Agent work settings
Decide who runs each kind of AI work that can wait: Kenso's AI (kenso_ai, the default) or your own coding agent (my_agent), which picks the work up with kenso work run.
Headers
The endpoints on this page take these headers. Each endpoint's curl shows the ones it sends.
| Name | In | Type | Required | Description |
|---|---|---|---|---|
Ken-Version | header | string, one of: 2026-11-02, 1.1 | optional | The 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-Id | header | integer (int64) | optional | The 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 agent work settings
/v1/agent-work-settingsagent-work-settings.get- Permission
- Any workspace member except a Network member
- Rate limit
- 12,000 requests a minute per API key
agent_work feature on your workspace. Until it is on, calls answer 404.Returns every kind with its executor, always all eight in hand-out order. A kind the workspace never saved is kenso_ai with updatedAt null. available is false for a kind Kenso cannot hand to an agent yet: it stays on kenso_ai.
Errors:
404 not_found: the workspace does not have theagent_workfeature.
Open to any workspace member except a Client seat.
curl -X GET "https://api.ken.so/v1/agent-work-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 AgentWorkSettings.
Show the 1 response field and an example
The fields and an example are also on this endpoint's Markdown page.
Update the agent work settings
/v1/agent-work-settingsagent-work-settings.update- Permission
- The
workspace_settingspermission - Rate limit
- 4,800 requests a minute per API key
agent_work feature on your workspace. Until it is on, calls answer 404.Sets the executor of each kind you name and leaves the others as they are. Body: { "settings": [ { "kind": "personalization", "executor": "my_agent" } ] }. Returns every kind after the change, in the same shape as the GET. With my_agent, the kind's work waits for the workspace's agent: Kenso's AI does not run it, and the full prompt and the lead's facts go to that agent.
Errors:
400 validation_failed:settingsis missing or empty, akindorexecutoris not a known value, or a kind is named twice. Each problem is onedetails[]entry, such assettings[1].kind. Nothing is saved. A kind set tomy_agentwhile itsavailableis false is a detail with codekind_not_available.404 not_found: the workspace does not have theagent_workfeature.
Requires the workspace_settings permission.
Request body
application/json, optional.
| Field | Type | Required | Description |
|---|---|---|---|
settings | array of UpdateAgentWorkSettingEntry | optional | One entry per kind to change, each kind at most once. At least one entry. |
curl -X PATCH "https://api.ken.so/v1/agent-work-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 '{
"settings": [
{
"kind": "meeting_brief",
"executor": "kenso_ai"
}
]
}'Response 200
data is a AgentWorkSettings.
Show the 1 response field and an example
The fields and an example are also on this endpoint's Markdown page.
More in AI:AI runsAI linesAI line holdsAutonomous repliesAgent permissionsAgent workAgent sandbox connectionsAgent sandbox runsAgent sandbox automatic runsAI feedbackAll resources