> For the complete documentation index, see [llms.txt](https://www.kauneonga.com/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://www.kauneonga.com/docs/ai/overview/ai.md).

# AI

Liberty brings AI into voice, SMS, quality, and administrative workflows across the platform.

It helps answering services extend coverage, reduce repetitive work, and improve consistency across accounts.

### How AI is organized

AI in Liberty is organized into four operational areas:

* [Voice AI](/docs/ai/voice-ai/voice-ai-assistants.md) for inbound and outbound voice workflows
* [SMS AI](/docs/ai/sms-ai/sms-ai-assistants.md) for guided Two-Way SMS workflows
* [Quality Assurance AI](/docs/ai/quality-assurance-ai/quality-assurance-ai.md) for review, coaching, and trend visibility
* [Admin AI](/docs/ai/admin-ai/admin-ai.md) for supported internal administrative workflows, with [MCP](/docs/ai/admin-ai/mcp.md) for external assistant access

### Current AI capabilities

Current AI capabilities in Liberty include:

* **Voice AI**
  * AI Assistants for structured inbound call handling
  * AI Call To Dos for outbound AI call workflows
  * speech-to-text for voicemail and quality review workflows
  * text-to-speech for IVR, Enhanced IVR, Agent Whisper, and AI Assistants
* **SMS AI**
  * guided Two-Way SMS workflows
  * shared assistant logic across channels
  * routing and scheduling for text conversations
* **Quality Assurance AI**
  * overview visibility across teams and agents
  * agent-level review and coaching support
  * message and call analysis for faster QA follow-up
* **Admin AI**
  * internal admin workflows for account setup and configuration
  * script, schedule, and routing updates
  * activity review for messages, voicemails, and calls
  * external assistant access through MCP for ChatGPT and Claude

### Explore AI capabilities

<table data-view="cards"><thead><tr><th>Title</th><th data-card-target data-type="content-ref">Target</th><th data-hidden data-card-cover data-type="image">Cover image</th></tr></thead><tbody><tr><td><p><img src="/files/YhbRgrXWe3F0qFC95fwx" alt="Voice AI" data-size="original"></p><p><strong>Voice AI</strong></p><p>Structured call handling, routing, and escalation workflows.</p></td><td><a href="/spaces/cvVWNsbzvWkRa4x8QSwZ/pages/vgW1Rx2dU4y4t7gLNMuF">/spaces/cvVWNsbzvWkRa4x8QSwZ/pages/vgW1Rx2dU4y4t7gLNMuF</a></td><td></td></tr><tr><td><p><img src="/files/AAtqjHucNINYF5L7Bpb9" alt="SMS AI" data-size="original"></p><p><strong>SMS AI</strong></p><p>Guided messaging workflows for Two-Way SMS operations.</p></td><td><a href="/spaces/cvVWNsbzvWkRa4x8QSwZ/pages/T5RBRaYQy1DQAhp5S3lc">/spaces/cvVWNsbzvWkRa4x8QSwZ/pages/T5RBRaYQy1DQAhp5S3lc</a></td><td></td></tr><tr><td><p><img src="/files/zdr54vkQoeNNN5Ew57DM" alt="Quality Assurance AI" data-size="original"></p><p><strong>Quality Assurance AI</strong></p><p>Review, coaching, and quality visibility across teams.</p></td><td><a href="/spaces/cvVWNsbzvWkRa4x8QSwZ/pages/8lRroDnGrNlOqURyQZvZ">/spaces/cvVWNsbzvWkRa4x8QSwZ/pages/8lRroDnGrNlOqURyQZvZ</a></td><td></td></tr><tr><td><p><strong>Admin AI</strong></p><p>Internal administrative workflows for account setup, routing, and review.</p></td><td><a href="/spaces/cvVWNsbzvWkRa4x8QSwZ/pages/WMDyC7k30nA6RPJcG41l">/spaces/cvVWNsbzvWkRa4x8QSwZ/pages/WMDyC7k30nA6RPJcG41l</a></td><td><a href="/files/o6wJHdMiV2PIayzTq4JM">/files/o6wJHdMiV2PIayzTq4JM</a></td></tr></tbody></table>

### How AI helps answering services

AI can help teams:

* extend after-hours and overflow coverage
* improve workflow consistency across agents and accounts
* reduce manual handling of routine interactions
* speed up review with transcripts and AI-assisted analysis
* support scalable multi-client operations with more control
* reduce wait times

### Admin AI and MCP

Liberty separates admin work from assistant connectivity.

[Admin AI](/docs/ai/admin-ai/admin-ai.md) covers the internal workflows Liberty supports for admins and supervisors.

[MCP](/docs/ai/admin-ai/mcp.md) covers how external assistants like ChatGPT and Claude connect to those workflows.

{% hint style="info" %}
Coming soon: future releases will extend speech-to-text and AI-generated summaries further into message workflows.
{% endhint %}

### Where AI fits best

AI works best in workflows that are:

* structured
* repeatable
* rules-based
* supported by clear escalation paths

Agents remain essential when interactions require judgment, empathy, or exception handling.

### Implementation guidance

Strong AI outcomes usually depend on:

* clear workflow design
* defined escalation rules
* account-specific scripting
* routing aligned to client requirements
* ongoing review of transcripts and outcomes

### Stay current

Product capabilities continue to evolve.

Review the [release notes](https://www.kauneonga.com/release-notes/) for the latest updates.


---

# 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://www.kauneonga.com/docs/ai/overview/ai.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.