> ## Documentation Index
> Fetch the complete documentation index at: https://docs.open.cx/llms.txt
> Use this file to discover all available pages before exploring further.

# Handoff Settings

> This page is a complete reference for every option on the Settings → Handoff page in your dashboard.

This page is a complete reference for every option on the **Settings → Handoff** page in your dashboard. If you are new to handoff, start with the [Human Handoff overview](/handoff/introduction).

## AI to human transfer behavior

Controls when the AI decides to hand off a conversation. You can configure this in one of two ways:

* **Preset levels** — four opinionated presets from "AI Only" to "AI-First".
* **Advanced mode** — individual toggles for each handoff trigger.

Only one of the two is active at a time. Switching between them is a UI toggle at the bottom of the section.

### Preset levels

<AccordionGroup>
  <Accordion title="Level 0 — AI Only" icon="robot">
    The AI handles all conversations without ever transferring to a human.

    * No handoff to human agents.
    * Customer requests for a human are declined.
    * Useful for fully-automated deflection channels where no human team is available.
  </Accordion>

  <Accordion title="Level 1 — Quick Handoff (default)" icon="bolt">
    The AI hands off quickly on any customer frustration or explicit request.

    * Hands off on any sign of frustration.
    * Transfers if the conversation isn't making progress.
    * Immediate transfer when the customer asks for a human.

    This is the default when you first enable handoff.
  </Accordion>

  <Accordion title="Level 2 — Balanced Mode" icon="scale-balanced">
    The AI attempts to resolve the issue, but respects direct requests for a human.

    * Tries to understand the problem first.
    * Transfers when the customer explicitly asks for a human.
    * Gathers basic information before the handoff to save the agent's time.
  </Accordion>

  <Accordion title="Level 3 — AI-First Mode" icon="bullseye">
    The AI requires a complete problem statement before any handoff.

    * Requires the customer to describe the problem clearly.
    * Attempts multiple solutions before escalating.
    * Transfers only after a thorough problem-solving attempt.

    Use this when your human team is a scarce resource and you want the AI to exhaust all options first.
  </Accordion>
</AccordionGroup>

<Tip>
  **Which level should you pick?** If you have a responsive human team and care most about customer experience, use **Quick Handoff**. If your team is small or you want the AI to deflect as much volume as possible, use **Balanced** or **AI-First**. You can change levels at any time — the setting takes effect immediately for new messages.
</Tip>

### Advanced mode

Advanced mode replaces the preset level with individual toggles. Use it when the presets don't fit your policy.

| Setting                                   | What it does                                                                            |
| ----------------------------------------- | --------------------------------------------------------------------------------------- |
| **Enable Handoff**                        | Master switch. When off, the AI never transfers to a human regardless of other toggles. |
| **Handoff on Frustration**                | Transfer when the AI detects customer frustration.                                      |
| **Handoff on Unproductive Conversations** | Transfer when the conversation stops making progress.                                   |
| **Handoff on Human Request**              | Transfer when the customer explicitly asks for a human agent.                           |
| **Require Problem Statement**             | Before transferring, the AI must extract a clear problem statement from the customer.   |

<Warning>
  Disabling **Handoff on Human Request** means the AI will ignore messages like "let me talk to a human". This is almost never what you want — customers expect that option to work, and blocking it is a common source of CSAT complaints. Only turn it off if you have a specific business reason and a separate escalation path.
</Warning>

## Within office hours

Customize the AI's message when it hands off during your configured office hours. The text you provide here is used as instructions for the AI — the AI will phrase it naturally in the conversation's language.

Example:

> I'll transfer you to our support team now. They'll be with you shortly.

Leave blank to use the AI's default wording.

## Outside office hours

Two settings control behavior when a handoff is needed outside office hours.

### Allow handoff outside office hours

<ParamField path="handoff_outside_office_hours" type="boolean" default="false">
  When enabled, conversations can still be transferred to human agents outside office hours. Agents will see the handoff when they're next online.
</ParamField>

When disabled, the AI will not transfer outside of office hours — even on explicit request.

### Outside hours AI instructions

Custom instructions used when the AI needs to respond to a handoff situation outside office hours. The wording depends on whether you allow handoff outside hours:

* **If allowed:** let the customer know the transfer happened but a response may be delayed.
* **If not allowed:** explain that the support team is unavailable and will reply during office hours.

Example (handoff allowed outside hours):

> I'll transfer you to our support team, but please note that since we're outside office hours, their response might be delayed.

Example (handoff not allowed outside hours):

> Our human support team is currently unavailable as we are outside office hours. They will be back during regular business hours.

<Info>
  Office hours are configured in **Settings → Office Hours**. The handoff settings read from that configuration.
</Info>

## Handoff summary language

When a handoff happens, the AI generates a short summary of the conversation for the human agent. This section controls the language that summary is written in.

<ParamField path="handoff_summary_based_on_session_language" type="boolean" default="true">
  When enabled, the summary is written in the same language the conversation is happening in.
</ParamField>

Disable this toggle to pin the summary to a specific language regardless of the conversation language — useful when your support team only reads one language but your customers chat in many.

## Forbidden topics

Certain topics always trigger a handoff, regardless of the level or advanced toggles above. These include legal matters, financial details, and other sensitive categories.

Forbidden topics are managed in **Settings → AI Autopilot**, not on the Handoff page. See [Unapproved Topics](/handoff/topics) for the full list and how to configure your own.

## Data collection

Before the AI transfers a conversation to a human, it can be required to collect specific information from the customer. This saves the human agent from asking for it again.

<ParamField path="must_collect_email" type="boolean" default="false">
  The AI will collect the customer's email address before handing off, unless it's already available from the customer's profile.
</ParamField>

<ParamField path="must_collect_name" type="boolean" default="false">
  The AI will collect the customer's name before handing off, unless it's already available from the customer's profile.
</ParamField>

<Note>
  These toggles save immediately — no need to click "Save" at the top of the page.
</Note>

## Saving changes

Most settings on this page only persist after you click **Save** at the top right. The two data collection toggles are the exception — they save on toggle. If you navigate away without saving, unsaved changes are lost.