Pricing
News
Blog
Docs
  • EU-based company
  • Encrypted in transit
  • Data deletion on request
  • Real human support

Footer

CapterraG2
Breezaro on SaasHubBreezaro on SaasHub

Product

  • Pricing
  • Blog

Company

  • Contact

Legal information

  • Terms of service
  • Privacy policy
  • Cookies
  • Withdraw from contract

© 2026 Breezaro s.r.o. · All rights reserved

← Back to blog

How to build an AI chatbot for your website, step by step (2026)

Guides2 min readPublished June 23, 2026

A practical guide to building your own AI chatbot for your website, from creating it and training it on your own content to embedding it and testing. No developer, in minutes.

What you'll need

Before you start, get ready:

  • A website to put the chatbot on.
  • Content for the bot to learn from. Your website is enough, ideally a few documents too (FAQ, terms, price list).
  • Just a few minutes. You don't need a developer.

Step 1: Create a bot

Set up a bot and fill in the basics: a name, a short description (what you do) and a default language. The description helps the bot understand context, so be specific.

Step 2: Train it on your content

This is where the knowledge base the bot answers from is built. You have three options, and you can combine them:

  • Website crawl. Enter your address and the bot goes through the pages (descriptions, FAQs, info).
  • Document upload. PDF, DOCX or TXT with terms, a price list, guides.
  • Product feed, if you run an e-shop with an XML feed.

Tip: the quality of the answers equals the quality of the source material. Make sure the answers to your three most common questions actually appear in the content.

Step 3: Embed the widget on your site

Copy one line of JavaScript and paste it into your site template, just before </body>. Common systems (WordPress, Shoptet…) have a field for custom code.

Step 4: Test it

Open your site in an incognito window (so you're not logged in) and ask the bot:

  • your three most common customer questions,
  • one question the content doesn't answer, so you see how the bot behaves when it doesn't know.

If something is answered wrong, add or clarify the material.

Step 5: Monitor and improve

Once it's live, it pays to:

  • Review conversations. Where the bot struggled is a signal to add content.
  • Have an escalation plan. A live operator can take over the harder questions (from the Pro plan and during the trial).
  • Keep content up to date. When prices, deadlines or your range change, update the material.

Common mistakes

  • Too little content. The bot then answers generically. Start with your FAQ and key pages.
  • Forgetting to update. Old prices or deadlines mean wrong answers.
  • No plan for "I don't know". Be ready to take over the conversation.

Building an AI chatbot today is something anyone can do in minutes. The key isn't the technology, but good source material and keeping the content updated based on real questions.

Related: AI chatbots for customer support, the complete guide.

Related articles

Guides4 min read

AI chatbot for WhatsApp, which to pick and how to connect it (2026)

AI chatbot for WhatsApp, what unlocks AI replies in each tool and how to connect your bot through Meta's official flow, with no code. On Breezaro it answers from the same knowledge base as your website widget, a human can take over, and it is included from the Standard plan and the trial. Current as of 17 July 2026.

July 16, 2026
Guides4 min read

Why does an AI chatbot make things up, and how to fix it (2026)

AI chatbots sometimes invent answers ("hallucinate"). Here's why it happens with a bot that answers from your own content, and three practical fixes that reliably reduce it.

July 1, 2026
Guides3 min read

How does an AI chatbot work? (RAG explained simply)

A plain-English look at how a knowledge-base AI chatbot actually answers. It learns from your content, finds the passages relevant to each question, and writes an answer from them. No jargon.

June 27, 2026