Skip to content

Spreadsheet · reads dataset

Data table

Uploaded rows (elastic data).

A grid you can type into, with formulas.

Deliberately generic. The moment it has a meaning, it should be a different module.
RefField AField BValue
R-001OberkampfQ31,204
R-002OberkampfQ41,488
R-003Market stallQ3612
R-004Market stallQ4705

What it does

Behaviours, not fields. Choosing between two modules is choosing between these.

The escape hatch: genuinely tabular data with no natural module, held without forcing a shape on it.

Sortable, filterable and editable in place, because this is data being worked with rather than presented.

Deliberately generic — the moment it has a meaning it should become a different module.

How it works

  1. 1

    A dataset is uploaded or synced and rendered as it arrived, with no interpretation applied.

  2. 2

    Columns are sortable and filterable in place, because this is data being worked with.

  3. 3

    Edits write back to the dataset, so it is a working surface rather than a view.

  4. 4

    When a shape emerges, the right move is to make it a real module rather than keep it here.

Best for

Budgets, quantities, anything people would otherwise export to Excel.

Not the right choice for

Records with long text — the grid fights you.

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.

FieldTypeFilled from
RefrequiredtextA row identifier, generated if the data has none.
Field AtextWhatever the first column happens to be. No meaning is assumed.
Field BtextAnd the second. The escape hatch does not interpret.
ValuetextA numeric column where one exists, so sorting behaves sensibly.

What it does not do

A module chosen for something it cannot do costs more than one that was never offered.

  • No relationships, no validation, no types. Every value is a string until something else says otherwise.
  • Large datasets render the first hundred rows; this is not a database client.
  • Nothing here feeds the agent well, because the agent has no idea what the columns mean.
  • Deliberately generic — the moment it has a meaning it should be a different module.

Before it works

What you have to provide, if anything.

  • Upload a CSV or JSON. Nothing else is required, which is the point.
  • Expect to replace it. This is where data lives before somebody decides what it is.

In practice

A team importing a spreadsheet that already worked.

Just put this CSV somewhere we can filter it.
What was said to the agent

What the agent built

A data table with the columns as they came, no interpretation applied.

What changed

Two of the columns turned out to be a supplier list. They became a Suppliers module a week later, and the rest stayed here.

Questions

What data does the Data table page use?

It reads dataset records the agent has collected. Uploaded rows (elastic data). 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 spreadsheet the wrong choice?

Records with long text — the grid fights you. It is best for: budgets, quantities, anything people would otherwise export to Excel.

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.

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

Agents

More

👤
Profile
FAQ