Chart · reads dataset
Charts
Visualize any dataset.
One measure over time or across a category.
What it does
Behaviours, not fields. Choosing between two modules is choosing between these.
A chart you publish or hand over, so it carries a title and a source rather than living inside a monitoring view.
A source on every series, because a chart without one gets challenged and cannot answer.
One comparison per chart — the discipline that keeps it readable.
How it works
- 1
A dataset is grouped by label and summed or counted into a series.
- 2
The source is recorded per series and rendered with the chart rather than in a footnote.
- 3
The chart is a deliverable — it carries a title and a source because it will be seen away from here.
- 4
Changing the underlying data redraws it; the source line stays.
Best for
Trends and comparisons.
Not the right choice for
Exact values — pair it with a table.
What a row holds
Every field, and what the agent listens for to fill it — which is the difference between a page you type into and one that fills itself.
| Field | Type | Filled from |
|---|---|---|
| Seriesrequired | text | What is being compared. One chart, one comparison. |
| Labelrequired | text | The category on the axis. |
| Valuerequired | text | The magnitude. Parsed for the bar, shown as written. |
| Sourcerequired | text | Where the number came from. Required, because a chart without one cannot answer a challenge. |
What it does not do
A module chosen for something it cannot do costs more than one that was never offered.
- One series per chart. Two makes it a metrics dashboard.
- No axis configuration, log scales or dual axes. It is a bar chart with opinions.
- Values are parsed leniently, so a mixed-format column produces a plausible but wrong bar.
- No export. Screenshot or link to the page.
Before it works
What you have to provide, if anything.
- Needs a dataset with a label column and something numeric.
- Name the source honestly. It is the field that makes the chart usable in an argument.
In practice
A founder preparing a pitch.
“Revenue by channel for September, as a chart.”
What the agent built
Four series with values and the source recorded against each.
What changed
The trade channel at 3,120 against the shop at 14,200 reframed the pitch. The source line meant the number was never questioned.
Better with
These do a different job on the same data. An agent can have all of them.
Someone outside the day-to-day needs the picture periodically, with interpretation rather than raw figures.
Numbers move over time and the movement matters more than any single reading.
The data is genuinely tabular, arbitrary, and being worked with directly rather than presented.
Questions
What data does the Charts page use?
It reads dataset records the agent has collected. Visualize any dataset. Nothing has to be imported first — the page appears once there is something to show.
Do I have to build or configure it?
No. You describe what you need in a sentence and the agent chooses the view and fills it. Custom pages exist for the cases no built-in view covers, and those are reviewed before they go live.
When is a chart the wrong choice?
Exact values — pair it with a table. It is best for: trends and comparisons.
Does it stay up to date?
Yes. The page is a view over the data rather than a copy of it, so anything the agent learns afterwards shows up without a rebuild or a re-import.
More in Analytics & data
Orders today
23
20
Unanswered messages
4
0
Stock alerts
2
0
Overdue invoices
1
0
KPI page
Headline numbers.
Metrics dashboard
Charts of trends.
Monthly performance
August · Sent 2 Sep · Maison Lauret
Quarterly review
Q2 · Sent 8 Jul · Board
Monthly performance
September · Draft · —
Stock and wastage
August · Sent 4 Sep · Internal
Reports
Generated summaries.
Data table
Uploaded rows (elastic data).
Ask for it in a sentence
You do not configure this page. You tell your agent what you need and it builds it from what it has already collected.
Build your agent free