Skip to main content
Collections list
A collection is the unit you work with in the foundation’s structured-data layer, the tabular counterpart to a knowledge base in the knowledge layer. The Collections page lists all your datasets. From here you create new collections, search existing ones, and open a collection to work with its data.

​
The Dashboard

The Dashboard gives you a quick health check before diving into a specific collection:
  • Collections: how many collections you own or have access to
  • Total Rows: the combined number of records across your collections
Below the metrics, the Recent Collections grid shows your six most recently used collections. Click View All to open the full list.

​
Viewing Collections

Each collection appears as a card showing:
  • Its name and description
  • The number of rows and columns
  • The agents linked to it, when applicable
Use the search bar to filter the loaded collections by name or description as you type. When you have many collections, the list is paginated: use the ◀ ▶ controls and the “X-Y of total” counter at the bottom to move between pages.

​
Creating a Collection

A collection always has a schema (at least one typed column), so there is no truly empty collection. You start from one of three paths, each ending on an editable schema you confirm before creating.
1

Open the creation form

Click New Collection (from the Dashboard) or Create (from the Collections page).
2

Choose how to start

  • Describe it with AI: type what you want to track; AI proposes the columns
  • Start from a template: pick a ready-made structure (Sales CRM, Tasks, Products, Feedback, Leads, Logs)
  • Import a CSV: upload a file and detect the schema automatically (see Importing Data)
A discreet Advanced: define columns manually option lets you build the schema from scratch.
3

Review the schema

Name the collection, then review the columns in the editor: rename them, change types, mark which are required, and (optionally) flag columns to index or make unique. A live preview shows the resulting table.
4

Create

Click Create. Your collection appears in the list, ready to use. For CSV imports, rows are loaded in the background with a progress bar.
Start from a CSV whenever you can: the schema (column names and types) is inferred from your actual data, which is faster and less error-prone than defining it by hand.

​
Opening a Collection

Click any collection card to open its detail page. The header shows the name, description, and size (X rows • Y columns), and the content is organized in tabs:

​
Deleting

​
Deleting a Collection

Deletion lives on the collection’s Settings tab (the collection cards no longer have a delete action).
1

Open the collection's Settings tab

Open the collection, then go to the Settings tab and find the Danger zone.
2

Confirm by typing

Click Delete collection, then type the confirmation word (delete) in the dialog and confirm. This prevents accidental deletions.
Deleting a collection permanently removes the collection and all its records. Agents linked to it lose access to the data. This cannot be undone.

​
Deleting Records

To remove individual rows without deleting the collection, select them in the Data tab and use the Delete action; see Working with Data.

​
Settings

Collection Settings tab
Each collection’s Settings tab gathers everything about that collection:
  • Collection name: rename the collection
  • Export data: download all rows as CSV or JSON
  • Endpoints: the per-collection MCP URL (to bind an agent to this collection) and REST endpoint, each copyable
  • Indexes & uniques: for each column, toggle Indexed (faster filters and sorts) or Unique (enforce no duplicates), then Apply
  • Danger zone: delete the collection (with typed confirmation)
The global Settings page (sidebar) shows usage statistics across all your collections.

​
Best Practices

Keep each collection focused on a single kind of record: deals, contacts, tickets. Mixed datasets are harder to query and produce confusing aggregations.
The description is visible to agents when they discover your collections. “Q3 2026 sales pipeline, one row per deal, amounts in EUR” tells an agent exactly how to use the data.
Aggregations group by exact values. “In Progress”, “in progress”, and “In-Progress” become three different groups, so normalize your categories before importing.
Old collections still appear in agent tool listings. Deleting stale datasets keeps agent behavior predictable.

​
Next Steps

Importing Data

Upload a CSV with automatic schema detection

Working with Data

Browse, sort, and manage records