Create an interactive management dashboard that pulls your key metrics directly from your data sources and keeps itself up to date.
This guide works for any kind of business and any metrics. The principle is always the same: connect a data source, let Claude read and verify it, build a Live Artifact (a persistent, interactive dashboard) and, if you want, set up automatic refreshes.
As an example we use Google Sheets via the Google Drive connector, but the exact same approach works with any other connected source.
What you will need
- a paid Claude plan
- Claude Desktop
- Claude Cowork
- at least one connector to your data (Google Drive in this example)
- a data source containing your metrics (a Google Sheets file in this example)
The Google Drive connector reads not only Google Docs, but also Google Sheets, Slides, PDFs, and Office files. If your data lives in another system (a CRM, e‑commerce platform, accounting tool, or project tracker), look for the matching connector — the same principle applies.
1. Prepare your data source
Start with one clear data source.
For example, a table:
| Month | Revenue | Expenses | Profit |
|---|---|---|---|
| January | 42,500 | 31,200 | 11,300 |
| February | 47,800 | 33,100 | 14,700 |
| March | 51,400 | 34,900 | 16,500 |
The same example table also carries an Orders column and a New customers column.
Choose metrics that fit your business — sales, projects, customer support, inventory, or anything else. The clearer your column names and the more consistent the structure, the more reliably Claude will understand the data.
2. Connect your source
In Claude, open:
Customize → Connectors
Choose the connector you need (Google Drive in this example), sign in, and grant access only to the files or data you want to use.
Claude will then be able to access your data directly through the connector, so you will not need to upload the file manually every time. Claude only sees the sources you connect, and you can disconnect any of them at any time.
3. Open Claude Desktop and Cowork
For this scenario, we recommend using Claude Desktop → Cowork rather than a standard Claude chat.
This lets you create a Live Artifact — a persistent, interactive dashboard that uses your connectors and refreshes with the latest data.
4. Ask Claude to verify the data first
Do not build the dashboard immediately. First, ask Claude to check what it can actually see in the data source. This is the most important step — it prevents wrong numbers.
Sign in to read and copy this prompt.
Sign inOnly after you have verified what Claude actually read should you create a visualisation.
5. If the source is large
Large files or tables may not be read in full through a connector. So if there is a lot of data, do not assume Claude has analysed the entire file simply because it found it.
Check:
- how many rows exist in the original
- how many rows Claude actually analysed
- whether totals and date ranges match
If Claude cannot access the full dataset, a more reliable path is:
Source → download as CSV/XLSX → Claude Cowork → Python analysis.
6. Process a large file with Python
Download the full data as CSV or XLSX and save it in a folder that Claude Cowork is allowed to access.
Then use a prompt like this:
Sign in to read and copy this prompt.
Sign inThis ensures the full file is analysed rather than only a partial extract.
7. Build the Live Artifact
Once the data is verified, ask Claude to build the dashboard. Be specific — which metrics, which time period, which layout you want.
Sign in to read and copy this prompt.
Sign in8. Refine by conversation
The dashboard is not a one-off. You refine it by simply chatting, and you see the result immediately: “add a section X”, “show this metric differently”, “fix calculation Y”. After each change, it is worth asking Claude to check its work: “verify the numbers are correct and the dashboard opens without errors”.
9. How the dashboard stays up to date
There are two main options.
A. Refresh when you open it
If the Live Artifact uses a connector, opening the dashboard can trigger a fresh request to the connected source and show the latest data. This is the simplest option.
B. Add scheduled automation
If you want Claude to do recurring work — for example, check the metrics every morning or every Monday and refresh the dashboard — add a Scheduled Task. You can choose the cadence freely (hourly, several times a day, weekly).
Good to know:
- Scheduled tasks run only while Claude Desktop is open; if the app is closed when a task is due, it runs the next time you open it.
- Click “Run now” once on the task — this pre-approves the tools it needs so future runs do not pause on permission prompts.
- If a task needs a local file or a local application, it must run locally through Claude Desktop.
10. Example scheduled prompt
Sign in to read and copy this prompt.
Sign inHow the full workflow works
- Connectorpull real data from the connected source.
- Verifycheck what Claude actually read.
- Python fallbackif the dataset is too large, download the full file and process it with Python.
- Live Artifactturn the data into a management dashboard.
- Iteraterefine by conversation.
- Scheduledadd recurring analysis or an update workflow.
