Skip to content

Documentation

Dashies keeps an AI-built HTML dashboard alive - published, refreshing on a schedule, versioned, and shareable by link.

Dashies is the agentic BI platform for publishing, refreshing, and sharing AI-built HTML dashboards. Your own AI tool authors the dashboard; Dashies keeps it running.

Where to start

Evaluating. Read What Dashies is, then Is Dashies right for you?, which states the anti-fit as plainly as the fit.

Building. Go straight to the Quickstart. It needs no warehouse and no paid plan, and it ends at a live URL. Then Quickstart: a self-refreshing dashboard for the real loop.

Understanding it. Core concepts is the mental model in reading order. If you read only two pages, Datasets and the four modes and Measure correctness are the two that decide whether your numbers are right.

Wiring Dashies into an AI tool. The MCP tool reference is the contract.

The three steps

  1. Install the Dashies plugin, which bundles the authoring skill and the publish service.
  2. Connect a data warehouse: PostgreSQL, BigQuery, Snowflake, Redshift, Databricks, SQL Server, or Oracle Database.
  3. Ask your AI for a dashboard. It gets published, refreshes itself on a schedule, and is shared with a URL.

In Claude Code, step 1 is two commands in your shell:

claude plugin marketplace add https://dashies.ai/marketplace.json
claude plugin install dashies@dashies --scope user

--scope user installs Dashies for every project rather than binding it to the directory you are in, which is the difference between the dashies skill existing in your next repository and not. Run /reload-plugins in Claude Code afterwards, or start a new session.

Install the connector has the equivalent for Codex, Cursor, Claude web and desktop, and any other plugin-capable tool.

Reading these docs with an AI tool

Every page here is also published as its markdown source: take any URL on this site and add .md. llms.txt is the index of all of them, and the changelog is what has changed recently.