---
title: "Update the workspace AI defaults"
method: PATCH
path: "/inbox/ai-settings/"
tags: ["inbox"]
---

# Update the workspace AI defaults

`PATCH /inbox/ai-settings/`

## Request

- Base URL: `https://api.getoneprofile.ai` (the document declares no server; this is the origin it was published from)
- URL: `https://api.getoneprofile.ai/inbox/ai-settings/`
- Auth: one of:
  - API key in header `X-API-Key`
  - HTTP bearer

Partial update: only the fields you send change. `labelling_enabled` is the auto-label switch: off means new replies stay unlabeled. `agent_replies_enabled` is the workspace switch for replies the agent writes and may send on its own; turning it off stops them all at once. `ai_disclosure_line` is added below every email reply the agent sends on its own. Needs a signed-in person: an API key cannot change these.

## Request body

- AiSettingsUpdateSchema: Partial update: only the fields present in the request are written.
  - `agent_replies_enabled` boolean, nullable: The workspace switch for replies the agent writes and may send on its own. Off, the agent writes no replies and nothing is sent without a person; Draft with AI in the inbox still works. Leave out to keep it as it is.
  - `ai_disclosure_line` string, nullable: A line added below every email reply the agent sends on its own, for rules that require saying a message was written with AI. Never added to a reply a person approved. Up to 300 characters. Send null to stop adding one; leave out to keep it as it is.
  - `default_language` string, nullable
  - `default_reply_mode` 'off' | 'draft_and_queue': How far the AI reply layer may go on this sequence. OFF is the default everywhere: a workspace opts in. DRAFT_AND_QUEUE is as far as it goes: every draft waits in Needs approval for a person, whatever its confidence. There is deliberately no mode past it. A self-sending auto-pilot shipped once and was removed under the ruling that a send cannot be taken back, so nothing may send with nobody present; rows that carried it were moved to DRAFT_AND_QUEUE by the ``retire_auto_send_reply_mode`` release task. A SENT draft with no approver is therefore always history from before that ruling.
  - `default_tone` 'professional' | 'friendly' | 'direct' | 'casual': How a generated reply should read.
  - `labelling_enabled` boolean, nullable

## Response `200`

Successful Response

- AiSettingsReadSchema: The workspace's AI defaults. The auto-label switch lives here.
  - `agent_replies_enabled` boolean, required: The workspace switch for replies the agent writes and may send on its own. Off, the agent writes no replies and nothing is sent without a person; Draft with AI in the inbox still works.
  - `ai_disclosure_line` string, nullable, required: A line added below every email reply the agent sends on its own, for rules that require saying a message was written with AI. Never added to a reply a person approved. Null adds nothing.
  - `default_language` string, nullable, required
  - `default_reply_mode` 'off' | 'draft_and_queue', required: How far the AI reply layer may go on this sequence. OFF is the default everywhere: a workspace opts in. DRAFT_AND_QUEUE is as far as it goes: every draft waits in Needs approval for a person, whatever its confidence. There is deliberately no mode past it. A self-sending auto-pilot shipped once and was removed under the ruling that a send cannot be taken back, so nothing may send with nobody present; rows that carried it were moved to DRAFT_AND_QUEUE by the ``retire_auto_send_reply_mode`` release task. A SENT draft with no approver is therefore always history from before that ruling.
  - `default_tone` 'professional' | 'friendly' | 'direct' | 'casual', required: How a generated reply should read.
  - `labelling_enabled` boolean, required

## Other responses

- `401`: Unauthorized
- `403`: Forbidden
- `422`: Invalid request made to the API.
- `500`: Internal server error.
- `502`: Bad gateway error.
- `503`: Service unavailable.

---

[API](https://skmtc.dev/getoneprofile/apis/api-reference-oneprofile.md) · [All operations](https://skmtc.dev/getoneprofile/apis/api-reference-oneprofile/llms.txt) · [OpenAPI document](https://skmtc.dev/getoneprofile/apis/api-reference-oneprofile/revisions/4a6bd71e3f02?raw)