- Rows
- 1,500
- Version
- v1
- Refreshed
- 12 d ago
8 columns
every change makes a new one
uploaded by hand
Import report
Nothing is changed silently. Fixes create a new version.
- "revenue" looks numeric but is stored as text (1500 of 1500 values, e.g. "$712.80", "$99.00"). Convert it to a number by removing currency symbols and thousands separators?
Cleaning rules
Rules a person approved. They run on every refresh and sync, and each change makes a new version.
AI suggestions are off for this workspace. Turning them on sends the column profile and 50 sample rows to Mistral (EU) when someone asks for suggestions. Workspace settings
Columns
Agents read what each column means and its unit. Change a type and the dataset rebuilds as a new version.| Column | Meaning | Type |
|---|---|---|
order_idunique on every row | Order identifier, unique per row iddrafted Edit | |
order_date1 Jan 2026 to 30 Sept 2026 | Order date datedrafted Edit | |
region3 values | Region, 3 values such as APAC, North Amer, EMEA dimensiondrafted Edit | |
country10 values | Country, 10 values such as Japan, Spain, Australia dimensiondrafted Edit | |
channel3 values | Channel, 3 values such as Partner, Online, Sales dimensiondrafted Edit | |
product5 values | Product, 5 values such as Analytics , Starter Pl, Team Plan dimensiondrafted Edit | |
units1 to 12 · total 8,074 | Units metricunitsadds updrafted Edit | |
revenue142 values, top 5 shown | Revenue, 142 values such as $712.80, $99.00, $420.75 dimensiondrafted Edit |
Sample rows
The first 10 rows, exactly as agents receive them.
| order_id | order_date | region | country | channel | product | units | revenue |
|---|---|---|---|---|---|---|---|
| SO-10001 | 2026-02-11 | North America | United States | Partner | Team Plan | 8 | $712.80 |
| SO-10002 | 2026-06-19 | APAC | Japan | Online | Team Plan | 1 | $99.00 |
| SO-10003 | 2026-06-04 | EMEA | France | Online | Team Plan | 5 | $420.75 |
| SO-10004 | 2026-09-15 | EMEA | Spain | Online | Onboarding Package | 1 | $382.50 |
| SO-10005 | 2026-08-18 | EMEA | Germany | Sales | Analytics Add-on | 4 | $176.40 |
| SO-10006 | 2026-07-22 | EMEA | Germany | Sales | Starter Plan | 5 | $130.50 |
| SO-10007 | 2026-01-09 | APAC | Singapore | Online | Onboarding Package | 1 | $450.00 |
| SO-10008 | 2026-02-18 | APAC | Singapore | Partner | Support Hours | 4 | $480.00 |
| SO-10009 | 2026-05-07 | APAC | Japan | Partner | Onboarding Package | 1 | $450.00 |
| SO-10010 | 2026-04-12 | APAC | Australia | Online | Analytics Add-on | 9 | $374.85 |
Who can see this dataset
Everyone in this workspace sees it, in the app and through their agents.
Agent activity
Open in audit13:23
Units: sum of units, by region, highest firstsam via ChatGPT · v1 · aggregate · 3 rows · 128 ms
same as Claude CodeCheck
13:21
Distinct values of regionsam via ChatGPT · v1 · distinct_values · 3 values · 160 ms
13:19
Units: sum of units, by region, highest firstsam via ChatGPT · v1 · aggregate · 3 rows · 192 ms
same as Claude CodeCheck
Wed 13:25
Units: sum of units, by region, highest firstsam via ChatGPT · v1 · aggregate · 3 rows · 112 ms
same as Claude CodeCheck
Wed 13:23
Distinct values of regionsam via ChatGPT · v1 · distinct_values · 3 values · 144 ms
Wed 13:21
Units: sum of units, by region, highest firstsam via ChatGPT · v1 · aggregate · 3 rows · 176 ms
same as Claude CodeCheck
Tue 15:51
Describe the datasetnorthwind via Claude Code · describe_dataset · 273 ms
Tue 15:49
Units: sum of units, by region, highest firstnorthwind via Claude Code · v1 · aggregate · 3 rows · 126 ms
same as ChatGPTCheck
Tue 13:25
Units: sum of units, by region, highest firstsam via ChatGPT · v1 · aggregate · 3 rows · 96 ms
same as Claude CodeCheck
Use it
Same engine, same numbers, whichever door you use.
- Add datatomcp from the Claude, ChatGPT or Cursor directory, or add this URL as a custom connector in any agent (Claude Code, n8n…). One connector covers all your datasets.
https://app.datatomcp.com/mcp - Sign in when asked and allow access. Then ask about sample_sales in plain language.
Full client-by-client setup on Connect.
curl https://app.datatomcp.com/v1/datasets/ds_uDso5S0fRltM/query \
-H "Authorization: Bearer $DATATOMCP_KEY" \
-H "Content-Type: application/json" \
-d '{"limit": 10}'Create an API key in Account. Filters, metrics and paging are in the dataset docs.
Use the datatomcp dataset "sample_sales" (id ds_uDso5S0fRltM) to answer questions about this data.
Call describe_dataset first to read the columns and today's date.
Before filtering on a text column such as region, call distinct_values to get the exact spelling.
Resolve relative dates ("last month") against the server date, using order_date.
Use aggregate for totals, counts and averages instead of reading rows. Never sum a column marked summable: false (prices, rates). Quote numbers exactly as returned with the unit from meta.units, mention the dataset version, and pass on meta.warnings that affect the number.Paste this into your agent's instructions so it queries this dataset the right way.