> For the complete documentation index, see [llms.txt](https://docs.mikopbx.com/mikopbx/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.mikopbx.com/mikopbx/english/modules/miko/module-a-i-supervisor/quick-start.md).

# Quick Start

Quick start guide for the AI Supervisor module

### Before you begin

You will need:

* MikoPBX 2025.1.1 or later;
* a Mac with Apple silicon and macOS 14 or later;
* network access from the Mac to the MikoPBX web interface.

{% hint style="info" %}
AI Supervisor analyzes completed transcripts. If speech recognition has not been configured yet, first follow the [Local Speech To Text quick start](/mikopbx/english/modules/miko/module-local-speech-to-text/quick-start.md).
{% endhint %}

### Installing the module

1. Open the MikoPBX web interface.
2. Go to **Modules** → **Module marketplace**.

<figure><img src="https://835495363-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FsZ8acWnNlSalIHQjMFu1%2Fuploads%2Fgit-blob-077c6ead7c0da0da965a81334a88a7d27f7b4532%2FMikoPBXModuleMarketplace.png?alt=media" alt=""><figcaption><p>Module marketplace</p></figcaption></figure>

3. Find **AI Supervisor** and install it.
4. Open the **Installed modules** tab and enable the module.

<figure><img src="https://835495363-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FsZ8acWnNlSalIHQjMFu1%2Fuploads%2FAFSDkwTymNIzDBQLKYy4%2FInstalledModulesSection-EnableModule.png?alt=media&amp;token=bdd2f47c-cea7-4a52-9f25-8fffc47faf15" alt=""><figcaption><p>Enabling the AI Supervisor module</p></figcaption></figure>

5. Click the settings button to the right of the module version.

<figure><img src="https://835495363-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FsZ8acWnNlSalIHQjMFu1%2Fuploads%2FnAryn2NqqB7ITcDFvoGJ%2FAIModuleGoToParams.png?alt=media&amp;token=76440e2f-03f1-416a-b9f0-df611fffaba7" alt=""><figcaption><p>Module settings button</p></figcaption></figure>

### Configuring the module

#### 1. Create a worker key

Open **Settings** → **Workers**. Click **Generate API key**.

Copy the displayed value. The complete key is shown only once. After you close the window, only safe information about the key remains in the list.

<figure><img src="https://835495363-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FsZ8acWnNlSalIHQjMFu1%2Fuploads%2Fgit-blob-66301ff74df3d606b8c773d143c1a06a32c6146a%2FQSAIModule-CreatingAKey.png?alt=media" alt=""><figcaption><p>Creating a worker key</p></figcaption></figure>

#### 2. Select the analysis components and model

Open **Settings** → **AI analysis**.

Select the analysis pipeline components that suit your needs:

* **Summary** — a structured call review covering topics, risks, and quality. This is the module's core component and is produced by the selected LLM.
* **Voice metrics** — tempo, pauses, interruptions, silence, and speaker balance. This component analyzes the technical aspects of a call.
* **Emotion Analysis** — text-based emotion detection for conversation fragments.
* **Acoustic analysis** — detection of acoustic features in the recording with an acoustic model. It helps confirm or challenge the results of voice metrics and LLM-based emotion analysis.

Also select a model profile. See [AI analysis](/mikopbx/english/modules/miko/module-a-i-supervisor.md#ai-analysis) for more information.

<figure><img src="https://835495363-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FsZ8acWnNlSalIHQjMFu1%2Fuploads%2Fgit-blob-44b705c6eddfe83a5ea2c4670a0a44c53546711a%2FAISupervisorAIAnalysis.png?alt=media" alt=""><figcaption><p>Selecting analysis components</p></figcaption></figure>

#### 3. Enable the call flow

Open **Settings** → **Call flow** and check that:

* **Automatically analyze new transcripts** is enabled;
* **Automatic import** is enabled;
* the required AI result language is selected;
* **Process internal calls** is enabled if required;
* an appropriate data retention period is selected.

<figure><img src="https://835495363-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FsZ8acWnNlSalIHQjMFu1%2Fuploads%2Fgit-blob-ce5d16a6121900c3c3934c53a76a73df5ab4fcf8%2FAISupervisorAIFlow.png?alt=media" alt=""><figcaption><p>Call flow settings</p></figcaption></figure>

### Configuring AI Supervisor Worker

#### 1. Install the application

Open **Workers**, click **Download worker**, and install the downloaded DMG.

#### 2. Select the language

Open **AI Supervisor Worker**. On the first screen, select the interface language and click **Continue**. Restart the application if it prompts you to do so after the language change.

<figure><img src="https://835495363-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FsZ8acWnNlSalIHQjMFu1%2Fuploads%2Fgit-blob-f965bbd5ae2a6839a8c0134550c7645b825599c0%2FAIWorkerOBLanguage.png?alt=media" alt=""><figcaption><p>Application language selection</p></figcaption></figure>

#### 3. Connect to MikoPBX

On the connection screen, enter:

* the MikoPBX address in `https://...` or `http://...` format;
* a friendly name for this Mac;
* the AI Supervisor worker key created earlier in the module.

Open **Advanced settings** only if you need to change the stable Worker UID, TLS verification, or select a custom PEM CA file. Click **Connect and continue**. The application verifies the address, key, and worker API v2 contract.

<figure><img src="https://835495363-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FsZ8acWnNlSalIHQjMFu1%2Fuploads%2Fgit-blob-d58c602079e33a5255e123ace81fb2236ef1d286%2FAIWorkerOBConnection.png?alt=media" alt=""><figcaption><p>Connecting to MikoPBX</p></figcaption></figure>

#### 4. Prepare local AI

On the **Prepare local analysis** screen, the application checks in sequence:

1. the local Ollama runtime;
2. the model selected in MikoPBX;
3. worker readiness.

If Ollama is not installed, click **Install Ollama**. After installation, click **Prepare and start**. The application downloads the selected model, registers this Mac, and starts the worker.

The first model download may take a long time. Do not close the application, and make sure the Mac has enough free disk space.

<figure><img src="https://835495363-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FsZ8acWnNlSalIHQjMFu1%2Fuploads%2Fgit-blob-9efc683203853ff219eb189580d662eded88657c%2FAIWorkerOBModelPreparation.png?alt=media" alt=""><figcaption><p>Preparing the local LLM runtime</p></figcaption></figure>

#### 5. Finish setup

On the final screen, check the **MikoPBX**, **Local model**, and **AI Worker** states.

If necessary, enable:

* **Launch at login** — the application opens automatically when you sign in to macOS.
* **Keep worker running** — the worker automatically resumes after the network or PBX connection is restored, or after the Mac wakes from sleep.

Click **Open AI Supervisor Worker**.

<figure><img src="https://835495363-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FsZ8acWnNlSalIHQjMFu1%2Fuploads%2Fgit-blob-799190b9d8582f113fefff1378761175adad5da6%2FAIWorkerOBFinal.png?alt=media" alt=""><figcaption><p>Final onboarding screen</p></figcaption></figure>

### Verifying the result

1. In AI Supervisor Worker, open **Overview**. The status should show that the worker is ready for the next job.
2. In MikoPBX, open **Settings** → **System** → **Processing** and make sure jobs move from waiting to in progress.
3. When processing finishes, open the **Calls** tab and select the processed call.

<figure><img src="https://835495363-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FsZ8acWnNlSalIHQjMFu1%2Fuploads%2Fgit-blob-af449d01766ee682a7ce8f142c85fb1c713bac8a%2FAIWorkerStatus.png?alt=media" alt=""><figcaption><p>Overview in AI Supervisor Worker</p></figcaption></figure>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.mikopbx.com/mikopbx/english/modules/miko/module-a-i-supervisor/quick-start.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
