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

# Intent Intelligence

> **Tip**
>
> **Not sure where to begin?** Explore our [Getting started](/docs/welcome/getting-started) guidelines to set up your first AI Agent, review [Key concepts](/docs/welcome/key-concepts) to understand the essentials, or check out [Improvement tactics](/docs/welcome/improvement-tactics) to resolve issues and keep things running smoothly.

**Intent Intelligence** organizes your conversations into a two-level taxonomy: **Topics** group conversations by subject, and each Topic contains **Intents** that capture the specific reason an end user reached out. Click into any Topic or Intent to see a detailed breakdown of the data collected, helping you better understand customer needs and Agent performance.

> **Note**
>
> Before getting started, make sure your AI Agent's core elements—like [Knowledge](/docs/knowledge), [Actions](/docs/automation/tools/api-tools), and [Processes](/docs/automation/processes)—are in place. Other core features may also apply depending on your setup.

This section covers how to use Topics and Intents to better understand what your customers are talking about. You'll learn [how Intent Intelligence works](/docs/optimization/performance/intent-intelligence/topic-and-intent-analysis#how-it-works), [how to review insights](/docs/optimization/performance/intent-intelligence/topic-and-intent-analysis#review-insights), [how to manage Topics and Intents](/docs/optimization/performance/intent-intelligence/topic-and-intent-analysis#manage), and [how to review AI-recommended Intents](/docs/optimization/performance/intent-intelligence/topic-and-intent-analysis#recommended-intents). You'll also see [how to export the performance table](/docs/optimization/performance/intent-intelligence/topic-and-intent-analysis#export) and [how classification works across languages](/docs/optimization/performance/intent-intelligence/topic-and-intent-analysis#multilingual-support).

Finally, you'll explore [Best practices](/docs/optimization/performance/intent-intelligence/best-practices), which demonstrates how to apply these insights in practice. By spotting patterns across Topics and Intents, connecting them to key metrics like AR Opportunity and CSAT, and drilling into [Conversations](/docs/optimization/conversations), you can uncover automation gaps and prioritize improvements that have the greatest impact on customer experience.

---

Have any questions? Contact your Ada team, or email us at [](mailto:help@ada.cx?subject=Help%20Docs%20inquiry).