> For the complete documentation index, see [llms.txt](https://themochi-app.gitbook.io/mochi-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://themochi-app.gitbook.io/mochi-docs/feature-and-settings/ai-setter.md).

# AI Setter

AI Setter is Mochi's AI-powered conversation assistant. It analyzes your team's conversations, discovers what works, and can even respond to leads on your behalf when you're away.

## AI Phases

AI Setter has three modes, configured by the Creator:

| Phase              | What It Does                                                               |
| ------------------ | -------------------------------------------------------------------------- |
| **Disabled**       | AI features are off. Mochi works as a standard CRM.                        |
| **Analytics Only** | AI analyzes conversations and provides insights, but never sends messages. |
| **Full**           | AI can suggest replies and handle conversations during Away Mode.          |

## Conversation Analysis

When enabled, AI Setter analyzes your DM conversations to provide:

### Conversation Signals

* **Sentiment** — Is the lead positive, neutral, or hesitant?
* **Engagement level** — How actively is the lead participating?
* **Intent** — What does the lead seem to want?
* **Response time patterns** — How quickly is each side responding?

### Stage Prediction

AI predicts which funnel stage a conversation is actually at, based on the content — not just what it's been manually set to. This helps identify leads that may need a stage update.

## Reply Suggestions

In Full mode, AI Setter suggests responses based on:

* Your **Creator DNA** voice profile (how you communicate)
* Your **Sales Playbook** (your methodology and scripts)
* The conversation context and history
* **Golden Scripts** — the highest-performing response patterns discovered from your data

Suggestions appear in the Inbox. Use them as-is, edit them, or write your own.

## Away Mode

When your team steps away, AI Setter can handle incoming messages automatically.

### How It Works

{% stepper %}
{% step %}
Enable Away Mode for a team member (Settings → Intelligence, or per-member)
{% endstep %}

{% step %}
Set the timeout — how long to wait before AI takes over (1 minute to 24 hours, default 30 minutes)
{% endstep %}

{% step %}
When the timeout passes with no human response, AI Setter begins responding
{% endstep %}

{% step %}
When the team member returns, they see a **Return Summary** — a recap of what AI handled
{% endstep %}
{% endstepper %}

### Configuring Away Mode

* **Per organization** — Set default timeout for all members
* **Per member** — Override the default for specific team members
* Enable/disable for individual team members

## Patterns & Golden Scripts

Over time, AI Setter discovers:

* **Patterns** — Recurring successful conversation flows in your data
* **Golden Scripts** — The specific messages and sequences that lead to the best outcomes

These are available in the AI Setter section for review and can inform your team's sales training.

## Auto-Tagging

AI can automatically tag new leads based on conversation content. Configure tag rules in **Tags**, and AI applies them as conversations progress.


---

# 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://themochi-app.gitbook.io/mochi-docs/feature-and-settings/ai-setter.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.