> For the complete documentation index, see [llms.txt](https://docs.storylane.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.storylane.io/repx-chat/training-repx/training-overview.md).
# Training overview
Learn how you can train RepX based on your product and website content.
RepX is not rule-based - you don't need to build workflows to handle every possible question from your website visitors, like you would with traditional sales chatbots. Instead, you connect your content and resources, and RepX leverages all of it to answer questions. \
\
From the Training section, you can add content that RepX can refer to or present, when it tries to answer questions. You can hand RepX the same material you'd give a new hire in your sales or SDR team - including:
1. your **website**,
2. your **decks**,
3. your best **sales call recordings or transcripts**,
4. **Storylane demos**, and
5. any **specific FAQs** that buyers ask which may not be answered clearly on the website.
There are two kinds of content you can add from the **Training** section in RepX:
* **Content RepX learns from:** this includes your webpages, docs, and FAQs. This is the knowledge RepX draws on to generate answers.
* **Content RepX presents:** your demos, images and videos. This is the visual material RepX can surface inside the conversation.
### How RepX generates answers
Every time a visitor sends a message, RepX does a few things in parallel to put together the best possible response:
1. **It finds the most relevant content to answer with.** RepX uses AI to pick the most relevant material from everything you've given it (your website, your documents, and your sales transcripts) to generate its answer based on your own information.
2. **It looks for something to show.** At the same time, RepX tries to identify the most relevant image, demo or video it can surface for the question being asked, so the visitor can also see something visual and interact with it, along with the answer.
3. **It carries the conversation forward.** In many cases RepX also passes along the history of the conversation, so each reply takes the full context into account rather than treating every message in isolation.
---
# 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://docs.storylane.io/repx-chat/training-repx/training-overview.md?ask=&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.
