Dashboards

Contextflo dashboards are live views of your data. You describe what you want in chat, and Claude (or ChatGPT) builds a dashboard where each chart is backed by a SQL query that runs against your warehouse on every load. Nothing is cached or stored on Contextflo's side.

Dashboards vs Claude artifacts

When you ask Claude for a chart, it generates an artifact: a self-contained visualization built from the data in that conversation. Because it has no connection to the database, it can't refresh itself.

A Contextflo dashboard is different. Each chart is backed by a live SQL query, so every time someone opens the dashboard the data is fresh. Claude handles the visualization; Contextflo handles the data connection and access control.

Creating a dashboard

Describe what you want in your LLM client. For example:

"Create a dashboard showing weekly revenue by region with a filter for product line."

Claude uses Contextflo to build the dashboard definition — charts, tables, KPI cards, and filters — all wired to live SQL against your warehouse.

To iterate, just say what to change: "make that a stacked bar chart," "add a date filter," "group by month instead of week." Claude updates the dashboard. You never open a chart library.

Chart types

Dashboards support the common chart types:

• Line, bar, pie, doughnut, and radar charts
• KPI cards
• Data tables

Filters

Dashboards support shared filters — dropdowns or pills that apply across every chart. Filter by date range, region, product line, or any dimension in your data. Claude sets these up from your schema.

Preview, publish, share

Every dashboard starts in preview. Tweak the layout, verify the numbers, and adjust filters. When you're happy, publish it and your team gets a live link.

Take the verify step seriously the first time. A dashboard is opened by people who weren't in the conversation where it was built and have no way to know what assumptions went into it, so confirm the numbers before publishing.

Branding

You can instruct the LLM to use your brand colors on every dashboard. Add the instruction once (for example in your organization context) and new visualizations will match your company's look with no design work.

Your data stays in your warehouse

Every chart queries your warehouse live. Nothing is cached or stored on Contextflo, so each time someone opens a dashboard the queries run fresh. Dashboards work with Postgres, BigQuery, Snowflake, Redshift, Databricks, and ClickHouse.

Where dashboards fit

Dashboards handle the questions you want to look at on demand. Reports handle recurring questions on a schedule. For a full walkthrough with examples, see Creating dashboards with AI.

Next Steps

• Automate recurring reports
• New User Guide (Claude)