Add Your Support Content

Glassix AI Chatbot thrives on information. The more you provide, the better it performs. This AI chatbot can utilize external support content, such as your website, files (PDF and Word), snippets, and Q&A pairs. You can choose the specific sources of information you want the AI Chatbot to use when responding to customers' questions.

AI Chatbot will automatically generate answers based on the support content you add, and you'll have the opportunity to preview these responses before they go live.

As your support content improves, so do the resolution rates and performance of the Glassix AI Chatbot.
Start adding your support content here.

Website

You can use any public URL (such as pages on your website, pricing information, blog posts, etc.), and we will import the content.

You can choose to add:

  • Content that is on a specific path: e.g., if you input the URL https://docs.glassix.com/docs/bot-best-practices, we’ll scan only that particular page.
  • Content that is under an entire domain like docs.glassix.com or path like www.glassix.com/blog.
    Our web crawler will scan the URL and crawl the entire website by following internal links and the sitemap.

The web crawler will scan only web pages from your domain; links to content on other domains or documents/PDFs will be ignored.
This process can take anywhere from a few minutes to 15 minutes, depending on the volume of your help content.
Once all content is synced and available, this content source will be marked as "active".

📘

We recommend using a URL dedicated to an FAQ, knowledgebase or help center, where the content primarily focuses on answering customer questions. Including irrelevant content may decrease the AI Chatbot's success rate.


How can we improve the web crawler scan?
If the imported web pages are missing text, you can change the crawler's settings to achieve better results.
The first step is to expand the "Advanced settings" and switch the crawler type.

Can you automatically sync content regularly?
You must manually initiate a re-sync in the AI knowledge center settings to update your content.

Can content from password-protected websites be synced?
No, only content from publicly accessible websites can be synced. Content from a protected site must also be made publicly available to sync.

What is the page limit for syncing per source?
Glassix can sync up to 100 pages per scan.

Advanced settings - general

Crawler type: choose "Static" if your webpage is based on classis HTML,CSS,JS combo. If your website is based on SPA (single page application - such as React, Angular, Vue etc') choose "Dynamic" option - that might be exporting better results.

Proxy type: Choose "Datacenter" option to scan your website from these 3 IP's: 107.175.80.80, 162.212.175.22, 107.172.69.119. This way - you can whitelist these IP's to ensure a successful scan of your website.
"Residential" option is using residential IP addresses in your current country.

CSS selectors to click on: Use this setting to specify which elements on the page the crawler should interact with. For example, elements like buttons, links, or dropdowns can be targeted. You can define selectors using attributes like aria-expanded="false" to target collapsible sections, class="question", class="FAQ", class*="accordion", and similar patterns.

CSS selectors to ignore: This setting allows you to exclude specific elements from the crawl, such as navigation bars, footers, and scripts.

Text to Ignore: text snippets that will be removed from the extracted results.

Advanced settings - full website scan settings

URL globs to include: Specify patterns or globs to include in the crawl. For example, you can use /products/** to ensure that only product pages or a specific section of your website are crawled. This helps focus the crawl on relevant parts of the site. You can test URL globs here

URL globs to ignore: You can define globs here to exclude certain URLs from the crawl, such as specific sections or file paths that don’t need to be scanned. For instance, if /products/** or certain directories should be skipped, add those here. You can test URL globs here

Max crawl depth: This setting controls how deep the crawler should go within your site’s link structure. For example: if set to 5 - the crawler will follow links up to 5 levels deep.

Max pages: This setting limits the number of pages the crawler will scan. Max 400 pages.

Use sitemaps: Enable this option if you want the crawler to prioritize scanning URLs listed in your website's sitemap.

Q&A

Q&A is an essential content type; it is accurate and concise, making it an ideal data source for the AI Chatbot to rely on for its answers. If you have a question that your customers ask repeatedly, add this question and answer as a Q&A. If the 80/20 rule applies to what your customers ask, a small number of questions is responsible for 80% of the overall volume of the questions. Add the frequently asked questions as Q&A content.

Files

PDF and Word files are another content source that Glassix AI Chatbot can consume. Upload a PDF/Word file, and the text content and images containing text will be scraped and made available for the AI Chatbot to use within minutes.

Snippets

Snippet is a simple, plain text - it comes in handy when you want to add new content like:

  • Canned replies: Using existing conversation canned replies.
  • Private knowledgebase: Information from knowledge bases that are not publicly accessible and cannot be imported into Glassix via the website crawler or as a file.
  • Bug/Issue Details: Specific bug or issue information that should not be searchable in your public knowledge base. Although not relevant to all customers, this information would be beneficial for the AI Chatbot in addressing specific customer inquiries.

For optimal results, we suggest breaking longer content, such as an FAQ list, into multiple snippets instead of uploading it as one long snippet. This approach helps the AI Chatbot learn and search through your content more efficiently.