> ## Documentation Index
> Fetch the complete documentation index at: https://algolia.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Measure Ask AI performance
> Ask AI provides analytics to help you understand user interactions and enhance their experience.
Ask AI is part of [Agent Studio](/doc/guides/algolia-ai/agent-studio)
and isn't available as a standalone feature for new applications.
Use these docs for existing Ask AI implementations.
Migration guides will be added when available.
Ask AI provides analytics to help you understand how users interact with your AI assistant and improve their experience.
To access metrics, go to the [Ask AI page in the dashboard](https://dashboard.algolia.com/ask-ai) and click your assistant's name.
The performance analytics metrics are:
* **Ask AI questions vs total queries.** Shows what percentage of user queries are handled by Ask AI instead of keyword search. A higher percentage suggests users prefer the assistant.
* **Upvoted responses vs total.** Shows how often users rate answers as helpful.
* **Downvoted responses vs total.** Shows how often users rate answers as unhelpful. Use this to improve prompts or content.
* **Thread depth.** Indicates how many interactions with the AI assistant to resolve a query. A lower number means clearer, more effective responses.
* **Recent feedback.** Lists positive and negative user ratings. Use the feedback to:
* Identify strengths and areas for improvement.
* Refine prompts or assistant behavior.
* Detect content gaps or recurring support issues.
* Enhance answer quality and relevance.
* Prioritize content updates.
Use the **Date range** to uncover trends, refine prompts, and address content gaps.
