Build data analysis reports and dashboards with a coding agent

Tools

custom-built or unnamed agent

Overview

Graphene is a data analytics framework built for coding agents.

Workflow

Graphene is a data analytics framework built for coding agents. Ask questions and build visualizations 10x faster when agents do the work. Why Graphene? Graphene is an everything-as-code analytics framework for SQL-based data exploration, visualization, and reporting. It is designed with coding agents in mind as the primary user persona. It provides two critical pieces that allow coding agents to do better data work: A semantic layer, which yields more accurate queries. Graphene SQL combines the power of SQL with the governance of metrics and modeled joins. A dashboard file type, which yields more consistent and polished visuals compared to raw Python or Javascript. Design goals Token efficiency. Languages are designed to be brief with minimal boilerplate. Agent ergonomics. Graphene is controlled entirely via CLI. All documentation is inside our agent skill. High ceilings. Graphene SQL follows ANSI and supports over 170 functions; Graphene pages support anything that can be expressed with HTML, CSS, Javascript, and ECharts. Versus traditional BI We believe coding agents coupled with an everything-as-code analytics stack beats traditional BI in several ways: Broad ecosystem of SOTA LLMs, harnesses, skills, and tools Leverage business-wide context from other tools or repos Perform end-to-end tasks across tools, where analytics is just one step More graceful change management and bulk refactors Easily promote/demote logic into or out of the semantic layer Version control and CI. Revert agent mistakes. Run tests on mission-critical dashboards. Tight, complete iteration loops. Agents can validate before running, view dashboards, and iterate locally Leverage continuous agents for self-healing codebases Open, forever Graphene is free to use, forever. Your business logic lives in your repo and is never locked into a contract with us. Rich visualizations Graphene pages support visualizations, input components for filtering and dynamic behaviors, and layout modes for monitoring-oriented dashboards vs. narrative-oriented notebooks. Powerful, next-generation semantic layer Traditional semantic layers give you governance at the expense of capability. They tend to expose niche query APIs that agents aren't familiar with. Graphene SQL's goal is to bring governance without sacrificing capability. It behaves like regular SQL—with CTEs, subqueries, window functions, set operators, and more—but also adds in the concepts of measures and modeled joins from semantic layers. Graphene SQL is inspired by Malloy, from the creators of LookML Lloyd Tabb and Michael Toy, but implements it as good old SQL for agent familiarity. Get started Try the demo project Create a new Graphene project Graphene currently supports Snowflake, BigQuery, ClickHouse, Postgres, MotherDuck, and local data (via DuckDB) as data sources. It is easy for us to add more - just ask. Once your project is set up, simply start the dev server via npm exec graphene serve (or pnpm graphene serve, etc. based on your package manager) and then prompt your coding agent to do analytics work: answer a data question, build a dashboard, edit the model, etc. How it works Graphene itself is a CLI which can be installed via npm (or pnpm, yarn, etc.). The CLI can run and compile Graphene SQL queries, render pages in the browser, check syntax, print screenshots, and more. A Graphene project can either be a standalone repo or a directory within a larger codebase (such as dbt). It is comprised of semantic models via .gsql files and pages via .md files. Graphene SQL and Graphene markdown Semantic models are defined like so: Models are then queried via select, either directly via CLI or inside a Graphene markdown page like this. Documentation Graphene's entire documentation ships as an agent skill in the Graphene npm package. The source files are available here. FAQ

Reported result

The source claims agents can ask questions and build visualizations 10x faster, but no measured results or specific case study outcomes are provided. Actual performance depends on the specific data complexity and agent configuration. A measurable acceptance check would be to time the creation of a standard dashboard using Graphene versus a traditional BI tool for the same dataset.

Human role

The original post does not say how a person stayed involved.

Limitations

Prerequisites include a supported data source (Snowflake, BigQuery, ClickHouse, Postgres, MotherDuck, or DuckDB) and a coding agent environment. Graphene is licensed under Elastic License 2.0, allowing free internal use but requiring contact for commercial applications. Integration uncertainty exists regarding how well the agent handles complex, non-standard business logic without human correction.

Try it

I want to set up a Graphene project to analyze [replaceable: business context, e.g., sales data] using a coding agent. First, install Graphene via npm and initialize a new project in [replaceable: target directory]. Create a semantic model file (.gsql) for [replaceable: data table name] with measures for [replaceable: key metrics]. Then, prompt the agent to generate a dashboard page (.md) visualizing [replaceable: specific insight]. Before finalizing, run the dev server with 'npm exec graphene serve' and manually verify the data accuracy and visual layout. Do not publish or share the dashboard until I confirm the output matches expectations. If the agent fails to generate valid SQL, ask it to explain the error and propose a fix based on the Graphene documentation skill.

More cases · Research & knowledge

• Draft a dissertation lit review from uploaded sources
• Run a 24/7 local agent that curates news digests
• Track daily arXiv papers into a Notion database
• Give a coding agent a paper corpus to find new techniques
• Run data cleaning to executive summary with agent pipeline