Skip to content

Use case

Share the dashboard with its filters still working.

Share a dashboard people can filter and sort in their own browser. Each week’s numbers become the next version at the same link.

Who it’s for: Analysts, operations leads, founders of small businesses

artifact.guru/harbor-kiln/autumn-tradingPrivateFull screen
Harbor Kiln autumn trading. The sales dashboard the studio checks each week.A sample. The company and its numbers are made up.
  1. Switch to 90 days and compare with the previous period.
  2. Untick Market stalls to take them out of every number.
  3. Click a bestseller to light up its line in the chart.

People ask the next question themselves

A screenshot answers the question you thought of. With working filters, each reader can answer their own, like how wholesale did over the last 90 days. When every number follows the filters, nobody has to ask you to re-cut the data.

An agent built the Harbor Kiln dashboard above from a sales export, and at its artifact.guru link the controls still work. Change the date range or the channel, and every chart and total updates.

A weekly dashboard in four steps

  1. Start from approved data

    Give the agent the export and say what each column means. Ask it to embed the data in one HTML page, with the date of the export on it.

  2. Check the totals

    Ask the agent for the expected totals for two or three filters, and compare them with the page before you share.

  3. Publish privately

    In a team workspace, Private already means the whole team. You can also invite an investor or an accountant to just this artifact by email.

  4. Refresh by publishing again

    Next week: “replace the data in the autumn trading dashboard with this export”. The link stays the same, and last week’s version stays in the history.

What makes a dashboard worth opening

DoBecause
Put the four numbers that matter firstReaders who stop there still get the point
Show the change against the last periodA number without a comparison means little
Let one filter drive everythingTotals that disagree with the chart destroy trust
Say when the data is fromReaders need to know how fresh it is
Add one thing to doA reorder or follow-up list gives people a reason to come back

Limits

  • Each version is a snapshot of the data it was published with. It doesn’t connect to your database or BI tool.
  • Filters and sorting run in the reader’s browser. Nothing they click is sent anywhere.
  • Pages can load chart libraries from a public CDN, or draw charts themselves as the Harbor Kiln dashboard does.

Prompt

Make your own

Have these ready, then paste the prompt into your agent:

  • A CSV export with clear column names
  • The four numbers that matter
  • The filters people need
  • The export date
Prompt
Use the attached CSV to build one self-contained HTML dashboard. Keep every
row. Lead with the four numbers I list, each with the change against the
previous period. Add a date range and the filters I list; every chart, table
and total must follow them. Add hover values on charts and a sortable table.
Show the export date.

Test the filters together and tell me the totals for two of them. Check 390px
and 1440px wide. Don’t add a live data connection.

Publish it privately to artifact.guru and give me the link.

Common questions

Can it pull live data?

Not from your own systems. The page shows the data it was published with; publish a new version to update it, and the link stays the same.

Who can see the numbers?

New artifacts are private to your workspace. Invite people by email, or use a secret code for anyone outside it.

Read next

More use cases

Try it with your own file

Copy the prompt above, add your file and publish.