# How to train a chatbot on your website

> How training an AI chatbot on your website works, which pages to include and leave out, how to test it with real questions, and how to keep it current.

Canonical: https://heykiko.io/blog/how-to-train-a-chatbot-on-your-website
Last updated: 2026-11-05

AI agent guides · by The HeyKiko team · published 5 November 2026 · 8 min read

Training a chatbot on your website means giving it your pages to read so it answers from them. It reads the text, splits it into short passages, and when a customer asks something, it finds the passages that fit and answers from those. You don't need code: the work is choosing the right pages, adding what your site doesn't say, and testing with the questions your customers really ask.

## What “training” actually means

The AI model itself isn't retrained on your site. Instead, most website chatbots, HeyKiko included, work like this:

1. **Read**: Each page's text is fetched, without menus, footers and code.
2. **Split**: The text is cut into short passages, so an answer can use just the part that matters.
3. **Index**: Each passage is stored in a way that can be searched by meaning, not just by matching words.
4. **Search**: When a customer asks, the passages closest to their question are found, often by searching several ways at once.
5. **Answer**: The model writes a reply from those passages, and can say which page it came from.

This is why a change to your website reaches the chatbot only once the page is read again, and why the chatbot can only be as right as the pages it reads.

## Which pages to include, and which to leave out

Website pages to give a customer-service chatbot, and pages to leave out

|  | Include | Leave out |
| --- | --- | --- |
| Selling | Services, products, prices, plans | Old promotions and expired offers |
| Help | FAQ, delivery, returns, warranty, how-to articles | Release notes nobody asks about |
| Contact | Opening hours, locations, how to book | Careers and team bios, unless customers ask |
| Policies | Terms customers ask about, such as refunds | Pages behind a login, admin pages |

An out-of-date page is a common cause of wrong answers. Our own agent tests keep an archived page with last year's delivery fee next to the current one, because it's exactly the trap a real website sets. Remove or unpublish old prices rather than leaving them for the chatbot to find.

## Step by step

1. **Find your pages**: Your sitemap lists them: usually yoursite.com/sitemap.xml. It's the standard file websites use to tell search engines which pages exist, and most chatbot builders read it first. [Sitemaps.org: protocol](https://www.sitemaps.org/protocol.html)
2. **Import and choose**: Give the chatbot your address, then untick the pages from the leave-out list above.
3. **Add what your site doesn't say**: Price lists, menus, brochures and policies that live in PDFs or documents, uploaded as files. Many builders, HeyKiko included, don't follow links to PDFs on your site, so upload those.
4. **Test with real questions**: Twenty questions your customers really ask, including a few your site doesn't answer (see below).
5. **Fix the source**: When an answer is wrong, change the page or file it came from rather than adding a rule to the chatbot's instructions.
6. **Keep it fresh**: Have it read your site again on a schedule, such as weekly, so a new price is picked up without you remembering.

## Write pages that answer well

- Put the number in the sentence: “Delivery is $49, free on orders of $1,500 or more” answers better than a table cell with no context.
- Say the exception next to the rule. “Clearance items can't be returned unless damaged” stops the chatbot promising a refund it shouldn't.
- Keep text as text. A price that only appears in an image, or a scanned PDF with no text layer, gives most chatbots nothing to read; HeyKiko doesn't read text inside images.
- One topic per page or section, with a clear heading, so the right passage is easy to find.
- Write how your customers talk. If they say “refund”, don't only say “reimbursement”.

## What a chatbot can't learn from your website

- Anything live: stock levels, an order's status, today's open slots. These need a connection to your systems, such as [your database](https://heykiko.io/features/database-answers) or [your calendar](https://heykiko.io/features/appointment-booking).
- Anything not written down. If your team “just knows” it, write it in a page or a document first.
- Pages a site hides from automated readers. Some sites block bots or build their pages only in the browser. A robots.txt file asks crawlers to stay away from parts of a site, and well-behaved ones listen. [Google: robots.txt](https://developers.google.com/search/docs/crawling-indexing/robots/intro)

> When HeyKiko can't find a site's pages because the site blocks page finders, it checks the home page in a real browser and tells you, so you can add the other pages by hand.

## How to test it before customers do

Ask a mix like this, and check where each answer came from:

Kinds of test question for a website chatbot, with what a good answer does

| Kind | Example | A good answer |
| --- | --- | --- |
| A plain fact | How long do I have to return something? | Gives the number from your returns page |
| An exception | Can I return a clearance item? | Applies the exception, not the general rule |
| Two pages at once | What does delivery to an island cost on a big order? | Combines the free-delivery rule and the surcharge |
| Not on your site | Do you price match? | Says it doesn't know and points to your team |
| Another language | The same question in your customers' other language | Answers in that language, from the same pages |

An answer that invents a policy for the “not on your site” question is the one to fix first: tell the chatbot to admit what it doesn't know, or hand the chat to a person.

## Doing it in HeyKiko

In HeyKiko you type your website address, choose the pages, and set how often they're read again: daily, weekly, monthly or never. Files can be PDF, Word, Excel, CSV, text and Markdown. The Playground shows which source each answer used, and every page shows how many answers it has supplied. See [training on your website and files](https://heykiko.io/features/train-on-your-website) and [testing your agent](https://heykiko.io/features/test-your-agent).

> You can try it on your own website free for 14 days, with no card.

## Sources

Checked on 5 November 2026. We make HeyKiko, which this guide uses as its example.

- [Sitemaps.org: the sitemap protocol](https://www.sitemaps.org/protocol.html)
- [Google Search Central: robots.txt introduction](https://developers.google.com/search/docs/crawling-indexing/robots/intro)

## Questions people ask

### How do I train a chatbot on my website?

Give it your website address and choose which pages it should read. It reads their text, splits it into passages and answers customers from the passages that fit. Then add files for anything your site doesn't say, and test it with real customer questions.

### Do I need to code to train a chatbot on my website?

No. Website chatbot builders read your pages for you. You choose the pages, add documents, and test the answers.

### Is the AI model retrained on my website?

Usually not. Most website chatbots search your pages for each question and answer from what they find. That's why a change to your site reaches the chatbot once the page is read again.

### How often should the chatbot read my website again?

As often as your prices and policies change. Weekly suits most businesses; daily suits a site that changes every day.

### Why does my chatbot give wrong answers?

Most often because a page is out of date, two pages disagree, or the answer only appears in an image. Fix the page the answer came from, then ask again.

### Can a chatbot read PDFs on my website?

Some do. Many builders skip links to PDFs, so upload important PDFs as files. A scanned PDF with no text layer can't be read at all.

### Can a website chatbot check stock or order status?

Not from your pages, which aren't live. It needs a connection to where that data lives, such as your database.

## Related

- [Train an AI chatbot on your website and files](https://heykiko.io/features/train-on-your-website)
- [Test and tune your agent](https://heykiko.io/features/test-your-agent)
- [Website AI chatbot](https://heykiko.io/channels/website-ai-chatbot)
- [Human hand-off](https://heykiko.io/features/human-handoff)
- [All guides](https://heykiko.io/blog)