Dust

App · 18 actions

Look up your Dust agents, search your data sources, and keep documents and tables in Dust folders up to date.

Actions

ActionWhat it does
Delete documentDelete a document from a folder.
Delete rowDelete one row of a table.
Delete tableDelete a table and all its rows.
Get agentGet one agent with its description, instructions, model and tools.
Get documentGet one document with its text.
Get rowGet one row of a table by its id.
Get tableGet one table with its columns.
List agentsList the Dust agents you can talk to, with their descriptions, models and instructions.
List data sourcesList a space's data sources: folders, websites and connected apps.
List documentsList the documents in a data source, one page at a time, without their text.
List rowsList a table's rows, one page at a time.
List spacesList the spaces your key can see, with their ids and kinds.
List tablesList the tables in a data source, with their columns.
Search agentsFind agents whose name contains some text, ignoring case.
Search data sourceSearch a data source's documents by meaning and get the best matches with their text.
Upsert documentAdd a text document to a folder, or replace the one with the same id, so agents can search it.
Upsert rowsAdd rows to a table.
Upsert tableCreate a table in a folder, or update the one with the same id.

Delete document

Delete a document from a folder. It cannot be undone.

Inputs

Spacespace_idtextRequired
The space that holds the data source. Pick one, or give its id.
Data sourcedata_source_idtextRequired
The data source (a folder, for anything that writes). Pick a space first, then choose from its data sources.
Document IDdocument_idtextRequired
The document's id, from 'List documents' or 'Upsert document'.

Outputs

deletedtrue/false
Always true once deleted
document_idtext
The document deleted
Example output
{
  "deleted": true,
  "document_id": "weekly-2026-10-26"
}

Delete row

Delete one row of a table.

Inputs

Spacespace_idtextRequired
The space that holds the data source. Pick one, or give its id.
Data sourcedata_source_idtextRequired
The data source (a folder, for anything that writes). Pick a space first, then choose from its data sources.
Tabletable_idtextRequired
The table. Pick a data source first, then choose from its tables.
Row IDrow_idtextRequired
The row's id, from 'List rows' or 'Upsert rows'.

Outputs

deletedtrue/false
Always true once deleted
row_idtext
The row deleted
Example output
{
  "deleted": true,
  "row_id": "row01"
}

Delete table

Delete a table and all its rows. It cannot be undone.

Inputs

Spacespace_idtextRequired
The space that holds the data source. Pick one, or give its id.
Data sourcedata_source_idtextRequired
The data source (a folder, for anything that writes). Pick a space first, then choose from its data sources.
Tabletable_idtextRequired
The table. Pick a data source first, then choose from its tables.

Outputs

deletedtrue/false
Always true once deleted
table_idtext
The table deleted
Example output
{
  "deleted": true,
  "table_id": "scores"
}

Get agent

Get one agent with its description, instructions, model and tools.

Inputs

Agentagent_idtextRequired
The Dust agent. Pick one, or give its id from an earlier step.
Detailvarianttext
Summary, or full with tools and data sources.One of: light (Summary (default)), full (Full, with tools and data sources).

Outputs

agentobject
The agent
Example output
{
  "agent": {
    "description": "Answers questions from the company wiki.",
    "id": "xYzAbC1234",
    "instructions": "Answer briefly and cite the page you used.",
    "is_favorite": false,
    "model": "claude-sonnet-4-5",
    "model_provider": "anthropic",
    "name": "Research assistant",
    "picture_url": "https://dust.tt/static/emojis/bg-sky-200/books/1f4da",
    "scope": "visible",
    "status": "active",
    "tools": [
      "search"
    ],
    "version": 3
  }
}

Get document

Get one document with its text.

Inputs

Spacespace_idtextRequired
The space that holds the data source. Pick one, or give its id.
Data sourcedata_source_idtextRequired
The data source (a folder, for anything that writes). Pick a space first, then choose from its data sources.
Document IDdocument_idtextRequired
The document's id, from 'List documents' or 'Upsert document'.

Outputs

documentobject
The document
Example output
{
  "document": {
    "chunk_count": 1,
    "created": 1761000000000,
    "id": "weekly-2026-10-26",
    "mime_type": "application/vnd.dust.folder.document",
    "source_url": null,
    "tags": [
      "notes"
    ],
    "text": "Refunds are accepted for 30 days.",
    "text_size": 120,
    "timestamp": 1761000000000,
    "title": "Weekly notes",
    "token_count": 25
  }
}

Get row

Get one row of a table by its id. A row just added may take about 15 seconds to be found.

Inputs

Spacespace_idtextRequired
The space that holds the data source. Pick one, or give its id.
Data sourcedata_source_idtextRequired
The data source (a folder, for anything that writes). Pick a space first, then choose from its data sources.
Tabletable_idtextRequired
The table. Pick a data source first, then choose from its tables.
Row IDrow_idtextRequired
The row's id, from 'List rows' or 'Upsert rows'.

Outputs

rowobject
The row
Example output
{
  "row": {
    "id": "row01",
    "values": {
      "name": "Ada",
      "score": 3
    }
  }
}

Get table

Get one table with its columns.

Inputs

Spacespace_idtextRequired
The space that holds the data source. Pick one, or give its id.
Data sourcedata_source_idtextRequired
The data source (a folder, for anything that writes). Pick a space first, then choose from its data sources.
Tabletable_idtextRequired
The table. Pick a data source first, then choose from its tables.

Outputs

tableobject
The table
Example output
{
  "table": {
    "columns": [
      {
        "name": "name",
        "type": "text"
      },
      {
        "name": "score",
        "type": "int"
      }
    ],
    "description": "Quiz scores",
    "id": "scores",
    "name": "scores",
    "tags": [],
    "timestamp": 1761000000000,
    "title": "Scores"
  }
}

List agents

List the Dust agents you can talk to, with their descriptions, models and instructions.

Inputs

Which agentsviewtext
Defaults to the agents you can use.One of: list (Agents I can use (default)), all (All shared agents), published (Published agents), global (Dust's built-in agents), favorites (My favorites).

Outputs

agentslist
The agents
countnumber
How many
Example output
{
  "agents": [
    {
      "description": "Answers questions from the company wiki.",
      "id": "xYzAbC1234",
      "instructions": "Answer briefly and cite the page you used.",
      "is_favorite": false,
      "model": "claude-sonnet-4-5",
      "model_provider": "anthropic",
      "name": "Research assistant",
      "picture_url": "https://dust.tt/static/emojis/bg-sky-200/books/1f4da",
      "scope": "visible",
      "status": "active",
      "tools": [
        "search"
      ],
      "version": 3
    }
  ],
  "count": 1
}

List data sources

List a space's data sources: folders, websites and connected apps. Only folders can be written to.

Inputs

Spacespace_idtextRequired
The space that holds the data source. Pick one, or give its id.

Outputs

countnumber
How many
data_sourceslist
The data sources
folderslist
Only the folders, the data sources that can be written to
Example output
{
  "count": 1,
  "data_sources": [
    {
      "connector_provider": null,
      "created_at": 1761000000000,
      "description": "Notes written by Lodol",
      "id": "dts_abc123",
      "is_folder": true,
      "name": "Meeting notes"
    }
  ],
  "folders": [
    {
      "connector_provider": null,
      "created_at": 1761000000000,
      "description": "Notes written by Lodol",
      "id": "dts_abc123",
      "is_folder": true,
      "name": "Meeting notes"
    }
  ]
}

List documents

List the documents in a data source, one page at a time, without their text.

Inputs

Spacespace_idtextRequired
The space that holds the data source. Pick one, or give its id.
Data sourcedata_source_idtextRequired
The data source (a folder, for anything that writes). Pick a space first, then choose from its data sources.
Page sizelimitnumber
How many to return, 1 to 200.From 1 to 200.
Skipoffsetnumber
How many to skip, to get a later page.At least 0.

Outputs

countnumber
How many on this page
documentslist
The documents
totalnumber
How many in all
Example output
{
  "count": 1,
  "documents": [
    {
      "chunk_count": 1,
      "created": 1761000000000,
      "id": "weekly-2026-10-26",
      "mime_type": "application/vnd.dust.folder.document",
      "source_url": null,
      "tags": [
        "notes"
      ],
      "text_size": 120,
      "timestamp": 1761000000000,
      "title": "Weekly notes",
      "token_count": 25
    }
  ],
  "total": 1
}

List rows

List a table's rows, one page at a time. Rows just added may take about 15 seconds to show.

Inputs

Spacespace_idtextRequired
The space that holds the data source. Pick one, or give its id.
Data sourcedata_source_idtextRequired
The data source (a folder, for anything that writes). Pick a space first, then choose from its data sources.
Tabletable_idtextRequired
The table. Pick a data source first, then choose from its tables.
Page sizelimitnumber
How many to return, 1 to 200.From 1 to 200.
Skipoffsetnumber
How many to skip, to get a later page.At least 0.

Outputs

countnumber
How many on this page
rowslist
The rows
totalnumber
How many in all
Example output
{
  "count": 1,
  "rows": [
    {
      "id": "row01",
      "values": {
        "name": "Ada",
        "score": 3
      }
    }
  ],
  "total": 1
}

List spaces

List the spaces your key can see, with their ids and kinds.

Inputs

None.

Outputs

countnumber
How many
spaceslist
The spaces
Example output
{
  "count": 1,
  "spaces": [
    {
      "id": "vlt_abc123",
      "is_restricted": false,
      "kind": "global",
      "name": "Company Data"
    }
  ]
}

List tables

List the tables in a data source, with their columns.

Inputs

Spacespace_idtextRequired
The space that holds the data source. Pick one, or give its id.
Data sourcedata_source_idtextRequired
The data source (a folder, for anything that writes). Pick a space first, then choose from its data sources.

Outputs

countnumber
How many
tableslist
The tables
Example output
{
  "count": 1,
  "tables": [
    {
      "columns": [
        {
          "name": "name",
          "type": "text"
        },
        {
          "name": "score",
          "type": "int"
        }
      ],
      "description": "Quiz scores",
      "id": "scores",
      "name": "scores",
      "tags": [],
      "timestamp": 1761000000000,
      "title": "Scores"
    }
  ]
}

Search agents

Find agents whose name contains some text, ignoring case.

Inputs

Name containsquerytextRequired
Part of the agent's name.

Outputs

agentslist
The matching agents
countnumber
How many
Example output
{
  "agents": [
    {
      "description": "Answers questions from the company wiki.",
      "id": "xYzAbC1234",
      "instructions": "Answer briefly and cite the page you used.",
      "is_favorite": false,
      "model": "claude-sonnet-4-5",
      "model_provider": "anthropic",
      "name": "Research assistant",
      "picture_url": "https://dust.tt/static/emojis/bg-sky-200/books/1f4da",
      "scope": "visible",
      "status": "active",
      "tools": [
        "search"
      ],
      "version": 3
    }
  ],
  "count": 1
}

Search data source

Search a data source's documents by meaning and get the best matches with their text.

Inputs

Spacespace_idtextRequired
The space that holds the data source. Pick one, or give its id.
Data sourcedata_source_idtextRequired
The data source (a folder, for anything that writes). Pick a space first, then choose from its data sources.
Search forquerytextRequired
What to look for, in plain words.
Resultstop_knumber
How many matches to return, 1 to 100. Default 10.From 1 to 100.
Return whole documentsfull_texttrue/false
Off: the matching passages. On: each document's full text.Default: false.
Only documents taggedtagslist
Documents with any of these tags.

Outputs

countnumber
How many
documentslist
The best matches
Example output
{
  "count": 1,
  "documents": [
    {
      "content": "Refunds are accepted for 30 days.",
      "id": "weekly-2026-10-26",
      "score": 0.82,
      "tags": [
        "notes"
      ],
      "timestamp": 1761000000000,
      "title": "Weekly notes"
    }
  ]
}

Upsert document

Add a text document to a folder, or replace the one with the same id, so agents can search it.

Inputs

Spacespace_idtextRequired
The space that holds the data source. Pick one, or give its id.
Data sourcedata_source_idtextRequired
The data source (a folder, for anything that writes). Pick a space first, then choose from its data sources.
Document IDdocument_idtextRequired
Your own id for the document. Using the same id again replaces it.
TexttexttextRequired
The document's text.
Titletitletext
Shown in Dust and in search results.
Tagstagslist
Labels to filter searches by.
Source linksource_urltext
A link back to where the text came from.
Document datetimestampdate and time
When the document was written. Defaults to now.

Outputs

documentobject
The document
Example output
{
  "document": {
    "chunk_count": 1,
    "created": 1761000000000,
    "id": "weekly-2026-10-26",
    "mime_type": "application/vnd.dust.folder.document",
    "source_url": null,
    "tags": [
      "notes"
    ],
    "text_size": 120,
    "timestamp": 1761000000000,
    "title": "Weekly notes",
    "token_count": 25
  }
}

Upsert rows

Add rows to a table. Each row is an object of column values; to replace a row, give its row_id and a value object. Dust makes new rows readable after about 15 seconds.

Inputs

Spacespace_idtextRequired
The space that holds the data source. Pick one, or give its id.
Data sourcedata_source_idtextRequired
The data source (a folder, for anything that writes). Pick a space first, then choose from its data sources.
Tabletable_idtextRequired
The table. Pick a data source first, then choose from its tables.
RowsrowslistRequired
A list of rows, each an object of column values, up to 500. Column names use lowercase letters, digits and underscores. Values are text, numbers or true/false.
Replace all existing rowstruncatetrue/false
On: delete every row already in the table first.Default: false.

Outputs

row_idslist
The id of each row, in order
rows_upsertednumber
How many rows were sent
table_idtext
The table
Example output
{
  "row_ids": [
    "row01",
    "row02"
  ],
  "rows_upserted": 2,
  "table_id": "scores"
}

Upsert table

Create a table in a folder, or update the one with the same id. Its columns come from the rows you add to it.

Inputs

Spacespace_idtextRequired
The space that holds the data source. Pick one, or give its id.
Data sourcedata_source_idtextRequired
The data source (a folder, for anything that writes). Pick a space first, then choose from its data sources.
Table IDtable_idtextRequired
Your own id for the table. Using the same id again updates it.
Namenametext
The table's name for queries. Defaults to the id.
Titletitletext
Shown in Dust. Defaults to the name.
Descriptiondescriptiontext
What the table holds, so agents know when to use it.
Tagstagslist
Labels for the table.

Outputs

tableobject
The table
Example output
{
  "table": {
    "columns": [
      {
        "name": "name",
        "type": "text"
      },
      {
        "name": "score",
        "type": "int"
      }
    ],
    "description": "Quiz scores",
    "id": "scores",
    "name": "scores",
    "tags": [],
    "timestamp": 1761000000000,
    "title": "Scores"
  }
}

On this page