> ## Documentation Index
> Fetch the complete documentation index at: https://algolia.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Ask AI

> Ask AI turns your support articles, developer documentation, and blogs into a conversational AI assistant (chatbot).

export const ApplicationID = () => <Tooltip tip="A unique alphanumeric string that identifies an Algolia application." cta="Application ID (dashboard)" href="https://dashboard.algolia.com/account/api-keys">
    application ID
  </Tooltip>;

export const Application = () => <Tooltip tip="An Algolia application is a self-contained environment with its own indices, configuration, and API keys. Applications don't share data or settings with each other.">
    application
  </Tooltip>;

export const AcademyLink = ({href, title}) => {
  return <Card horizontal title="Algolia Academy" href={href} icon="square-play">Learn more about: {title}</Card>;
};

<Note>
  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.
</Note>

Ask AI enhances keyword search with conversational AI,
using your Algolia index to provide rich, context-aware answers.
It's designed for technical documentation, blogs, and support content.
It's integrated into [DocSearch](https://docsearch.algolia.com/docs/docsearch)
but you can use your own UI as well.
Connect your favorite large language model (LLM) from your provider of choice,
and Ask AI turns search results into clear, AI-generated responses grounded in your existing content.

<Columns cols={2}>
  <AcademyLink href="https://academy.algolia.com/pages/contentcatalog/training/0199aaef-c029-7b43-9ffc-7ac53b3b5c15/overview" title="Ask AI" />

  <Card horizontal title="DocSearch playground" href="https://community.algolia.com/docsearch-playground/" icon="monitor-play">
    Try the Ask AI demo.
  </Card>
</Columns>

## Why you should use Ask AI

* **Reduce support workload.**
  Deflect repetitive questions and let users self-serve with AI-powered answers.

* **Boost user satisfaction.**
  Provide fast, conversational help directly from your content.

* **Launch and maintain with minimal setup.**
  No retraining, no manual tagging—just connect your index.

* **Customizable for your needs.**
  Adapt prompts, tone, and model to your brand and audience.

* **Future-proof.**
  As your content or LLM provider evolves, AskAI adapts with you.

## Before you begin

You can use your existing Algolia <Application /> or create a new one for testing.
Algolia needs to know your <ApplicationID /> to enable Ask AI for it.

## Get started

<Steps>
  <Step title="Enable and Configure Ask AI">
    Follow one of these guides, depending on your implementation:

    * [Configure Ask AI for DocSearch](https://docsearch.algolia.com/docs/v4/askai)
    * [Configure Ask AI for other implementations](/doc/guides/algolia-ai/askai/guides/setup)
  </Step>

  <Step title="Connect your LLM provider">
    Ask AI is LLM-agnostic and supports several providers.
    You use your own API keys and are in control over usage, costs, and LLM behavior.

    For more information, see [Supported LLMs](/doc/guides/algolia-ai/askai/guides/models).
  </Step>

  <Step title="Test in the DocSearch playground">
    Verify your setup using the [DocSearch playground](https://community.algolia.com/docsearch-playground).
    Enter your application ID and Ask AI credentials to start testing.
  </Step>

  <Step title="Optimize accuracy and relevance">
    Apply [filters](/doc/guides/algolia-ai/askai/guides/prompting#optimize-relevance-and-accuracy-in-ask-ai-responses) to reduce the search scope.

    To ensure that Ask AI generates the most relevant and accurate answers,
    it's best to [create a dedicated index](/doc/guides/algolia-ai/askai/guides/markdown-indexing)
    for your content.
  </Step>
</Steps>