Training Your Chatbot on Your Content

3 min read Updated Aug 17, 2026 AI Chatbots

Your chatbot is only as good as its knowledge. The Knowledge page - opened from your widget's AI Agent tab - is where you feed it websites, documents, and curated Q&A, and where you continuously improve it from real visitor feedback. This guide covers every source type and the practices that produce accurate answers.

The Knowledge Page at a Glance

  • Sources - Website pages, sitemaps, and uploaded files the bot is trained on, with per-source status, retrain, and delete.
  • Q&A - Hand-written question/answer pairs that take priority for exact matters like pricing and policies.
  • Improve - Visitor thumbs-down feedback turned into training fixes (Admin/Manager only). Covered in Improving Response Quality.
Knowledge page showing trained sources with status, filters, and the Train All button

Adding Sources

Add Website (crawl)

Enter a starting URL and the crawler discovers and imports linked pages on the same site. Best for training on your whole site or a section like /help. Review the imported list afterward and delete pages that should not inform answers (careers, legal boilerplate, old blog posts).

Add Sitemap

Point at an XML sitemap (yoursite.com/sitemap.xml) to import exactly the URLs it lists. The most precise way to train on a large site - no crawler guesswork.

Add Page (single URL)

Import one specific page. Use it to top up training after publishing a new page without re-crawling everything.

Upload File

Drop in PDFs, Word documents, or text files - product sheets, internal FAQs, policy docs that are not on your website. Uploading a CSV of URLs bulk-imports every URL listed, which is the fastest way to train on a curated page list.

Training and Maintaining

Train

Click Train All after adding sources. Each row shows its status; large imports process in the background.

Retrain After Changes

Training is a snapshot - the bot does not see website edits until you retrain that source (the refresh icon per row, or Train All). Add "retrain the bot" to your content-publishing checklist.

Curate

Use the search, type filters (URL / file / sitemap), and sorting to audit what's trained. Download CSV exports the full source list; Remove All clears it when you want to rebuild from scratch.

Using Q&A Pairs

Q&A pairs are exact answers you write yourself, and the bot strongly prefers them when a visitor's question matches. Use them for:

  • Precision-critical answers - prices, refund windows, SLAs, compatibility - where paraphrasing from a web page risks drift.
  • Questions your site never answers directly - "Do you offer discounts for nonprofits?"
  • Corrections - when a transcript shows a wrong answer, a Q&A pair is the fastest permanent fix.

What Trains Well (and What Does Not)

Trains wellTrains poorly
FAQ and help center pagesPages that are mostly images or video
Product and pricing pages with real textContent behind logins or paywalls
Policy pages (shipping, returns, privacy)Heavily scripted single-page apps with no server-rendered text
Plain-text and document uploadsSpreadsheets of raw numbers with no context
Tip: Ask the bot in the Playground about a specific page after training. If it answers well, the page imported cleanly; if not, check that the page's text is server-rendered and retrain.

Frequently Asked Questions

How much content can I train on?

Training capacity scales with plan tier. Most teams need far less than they expect - 200 well-chosen pages beat 2,000 unfocused ones. See Chat Limits, Agent Limits & Usage.

Does the bot browse the live web when answering?

No. It answers from trained knowledge only, which is what keeps answers consistent and on-brand. That is also why retraining after content changes matters.

Can I train on a competitor's site or third-party docs?

Technically the crawler will import any public URL, but train only on content you have the right to use - and remember the bot will represent whatever you feed it as your answer.

Why does the bot miss content from a page I trained?

Most often the page renders its text with client-side JavaScript, so little text was imported. Check the page's "view source" for the actual copy; if missing, add the content as a file upload or Q&A instead.

Related Articles