What type of site crawl is best for you? Learn how to gather website information to power your chatbot.
In this article
Site crawls
💡 Use Site Crawl to bring in all available information from your site at once.
- Paste in the URL of your website
- We’ll automatically scan the text and extract content from on-page text and PDFs.
RSS feeds
💡 Use the RSS Feed option to connect event-related or time-sensitive content. Ideal for sites with frequently updated calendars or announcements.
- Paste in your RSS feed URL.
- We’ll pull in information like event names, dates, times, and locations.
Custom URLs
💡 Great for curated content strategies or partial site ingestion.
Use Custom URLs when:
- You want to enter a few URLs manually
- You have content spread across multiple domains or microsites
- You have a list of important pages to add via Excel upload
You can either:
-
Manually enter individual URLs
-
Upload an Excel file with all URLs listed in a single column
File crawls
💡 Perfect for internal manuals, onboarding guides, or product specs.
Use the From Files option when you have documents you want the chatbot to learn from:
- Upload PDFs, text files (.txt), or Word documents (.docx)
- We’ll extract the content and make it available to the chatbot for response generation
💡 Why this matters: All of these options help ensure your chatbot is pulling from reliable, relevant information—whether it’s live on your site, sitting in a document, or published in an RSS feed. The better the crawl, the better the answers.