> For the complete documentation index, see [llms.txt](https://doc.autoreach.tech/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://doc.autoreach.tech/ai-and-conversations/conversation-analyzer.md).

# Conversation Analyzer

The Conversation Analyzer reviews your conversations, identifies patterns, and generates actionable suggestions to improve your AI's outreach voice.

## How It Works

When you run an analysis:

1. Fetches all replied conversations for the sequence
2. Classifies outcomes (positive, negative, neutral) based on conversation status
3. Analyzes patterns across your conversations using AI
4. Generates actionable suggestions for improvement

Analysis is triggered manually- it is not automatic.

## Suggestion Types

The Analyzer generates four types of suggestions:

### Modify Tone Example

An existing tone example isn't matching your actual voice. The Analyzer identifies the misalignment and suggests specific edits.

### Add Tone Example

A conversation stage is missing examples or has too few. The Analyzer identifies a gap and suggests a new example based on your successful conversations.

### Remove Tone Example

A tone example contains anti-patterns or is consistently associated with stalled conversations. The Analyzer recommends removing it.

### Modify Prompt

Your AI prompt needs adjustment. Each prompt modification suggestion targets a specific prompt field:

* **AI Prompt**- general conversation AI instructions
* **How AI Engages With Posts**- the prompt for engaging with leads' posts (X, LinkedIn, and Instagram)
* **DM Generation Prompt**- cold DM generation prompt

## Applying Suggestions

For each suggestion, you can:

* **Accept**: Select the suggestion for application
* **Discard**: Remove the suggestion

After reviewing, click **Apply** to implement all accepted suggestions at once, or **Dismiss** to clear all results.

## When to Run Analysis

Run the Conversation Analyzer after accumulating enough conversations for meaningful patterns- typically after 20+ replied conversations. The more data available, the more reliable the suggestions.

## Next Steps

* [**Tone and Knowledge Base**](/ai-and-conversations/tone-and-knowledge.md): Manage the tone examples that suggestions modify
* [**AI Response Engine**](/ai-and-conversations/ai-response-engine.md): How tone and prompt changes affect responses


---

# 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://doc.autoreach.tech/ai-and-conversations/conversation-analyzer.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.