> For the complete documentation index, see [llms.txt](https://help.gleantap.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.gleantap.com/ai-chatbot/train-ai.md).

# Train AI

The Train AI feature is where you can upload a CSV spreadsheet, link your website and add any additional verbiage to teach your AI Agent the specific information you want it to know.

If you have not set up the Basic Instructioins for your AI Chatbot, please start there. You can use [this article](/getting-started/configure-ai-chatbot.md) to guide you through the process. 

<figure><img src="https://312952119-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FaFKpjLzPT7iDAWD0tQXo%2Fuploads%2FXPSepTvCtaoCGy8qVKM3%2Funnamed%20(6).png?alt=media&amp;token=b29ae17b-97f3-443d-963e-e994ef01efa2" alt="" width="563"><figcaption></figcaption></figure>

**Steps to Train Your AI Agent:**

1. **Prepare Your CSV File**: Set up a spreadsheet with two columns. The first column should contain common questions, and the second should have the corresponding answers you’d like the AI to use. See examples below.
2. Upload the CSV file, add your URL and any additional verbiage in the Text area

<figure><img src="https://312952119-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FaFKpjLzPT7iDAWD0tQXo%2Fuploads%2FAF6PEFZNNFaZF405MFu0%2Funnamed%20(7).png?alt=media&amp;token=67e7cc19-1edb-4f3b-9870-4f46fc6c98f6" alt="" width="404"><figcaption></figcaption></figure>

CSV File examples to help you in your preparation process:

<figure><img src="https://312952119-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FaFKpjLzPT7iDAWD0tQXo%2Fuploads%2FdB5x0Y4YuU8U1RkHtSvY%2FScreenshot%202024-10-30%20at%202.08.36%20PM.png?alt=media&amp;token=c7b7e1b1-f3b8-4103-8045-6f9dda7a5ae5" alt=""><figcaption></figcaption></figure>

<figure><img src="https://312952119-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FaFKpjLzPT7iDAWD0tQXo%2Fuploads%2FijJt6kFUo9PkCNyD1HBc%2FScreenshot%202024-10-30%20at%202.14.40%20PM.png?alt=media&amp;token=b29f12b0-0fed-466a-b69d-4b6e01b61587" alt=""><figcaption></figcaption></figure>

<figure><img src="https://312952119-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FaFKpjLzPT7iDAWD0tQXo%2Fuploads%2FvMyigImS2xZrm8YMLE2c%2FScreenshot%202024-10-30%20at%202.11.29%20PM.png?alt=media&amp;token=88889e94-c66e-4c41-9f9f-66720a2525c8" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://help.gleantap.com/ai-chatbot/train-ai.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.