> For the complete documentation index, see [llms.txt](https://docs.wonderchat.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.wonderchat.io/setup-guides/training-your-chatbot/training-on-custom-instructions-and-q-and-as.md).
# Training on Custom Instructions and Q\&As
How to train your AI chatbot on raw text and Q\&A information.
By adding raw text as a data source, you can directly paste FAQs, internal notes, policies, product descriptions, or any other written content into Wonderchat.
This gives your chatbot immediate access to custom knowledge, without needing a URL or file upload, and lets you keep answers accurate and fully tailored to your business.
***
### STEP 1 — Go to your Chatbot’s “Data Sources” Panel
* Log in to your account open your wonderchat chatbot page.
* Select the bot you want to edit, and click edit.
### Step 2 — Select “Add Raw Text” Option
* Click on “Data Source”
* Choose “FAQ”
### Step 3 — Upload Your Text Content
* Click on "Add" and text area will pop up.
* In the text area provided, paste or write your raw text content.
This can include:\
FAQs, knowledge-base articles, guidelines, Product descriptions, policies, internal documentation\
Markdown / plain-text copy, etc.
* NOTE: Add Q (for questions) and A (for answers)
* When you are done click on "Add text"
### Step 4 — Test the Chatbot
* After adding your raw text, ask a few sample questions relevant to that text to ensure the bot returns correct answers.
* If something seems off, you can edit the source, refine the text, or add more context.
