> For the complete documentation index, see [llms.txt](https://replai-1.gitbook.io/replai-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://replai-1.gitbook.io/replai-docs/answers-and-grounding/how-answering-works.md).

# How answering works

## How answering works

Replai answers from connected content only.

It does not guess when the content cannot support an answer.

### How does Replai answer a question?

{% stepper %}
{% step %}

### Retrieve

Replai searches the connected sources first.

It pulls the passages most likely to answer the question.
{% endstep %}

{% step %}

### Rerank

Replai reranks the retrieved passages for true relevance.

This helps the strongest evidence rise to the top.
{% endstep %}

{% step %}

### Ground

Replai writes the answer from the connected content.

It does not invent product details, pricing, or policy terms.
{% endstep %}

{% step %}

### Cite

Replai adds citation chips for the strongest source pages.

These chips let the visitor open the original source.
{% endstep %}
{% endstepper %}

### What content can Replai use?

Replai can answer from any source attached to the assistant.

That can include GitBook, Website crawler content, and published Q\&A snippets.

{% hint style="info" %}
One assistant can use multiple sources.

One source can feed multiple assistants.
{% endhint %}

### What if the content conflicts or says too little?

Replai only answers from what it can support.

If the content is weak, missing, or conflicting, Replai declines instead of guessing.

### Related links

* [Citations](/replai-docs/answers-and-grounding/citations.md)
* [Honest decline](/replai-docs/answers-and-grounding/honest-decline.md)
* [Handoff & lead capture](/replai-docs/answers-and-grounding/handoff-and-lead-capture.md)
* [Sources overview](/replai-docs/connectors-sources/sources-overview.md)


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://replai-1.gitbook.io/replai-docs/answers-and-grounding/how-answering-works.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.