Summary
Training a chatbot on your data means connecting your help center, docs, and files so it looks up each answer there. No model gets retrained.
Pick your route first. Your data, your comfort with code, and where the chatbot will live decide the tool.
Clean before you connect. The failure Wonderchat’s support team sees most is an old policy page answered correctly.
Test with your most common questions and one your docs can’t answer, then open every source.
You don’t retrain a model to train a chatbot on your own data. You connect the content you already have, like your website, help center, PDFs, and Google Drive, and the chatbot looks up the answer there every time someone asks.
With a no-code tool, the setup takes six steps. Connect your site, add your files, set the role, set handover rules, test, and go live.
The hard part is the confident wrong answer a customer sees before you do. The version worth building is an AI customer service agent that shows its source and says when it doesn’t know.
What Training AI on Your Own Data Means (RAG vs. Fine-Tuning)
Most no-code tools use retrieval-augmented generation. When a question comes in, the tool searches your content, pulls the passages that match, and the model writes the answer from them.
Fine-tuning is the other meaning of “training,” and a support team rarely needs it. OpenAI’s own guide to optimizing accuracy describes retrieval as giving the model “domain-specific context” and fine-tuning as teaching it a task so it performs “consistently and reliably.”
Retrieval (connect your content) | Fine-tuning (change the model) | |
|---|---|---|
What changes | Nothing in the model. Your pages are searched when a question arrives | The model itself, trained on example answers |
How you fix a wrong answer | Edit or replace the page | Prepare new examples and train again |
Can it show the page it used? | Yes, when the tool cites its source | Not by itself. What it learned isn’t tied to a page |
A grounded answer stays inside what you connected, and a source link lets you check it in one click.
Wonderchat answers only from what you connect and shows the source on every reply, with web and PDF-page citations. So “chatbot training data” here means your own pages and files, not a labeled dataset.
Asked how to add a website, the agent lists the steps and the pages behind them, with a person one click away.
No-Code Tool or Python Script? Three Questions to Pick Your Route
Three answers decide the tool before you compare a single feature.
Question | Pick a no-code tool if | Build it yourself if |
|---|---|---|
What data are you training it on? | Your answers live on your website, in a help center, in PDFs and Office files, or in Google Drive | Your answers live in an SQL database or an internal system that changes every day |
Do you want a dashboard or a Python script? | You want to connect, test, and publish without code | A developer wants custom actions, its own hosting, or its own retrieval rules |
Where will the chatbot live? | A website widget, Slack, Microsoft Teams, WhatsApp, or another chat channel | Inside your own product, behind your own interface |
If your data sits in a database but rarely changes, export the table to CSV and upload it as a file, no code needed.
If a developer is part of the plan, you can build a RAG chatbot yourself and control every part of the retrieval.
As for where it lives, Wonderchat’s website widget, search bar, and live chat are on every plan, Free included. Slack and WhatsApp open from the Starter plan, Microsoft Teams from the Basic plan, and the same answer, with its source, shows up in each one.
How to Prepare Your Docs Before You Connect Them
Run two checks before you connect anything, one for pages that are no longer true and one for pages that disagree or that the chatbot can’t read.
First: Remove Outdated Pages and Old Policies
Wonderchat’s support team sees one failure more than any other, and it isn’t invention. It is retrieval pulling an archived policy and answering from it correctly.
The agent did its job. It found a page, quoted the text faithfully, and cited the source, but the page was no longer true.
Picture a refund policy from two years ago, still live at an old URL next to the current one. A customer asks about refunds and gets the old terms, with a source link that looks official.
The chatbot quoted the old page correctly and cited it, so the answer looked right and was wrong.
Before you connect anything, find and remove:
retired prices and plan names
expired policies and old terms of service
release notes that read like current rules
pages for products or features you no longer offer
If an old page has to stay live for your records, add it under “Ignore URLs” when indexing in the Data Source instead. An asterisk at the end, like yourdomain.com/archive/*, covers a whole folder.
Wonderchat’s docs note that a deleted page can come back after a re-crawl, while an ignored URL is never crawled again.
Second: Merge Conflicting Pages and Move Text Out of Images
More pages aren’t always better. Zendesk’s own help center warns that “having lots of sources can in some cases lead to reduced accuracy and increased latency.”
Two pages that answer the same question differently force the chatbot to pick one. Merge them, or decide which one is right and retire the other.
Then check the format.
Wonderchat’s documentation guide says it “reads text-based information best,” so text locked inside screenshots can lose its context. Put the text on the page itself.
How to Train an AI Agent on Your Own Data in Six Steps
The steps below use Wonderchat’s settings as the worked example. Most no-code tools follow the same order.
Before you start, have your help center address, the files customers ask about, and a list of your ten most common customer questions ready.
Connect your website and help center.
Add your files and Google Drive.
Set the role, tone, and fallback message.
Set when the agent hands over to a person.
Test the agent in the preview.
Add the agent to your website and channels.
1. Connect Your Website and Help Center
Paste the address of your site or help center, and the tool reads the pages. In Wonderchat, open your agent and go to Data Source.
Your site goes in as a root URL, and any page on the ignore list stays out of answers.
An asterisk at the end, like yourdomain.com/*, decides how much gets added.
What you enter | What Wonderchat adds |
|---|---|
help.yourdomain.com/* | Every page of your help center |
yourdomain.com/* | Your whole site |
yourdomain.com/pricing | That one page only |
Start with the help center, because it’s already written to answer customer questions. Most no-code tools, often sold as a free AI chatbot builder, begin there too.
Each self-serve plan caps the pages per agent, at 100 on Free, 200 on Starter, 1,000 on Basic, and 2,000 on Scale. If your whole site runs past the cap, connect the help center and the pages customers ask about, and leave the blog out.
Website and help center pages are open on every Wonderchat plan, Free included.
If your help center sits behind a firewall or bot protection, allow requests that carry the header below. Wonderchat’s technical FAQ recommends it over allowlisting IP addresses.
X-Wonderchat-Identifier: Wonderchat-Prod
2. Add Your Files and Google Drive
Upload the files that hold answers your site doesn’t, like PDFs, Word, PowerPoint, Excel, CSV, and text files.
Files and Google Drive sit next to your website as sources, so one agent answers from all of them.
Match each source to the answers it holds.
Source | What it’s good for | Plan |
|---|---|---|
Files (PDF, Word, PowerPoint, Excel, CSV, and text) | Public price lists, onboarding guides, product sheets, and database exports | Every plan |
Google Drive | Folders your team already keeps current | Every plan |
SharePoint | Docs your team keeps in Microsoft 365 | Scale |
Audio files | Recorded webinars and training calls | Scale |
To connect Google Drive in Wonderchat:
Open Settings → Integrations, find the Google Drive card, and click Connect.
Sign in with the Google account that owns your Wonderchat subscription. A teammate’s own Drive can’t be added to the plan.
Open your agent, open More in Data Source, choose Google Drive, select the files, and click Update.
Only connect what you’d let a customer read. An internal pricing sheet sitting in the same folder can end up in an answer.
Before you upload, check each file for three things:
text you can select, not a scanned image of a page
one current version, with older copies out of the folder
no internal notes, draft prices, or customer data
If the files are sensitive, check where they’re stored. Wonderchat is EU-hosted in Frankfurt, with SOC 2 Type II, GDPR, and a HIPAA BAA available.
3. Set the Role, Tone, and Fallback Message
Tell the agent who it is and how to sound. Wonderchat’s controls cover role and tone, creativity (precise, balanced, or creative), preset messages, and a consent checkbox before chatting.
In Wonderchat, the role and its instructions sit under Model & Behavior in the agent editor. Pick the Customer support role, or start from the instructions below.
You are the support assistant for [Company].
Answer only from the connected help center and docs, and link the page you used.
Keep answers short and plain.
If no page covers the question, say you can't find it and offer to connect the customer with the team.
Never state a price, refund term, or date that isn't on a connected page.
The AI model is a setting too, from OpenAI, Anthropic, Google, or DeepSeek, and answers still come only from your content. The Free plan runs fast models, and Basic and Scale add frontier models.
Set the greeting and the fallback message as well.
Setting | What to set | Example |
|---|---|---|
Role | Who the agent is and who it serves | A support agent for your billing app |
Tone | How it sounds | Plain and brief |
Creativity | Precise, balanced, or creative | Precise, for support answers |
Greeting | The first line a visitor sees | “Ask me anything about billing. I’ll answer from our help center.” |
Fallback message | The reply when no page covers the question | “I can’t find that in our docs. Want me to connect you with the team?” |
The fallback message matters most, because it’s what a customer reads when the docs run out.
The fallback message covers questions your docs don’t, and source links and precise wording keep the other answers checkable.
4. Set When the Agent Hands Over to a Person
Decide when a person takes over. Wonderchat hands over with the full conversation attached, on any of three rules.
Here’s what each rule covers.
Handover rule | When it starts a handover | How to set it |
|---|---|---|
Direct request | The customer asks for a person or types “live chat” | Under Handover, turn on Enable Human Handover and When user asks to escalate his request to a human |
Number of messages | After a set number of messages in one chat | Turn on After user has sent and set the number of messages, for long chats that don’t reach an answer |
Failed answers | After the agent fails to answer a set number of times | Turn on After chatbot fails to answer and set it low, so a customer isn’t left stuck |
The agent can also collect an email so your team can follow up when nobody is online. Handovers land in Wonderchat’s help desk as tickets with the full chat, or in live chat, both on every plan.
In Wonderchat, the rules sit under Handover and Live Chat in the agent editor, with handover email addresses under Handover and your team’s online hours under Live Chat.
Any trigger you turn on opens the handover form, so a customer doesn’t have to hunt for a person.
Teams on Zendesk or Freshdesk can keep them, with ticket sync from the Basic plan (up to 50 tickets until Scale), so use Wonderchat’s help desk or keep yours.
5. Test the Agent in the Preview Before You Publish
Run the four-question test in the section after step 6 before any customer sees the agent, while you can still fix what it gets wrong.
In Wonderchat, open the agent and ask your questions in Real time preview of your chat widget on the Profile page, or click Preview Widget in the top bar.
Asked about a Swiss franc bank transfer that no page covers, the agent says it doesn’t know, asks for an email, and offers a live agent.
6. Add the Agent to Your Website and Channels
Share a hosted link first, then add the widget with one snippet, pasted where your analytics code goes. The widget is on every plan, Free included. Slack and WhatsApp open from the Starter plan, and Microsoft Teams from the Basic plan.
Your team tries the hosted page from Share Link first, and Install has the snippet for your site.
In Wonderchat, follow the same order:
Click Share Link in the agent editor’s top bar, and send the hosted page to your team to try.
Click Install, copy the snippet, and paste it into your site’s HTML just before the closing </body> tag.
Open your site on a desktop, a tablet, and a phone, and ask one question on each.
In a typical page, the snippet sits here:
<!-- your analytics code -->
<!-- paste the Wonderchat snippet from Install here -->
</body>
</html>
Wonderchat’s docs have install guides for WordPress, Wix, Webflow, Shopify, and Drupal. On WordPress, the snippet goes in the Scripts in Footer box of the Header and Footer Scripts plugin.
Set your expectations from real numbers. 80% of Wonderchat agents that go live do so the same day (384 of 478), while knowledge bases over 500 pages take a median of 15 days, so give a large help center more time.
When you’re ready to grow past the free plan, see plans for what each one includes.
Test Your AI Agent the Way Your Customers Will
Whatever a tool calls training, the test that matters is the question your docs can’t answer. Ask four questions, in this order:
The question customers ask most.
The second most common one.
A pricing, refund, or policy question, where a wrong answer costs you.
One plausible question your docs don’t cover, asked on purpose.
For the first three, open every source link and check that the page says what the answer says. For the fourth, a pass is a clear “I can’t find that” with a person offered, never a guess.
An honest “I can’t find that” is the fallback message you set in step 3. When no page covers a question, Wonderchat sends it instead of guessing and offers a person.
| What you ask | A pass looks like | A fail looks like |
|---|---|---|
| Q1, Q2 · Your two most common questions, asked the way customers ask them | A correct answer, with a source link to the page that says it | No source, or a source page that doesn’t say it |
| Q3 · A pricing, refund, or policy question, where a wrong answer costs you | The current policy, from the current page | An old policy, quoted correctly from an archived page |
| Q4 · A question your docs don’t cover, plausible and asked on purpose | It says it can’t find that, doesn’t guess, and offers a person | A confident answer that no page supports |
Sourced answers to your common and policy questions, plus an honest “can’t find that” for the fourth, mean the chatbot is ready.
How to Keep Your AI Agent’s Answers Up to Date
Every question the agent can’t answer points to a missing or outdated page. In Wonderchat, those questions land in one review inbox, sorted into user-reported answers, knowledge gaps, quick fixes, conflicts, and model issues.
Your team fixes each one once. Open the item in Review, go to Where does the answer live?, and paste the URL, pick a file, or write the answer so the agent uses it from then on.
For answers that don’t belong on a page, add a correction. A correction is an approved question and answer the agent uses next time for questions with the same meaning or an exact match.
Wonderchat retrains on your website every month on Starter and Basic and every week on Scale. On Free, run a manual recrawl after you change a page.
Stale answers are a real complaint. Across 1,309 complaints in reviews of 18 vendors, which Wonderchat read in September 2026, stale knowledge accounted for 38.
How to Train an Internal AI Agent on Google Drive or SharePoint
The same steps work when the people asking are your team. Wonderchat’s Internal AI Agent, a separate product built and deployed with you through sales, answers them in Slack or Microsoft Teams.
Customer service agent | Internal agent | |
|---|---|---|
Who asks | Customers | Your team |
Where it answers | Your website, plus Slack and WhatsApp from Starter and Microsoft Teams from Basic | Slack or Microsoft Teams |
What it reads | Website, help center, files, Google Drive, SharePoint | Google Drive or SharePoint |
Cleanup matters even more inside a company, because internal folders keep drafts, old versions, and private files side by side. Connect the folders that hold current, approved answers, and remember that SharePoint needs the Scale plan.
When Chatbase or Botpress Is the Better Choice
On usage per dollar, Chatbase comes out ahead on paper. On 15 October 2026, its paid plans listed more message credits for the price than Wonderchat’s plans list AI replies, though the two meters don’t count the same work.
Chatbase’s gap tool, Backstage, comes with a draft of the fix for each gap. Wonderchat doesn’t draft pages, so your team writes the answer once.
Botpress is the better pick for a team with a developer who wants to build its own logic. The flexibility is worth the extra setup only when someone on the team will own the build.
How Wonderchat Answers From Your Own Docs
Training a chatbot on your own data comes down to two habits, connecting clean pages and testing the question your docs can’t answer. Wonderchat is built around both.
A customer asks how to export their data, and the agent answers from your help center page with the link. Another asks about a discount you never wrote down, so the agent says it can’t find that, offers a person, and hands over the whole conversation.
The discount question lands in the review inbox, where your team answers it once. The free plan refills 50 AI replies every month with no credit card, so start for free and run the four-question test on your own help center, or book a demo to see it on your docs.
Frequently Asked Questions
Can I train ChatGPT with my own data?
Yes, with a custom GPT. OpenAI says Knowledge “lets your GPT use information from files you upload,” up to 20 files of 512 MB each. For a custom GPT for business, where customers ask on your website, you’ll also want source links and a handover to a person.
How do I train AI on my own data for free?
Start with a tool that has a free plan, and connect your help center. Wonderchat’s free plan refills 50 AI replies every month with no credit card, which is enough to run the four-question test before you pay anything.
How do I program my own chatbot?
With code, you choose a model, a way to search your documents, and a chat interface, then connect them yourself. Without code, a no-code tool handles all three. You connect your content and set the rules.
Will a chatbot trained on my docs make things up?
A chatbot trained on your docs can still be wrong, usually by answering from an outdated page. Pick a tool that answers only from your content, shows the source on every reply, and says when it can’t find an answer.
How long does it take to train a chatbot on my data?
Usually the same day. 80% of Wonderchat agents that go live do so the same day, while knowledge bases over 500 pages take a median of 15 days to go live.
