Build data analysis reports and dashboards with a coding agent
A toolkit gives a coding agent a semantic layer and dashboard files so it can query data warehouses and publish in-depth reports and visualizations.
Done with a custom-built or unnamed agent
- What they did
- Graphene is an npm CLI that you add to a project, either standalone or inside a repo such as dbt. You define semantic models in .gsql files and pages in markdown files. You start the dev server and prompt your coding agent to answer a question, build a dashboard, or edit the model. The agent writes GSQL queries and chart components, and the CLI checks syntax, renders pages, and prints screenshots so it can iterate.
- How it went
- The source gives no measured results. It claims analysis runs 10x faster and that pages look consistent by default, and it lists Snowflake, BigQuery, ClickHouse, Postgres, MotherDuck and DuckDB as supported sources.
- Worth knowing
- The Elastic License 2.0 allows free internal use only. Building a commercial product on it needs a separate agreement, and using it without Graphene Cloud requires git and a coding agent.
Try it yourself with Claude Code
Help me build a data analysis report from [my data warehouse or data files, e.g. a Postgres database or a folder of CSVs]. First define a simple semantic layer in files, with the key tables, metrics and joins for [my business area]. Then query the data, answer [my main question], and publish a dashboard or report with charts as files in this folder. Stop when I can open the report and each chart lists the query behind it, and ask me before running anything that writes to the database.
Discussion on HN · Oct 1, 2026
Five of these in your inbox every morning
The best things people got an AI agent to do, each with the prompt to try it.
More like this
Find connections across 100 non-fiction books
Claude Code browses a personal library with CLI tools and surfaces trails of related excerpts across books.
Scrape weekly Substack rankings and write a report
Claude in Chrome runs weekly to scrape Substack ranking data into a dataset, and Cowork analyzes it and writes a weekly report.
Summarize 20 articles into a cited document
An agent extracted key insights from 20 articles, found common themes and produced a cited summary; the write-up estimates 18 minutes versus hours by hand.
Research conference speakers and organize tabs
Comet researched 50 HumanX speakers, surfaced themes and podcast guests, built a camera spec table, and cleaned up tabs.
Let Cursor maintain an Obsidian notes vault
Cursor reviews vault structure, suggests connections, answers questions about notes and writes a daily done note documenting other agent sessions.
Research content from Slack and draft Notion guide ideas
A team DM'd Lindy in Slack to summarize a year of guides and research a model, and it created a Notion guide idea after asking for approval.