, Apache Airflow for orchestration, Pentaho Data Integration, PostgreSQL, Azure DevOps.
MicroStrategyApache AirflowPentaho Data IntegrationPostgreSQLAzure DevOps
Delivered
Business analytics projects on Google Cloud
Alphalabs · 2020–2022
Co-founder and technical lead of a software company: technical proposals and budgets, the technical execution of client projects, and business analytics projects on Google Cloud.
Google Cloud