Welcome to ChattyBox

Turn your documentation into a source-cited AI chatbot that answers from your content. Choose a one-line hosted widget, mount that same widget from application code, build your own UI with the headless SDK, or manage the project with versioned configuration as code.

Fast path

If you already have a docs site or help center, start with Getting Started, pick the right Installation Guide, and use Analytics to find unanswered questions.

1. Create a ChattyBox project. Add your site URL or sitemap so the crawler can discover documentation pages.
2. Test grounded answers. Ask real support questions and verify the cited source pages.
3. Choose an integration. Paste the script, mount the hosted UI with the SDK, or use the headless SDK with your own components.

Get running

Create a project, scrape your content, test responses, and launch the widget in minutes.

Integrate with the SDK

Install the npm package, configure your public key and API URL, then mount the maintained UI or build your own.

Use an AI coding assistant

Give your coding assistant a complete SDK-first integration prompt for your framework.

Configure as code

Keep one project's assistant, knowledge source, runtime, and widget settings in version control.

Four ways to use ChattyBox

Goal	Use	You own
Add the maintained chatbot UI from React or app code	Chattybox.mountWidget()	App initialization
Use ChattyBox infrastructure with your own chatbot UI	Headless SDK	Components, state, and interaction design
Manage project behavior from Git and CI instead of the dashboard	CLI and config as code	One config file and its deployment pipeline
Add the maintained UI without npm or a build step	widget.js HTML snippet	Where the script is installed

The browser integrations use a public widget API key. Configuration deployment uses a separate secret deployment token; never put that token in browser code.

Choose an implementation or evaluation path

• Compare verified framework guidance in the platforms hub, including the Docusaurus implementation and MkDocs implementation.
• Plan technical-docs evaluation with the documentation chatbot guide or narrow endpoint and authentication testing with the API documentation guide.
• Review retrieval, freshness, and fallback behavior in the RAG architecture guide.
• Define answer-verification behavior with the source-citation guide.
• Browse support, trust, and content-discovery goals in the use-cases hub, or compare products through the alternatives hub.

What ChattyBox Does

ChattyBox is an AI-powered chatbot platform that:

• Scrapes your website and indexes documentation, guides, help centers, or knowledge bases.
• Answers from retrieved content instead of generic model memory.
• Shows source citations so visitors can verify answers and continue reading.
• Refuses missing information instead of inventing unsupported answers.

Quick Start

Build and verify the chatbot before exposing it to visitors.

1. Create an account and make your first project.
2. Configure and index your content, then review the pages that were discovered.
3. Use Test Chat to verify representative answers, citations, and fallback behavior.
4. Tune the persona and hosted-widget appearance for the experience you want.
5. Create a restricted public key and choose an integration.
6. Run the launch checklist before publishing broadly.
7. Review analytics to see what visitors ask and what content is missing.

Key Features

Source-Grounded Answers

Unlike generic chatbots, ChattyBox is designed to answer only from your scraped content. If the information isn't in your documentation, the bot can say it doesn't know. Answers can include source citations for verification.

Source Citations

When relevant source pages are retrieved, answers can include clickable links to your documentation. This builds trust and lets users verify information.

Analytics Dashboard

Track what questions visitors are asking, identify content gaps, and improve your documentation based on real user needs.

Easy Customization

Match the chat widget to your brand with custom colors, icons, and welcome messages, all from the dashboard with no code required.

How It Works

1. Scraping - Our crawler visits your website, extracts text content, and handles sitemaps automatically
2. Vector Embeddings - Content is converted to high-dimensional vectors for semantic search
3. RAG Response - When a user asks a question, we retrieve relevant chunks and generate an answer using only that context

Recommended Reading Order

1. Getting Started

Create the project and understand the basic launch flow.

2. Content Scraping

Control what gets indexed and keep multilingual content organized.

3. Test and Integrate

Verify answers first, then install the hosted widget or choose the SDK.

4. Troubleshooting

Fix missing widget, API key, origin, language, citation, and stale content issues.

Pricing

ChattyBox offers a free tier with generous limits for testing, plus affordable paid plans as you grow. See our pricing page for details.

Frequently Asked Questions

What content can ChattyBox index?

ChattyBox can index website pages, documentation, help centers, CMS content, knowledge bases, and sitemap-discovered pages. The crawler extracts readable text and headings so the assistant can answer from source content instead of generic model memory.

How do source citations work?

When a visitor asks a question, ChattyBox retrieves relevant passages from indexed pages and can include links to the source pages used for the response. Citations help visitors verify answers and continue reading the official documentation.

What should I test before launch?

Ask real support and documentation questions, confirm the cited pages are correct, check fallback behavior when information is missing, and run through the launch checklist before publishing the widget broadly.

Need Help?

• Email us at support@chattybox.ai
• Check the documentation for detailed guides
• Use Troubleshooting if the widget does not appear or answers look weak