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

# Show starter prompts on the chat welcome screen

> Build a custom chat welcome screen with starter prompts for React InstantSearch.

<div className="not-prose algolia-flavor-switcher">
  <div className="afs-dropdown">
    <div className="afs-trigger" role="button" tabIndex="0" aria-haspopup="listbox">
      <span className="afs-current">React</span>

      <svg className="afs-chevron lucide lucide-chevron-down" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2" strokeLinecap="round" strokeLinejoin="round" aria-hidden="true">
        <path d="m6 9 6 6 6-6" />
      </svg>
    </div>

    <ul className="afs-menu" role="listbox">
      <li role="option" aria-selected="false"><a className="afs-option" href="/doc/guides/building-search-ui/going-further/chat-customization/welcome-screen/js"><span className="afs-option-name">JavaScript</span><span className="afs-option-lib">InstantSearch.js</span></a></li>
      <li role="option" aria-selected="true"><a className="afs-option is-current" href="/doc/guides/building-search-ui/going-further/chat-customization/welcome-screen/react"><span className="afs-option-name">React</span><span className="afs-option-lib">React InstantSearch</span></a></li>
    </ul>
  </div>
</div>

<Note>
  This is the **React InstantSearch v7** documentation.
  If you're upgrading from v6, see the [upgrade guide](/doc/guides/building-search-ui/upgrade-guides/react/#migrate-from-react-instantsearch-v6-to-react-instantsearch-v7).
  If you were using React InstantSearch Hooks,
  this v7 documentation applies—just check for [necessary changes](/doc/guides/building-search-ui/upgrade-guides/react/#migrate-from-react-instantsearch-hooks-to-react-instantsearch-v7).
  To continue using v6, you can find the [archived documentation](https://algolia.com/old-docs/deprecated/instantsearch/react/v6/api-reference/instantsearch/).
</Note>

When the [`<Chat>`](/doc/api-reference/widgets/chat/react) widget has no messages yet, it shows a welcome screen. Use the [`emptyComponent`](/doc/api-reference/widgets/chat/react) prop to replace it with your own greeting and a set of starter prompts. Each prompt sends a message to the agent when clicked, so users can start a conversation in one tap.

If you only need prompt suggestions *after* the agent responds, use [Agent Studio prompt suggestions](/doc/guides/algolia-ai/agent-studio/how-to/integration#prompt-suggestions) instead.

## Render starter prompts with `emptyComponent`

The `emptyComponent` receives a `sendMessage` function. Call it with `{ text }` to submit a starter prompt as the first message:

```jsx React icon=code theme={"system"}
import React from "react";
import { liteClient as algoliasearch } from "algoliasearch/lite";
import { Chat, ChatTrigger, InstantSearch } from "react-instantsearch";

const searchClient = algoliasearch(
  "ALGOLIA_APPLICATION_ID",
  "ALGOLIA_SEARCH_ONLY_API_KEY"
);

const starterPrompts = [
  "What are your best-selling headphones?",
  "Help me find a gift under $50",
  "Compare espresso machines",
];

function WelcomeScreen({ sendMessage }) {
  return (
    <div className="ais-ChatGreeting">
      <h2 className="ais-ChatGreeting-heading">How can I help you today?</h2>
      <p className="ais-ChatGreeting-subheading">
        Ask me anything about our products, or start with a suggestion.
      </p>

      <div className="ais-ChatPromptSuggestions">
        {starterPrompts.map((prompt) => (
          <button
            key={prompt}
            type="button"
            className="ais-ChatPromptSuggestions-suggestion"
            onClick={() => sendMessage({ text: prompt })}
          >
            {prompt}
          </button>
        ))}
      </div>
    </div>
  );
}

function App() {
  return (
    <InstantSearch searchClient={searchClient}>
      <Chat agentId="YOUR_CHAT_AGENT_ID" emptyComponent={WelcomeScreen} />
      <ChatTrigger />
    </InstantSearch>
  );
}
```

<Note>
  Pair `<Chat>` with the [`<ChatTrigger>`](/doc/api-reference/widgets/chat-trigger/react) widget (or [AI mode](/doc/guides/building-search-ui/going-further/chat-customization/ai-search-experience/react) on a `<SearchBox>`) to provide a way to open the chat.
</Note>

The `emptyComponent` reuses the built-in classes (`ais-ChatGreeting` and `ais-ChatPromptSuggestions`) so it inherits the default styling. Replace them with your own classes to fully restyle the welcome screen.

## Reuse the default greeting

Instead of writing the greeting markup yourself, render the built-in `ChatGreeting` component, then add your starter prompts below it. It renders the default heading and subheading, and accepts a `banner` image, `translations`, and `classNames`:

```jsx React icon=code theme={"system"}
import { Chat, ChatGreeting } from "react-instantsearch";

function WelcomeScreen({ sendMessage }) {
  return (
    <>
      <ChatGreeting
        banner="https://example.com/welcome-banner.png"
        translations={{
          heading: "Welcome to our store",
          subheading: "Ask me anything, or pick a suggestion to get started.",
        }}
      />
      <div className="ais-ChatPromptSuggestions">
        {starterPrompts.map((prompt) => (
          <button
            key={prompt}
            type="button"
            className="ais-ChatPromptSuggestions-suggestion"
            onClick={() => sendMessage({ text: prompt })}
          >
            {prompt}
          </button>
        ))}
      </div>
    </>
  );
}
```

## Fetch starter prompts dynamically

The prompts don't have to be static. Fetch them once—for example, from a dedicated Agent Studio agent that returns starter prompts—and render them from `emptyComponent`:

```jsx React icon=code expandable theme={"system"}
import React, { useEffect, useState } from "react";

const appID = "ALGOLIA_APPLICATION_ID";
const apiKey = "ALGOLIA_SEARCH_ONLY_API_KEY";
const promptsAgentId = "YOUR_STARTER_PROMPTS_AGENT_ID";

async function getStarterPrompts() {
  const response = await fetch(
    `https://${appID}.algolia.net/agent-studio/1/agents/${promptsAgentId}/completions?stream=false&cache=true&compatibilityMode=ai-sdk-5`,
    {
      method: "POST",
      headers: {
        "Content-Type": "application/json",
        "X-Algolia-Application-Id": appID,
        "X-Algolia-API-Key": apiKey,
      },
      body: JSON.stringify({
        messages: [
          {
            role: "user",
            parts: [{ text: "Return starter prompts for the welcome screen." }],
          },
        ],
      }),
    }
  );

  const data = await response.json();
  const text = data.parts?.find((part) => part.type === "text")?.text ?? "";

  return text
    .split("\n")
    .map((line) => line.trim())
    .filter(Boolean);
}

function WelcomeScreen({ sendMessage }) {
  const [prompts, setPrompts] = useState([]);

  useEffect(() => {
    getStarterPrompts()
      .then(setPrompts)
      .catch(() => setPrompts([]));
  }, []);

  return (
    <div className="ais-ChatGreeting">
      <h2 className="ais-ChatGreeting-heading">How can I help you today?</h2>

      <div className="ais-ChatPromptSuggestions">
        {prompts.map((prompt) => (
          <button
            key={prompt}
            type="button"
            className="ais-ChatPromptSuggestions-suggestion"
            onClick={() => sendMessage({ text: prompt })}
          >
            {prompt}
          </button>
        ))}
      </div>
    </div>
  );
}
```

## Customize more than the empty state

The `emptyComponent` only replaces the initial empty state. To customize the surrounding chat layout (header, message list, prompt input), use the [`layoutComponent`](/doc/api-reference/widgets/chat/react) prop instead. Use `ChatInlineLayout` for an inline (non-overlay) layout, or `ChatOverlayLayout` for the default floating overlay, and reuse `headerComponent`, `messagesComponent`, and `promptComponent` to keep the built-in behavior.

## Related

* [Chat widget reference](/doc/api-reference/widgets/chat/react)
* [ChatTrigger widget reference](/doc/api-reference/widgets/chat-trigger/react)
* [Agent Studio](/doc/guides/algolia-ai/agent-studio)