Skip to Content
AI

Autonomous replies

How Ken answers replies on its own.

AI2 endpointsKen-Version: 2026-11-02AuthenticationWorkspacesErrors
MarkdownOpenAPI

Headers

The endpoints on this page take these headers. Each endpoint's curl shows the ones it sends.

NameInTypeRequiredDescription
Ken-Versionheaderstring, one of: 2026-11-02, 1.1optionalThe API version, a date in YYYY-MM-DD form. 1.1 is another name for the first dated version. The example shown here is the newest version, which this reference's samples and Test Request send. Leave it out to use your API key's pinned version. Keys created in the Kenso app are pinned to the newest version; keys minted by the CLI login are not. A key with no pinned version and no header gets the legacy shape where the path has one, and 404 where the path exists only in this version. A date that is not a version answers 400 unsupported_version; any other value that is not a version is treated as legacy.
X-Ken-Workspace-Idheaderinteger (int64)optionalThe id of the workspace to act in. Leave it out when your API key reaches only one workspace. When the key reaches more than one, a request without this header answers 400 workspace_required. A workspace you are not a member of answers 404 not_found.

Get the autonomous reply settings

GET/v1/autonomous-reply-settingsautonomous-reply-settings.get
Permission
Any workspace member except a Network member
Rate limit
12,000 requests a minute per API key

Try it on developer.ken.so

Returns the workspace's reply settings. A workspace that never saved them gets the defaults: replies off, draft mode, no extra instructions, and no createdAt or updatedAt.

Open to any workspace member.

Request
curl -X GET "https://api.ken.so/v1/autonomous-reply-settings" \
  -H "Authorization: Bearer $KENSO_API_KEY" \
  -H "Ken-Version: 2026-11-02" \
  -H "X-Ken-Workspace-Id: $KENSO_WORKSPACE_ID"

Response 200

data is a AutonomousReplySettings.

Show the 6 response fields and an example

The fields and an example are also on this endpoint's Markdown page.

Update the autonomous reply settings

PATCH/v1/autonomous-reply-settingsautonomous-reply-settings.update
Permission
The workspace_settings permission
Rate limit
4,800 requests a minute per API key

Try it on developer.ken.so

Changes the fields you send and keeps the rest. Send a JSON object with any of these fields:

  • defaultEnabled (boolean): turns Ken's replies on or off for the workspace.
  • linkedInEnabled (boolean): lets Ken reply on LinkedIn too while defaultEnabled is true. On LinkedIn Ken writes drafts only, whatever mode says.
  • mode: draft, autonomous or approve_risky. approve_risky needs the reply_agent_approve_risky feature on the workspace.
  • extraInstructions (string, at most 4,000 characters): instructions Ken follows when it writes replies. Kenso trims the text. null or a blank string clears them.

When you turn replies off or set mode to draft, Kenso turns the replies Ken is holding to send into drafts for a member to review. An empty object changes nothing and returns the settings.

Errors:

  • 400 validation_failed: the body is not a JSON object, a field is unknown or has the wrong type, extraInstructions is longer than 4,000 characters, or mode is not a known mode. A workspace without the reply_agent_approve_risky feature gets this error for approve_risky too.

Requires the workspace_settings permission.

Request body

application/json, optional: object.

Request
curl -X PATCH "https://api.ken.so/v1/autonomous-reply-settings" \
  -H "Authorization: Bearer $KENSO_API_KEY" \
  -H "Ken-Version: 2026-11-02" \
  -H "X-Ken-Workspace-Id: $KENSO_WORKSPACE_ID" \
  -H "Content-Type: application/json" \
  -d '{}'

Response 200

data is a AutonomousReplySettings.

Show the 6 response fields and an example

The fields and an example are also on this endpoint's Markdown page.


On this page