> This page is for version Generative (default).
> For other versions, use one of these documentation indexes:
> - Generative (default): https://developers.ada.cx/generative/llms.txt
> - Scripted: https://developers.ada.cx/scripted/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://developers.ada.cx/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://developers.ada.cx/_mcp/server.

# Conversations

Conversations are a [key concept](/generative/docs/welcome/key-concepts) in Ada, providing insight into how your AI agent interacts with customers. The Conversations view allows AI Agent Managers to review all conversations and apply [Coaching](/generative/docs/monitoring/coaching) when needed to improve future responses. A good starting point is to explore the full history of conversations.

> **Note**
>
> Before getting started with reviewing past conversations, make sure your AI Agent's core elements—like [Knowledge](/generative/docs/knowledge), [Actions](/generative/docs/automation/actions), and [Processes](/generative/docs/automation/processes)—are in place. Other core features may also apply depending on your setup. To learn more, see the [Getting started](/generative/docs/welcome/getting-started) section.

This section covers how to work with conversations to improve your AI agent’s \[performance]. You’ll learn how to [track and improve the automated resolution rate](/generative/docs/monitoring/conversations/resolution-rate-optimization), [use past conversations to enhance responses](/generative/docs/monitoring/conversations/response-training), and [export conversation data for analysis](/generative/docs/monitoring/conversations/data-export). These tools help you understand how your AI agent is performing and identify opportunities to improve the customer experience.

![Conversations](/_fern-files/_img/7d38fb2f218c35d98506bd7f4b0fe941e8b37550491a46e3ceeeab02293c99ea.webp)

---

Have any questions? Contact your Ada team, or email us at [](<mailto:help@ada.support%20%E2%80%9CHelp Docs inquiry%E2%80%9D>).