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

# Activate and pause GHL chat

> Route a connected GoHighLevel contact’s messages to the right assistant and verify a delivered reply.

For a GoHighLevel-connected subaccount, an **Active Tag** rule selects which assistant handles an eligible incoming contact message. Use this guide after the GHL location and the intended messaging channel are connected.

## Before you start

Have an enabled assistant, a test contact in the connected GHL location, and a channel that can both receive and send messages. A channel toggle allows an assistant to use a connection; it does not create the provider connection itself.

## Create the routing rule

1. Open **Active Tags** in the intended subaccount.
2. Click **New active tag** or **Create active tag** in the empty state.
3. Enter a **Rule name** that your team will recognize.
4. Set the **Matching tag** value you will apply to contacts.
5. Choose the assistant and save the rule.
6. In GoHighLevel, add that matching tag to the test contact.

The rule's display name and its matching tag are separate. Use the matching value shown on the rule; renaming the display name does not rename existing CRM contact tags.

## Configure reply behavior

Open the assistant's **Chat Settings**:

* **Wait time** delays the queued reply in seconds and helps group closely spaced incoming messages.
* **Max responses** limits AI responses in a conversation.
* **Channels** controls the channels the assistant may answer. Enable only the connected channels you intend to use.
* **Sleep mode** pauses eligible replies after a human sends a message. **Sleep duration** controls that pause. **Sleep on workflow messages** determines whether recognized automated sends also start it.

Wait for the settings to save. Review the assistant's enabled/published state before testing.

## Chat Settings reference

Defaults describe a fresh form; saved assistants load their existing configuration.

| Setting | Values and effect |
| - | - |
| **Wait time** | Seconds before responding; minimum 0, default 15. The form has no upper bound. Incoming messages during the wait can be combined before the reply. |
| **Max responses** | Reply cap per conversation; minimum 1, default 50. The form has no upper bound. |
| **Temperature** | 0–1 in steps of 0.01, default 0.35. Higher values request more varied responses. |
| **Sleep mode** | Off by default. When enabled, a team message pauses AI replies for the configured duration. |
| **Sleep duration** | Minutes; minimum 1, default 30. Shown when Sleep mode is on. The pause is measured from the triggering message; new contact replies do not extend it. |
| **Sleep on workflow messages** | On by default; applies while Sleep mode is enabled. Turn it off to exclude GHL workflow messages as sleep triggers. |
| **Voice note replies** | Off by default; available for GHL accounts. Requests a voice-note reply alongside text for supported WhatsApp, Facebook, Instagram, or email voice-note conversations. Requires voice notes enabled in **AI Media** and an assistant voice. |
| **Purposeful misspellings** | Off by default. Enables deliberate typographical variation in generated replies. |
| **Misspelling frequency** | 0–100% in steps of 1; default 10%. Shown when Purposeful misspellings is on. This is a generation instruction, not a guarantee that exactly that proportion of delivered words changes. |
| **Channels** | **SMS**, **Email**, **WhatsApp**, **Instagram**, **Facebook**, **3rd-party**, and **Live chat**. All are selected in a fresh form. A channel must also be connected and supported by the account. |
| **Home screen prompts** | Up to 8 quick-tap suggestions, up to 120 characters each. Initially empty. When set on the assistant, these override the widget's own home prompts. |

Wait for the saved state before testing. Channel selection allows responses through an existing integration; it does not connect the channel or configure active-tag routing.

## Verify a delivered reply

Send a new message from the test contact through the actual channel. Wait for the configured delay and inspect both sides of the conversation. Confirm the customer received the reply and that the intended assistant handled it.

If there is no reply, check the matching contact tag, `ai_off`, assistant enabled state, channel settings, sleep state, response cap, integration connection, and funding/error status. Removing every matching active tag prevents this automatic routing path from selecting an assistant; it does not promise a particular memory or logging outcome.

For a manual pause, use [ai\_off](/v3/guides/chat/pause-contact). For an in-progress indicator, see [AI Replying](/v3/guides/chat/replying-indicator).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.