# Data sources

URL: https://aihio.ai/en/help/ai-agent/knowledge\
Description: Add, inspect, and keep your AI agent’s data sources up to date in one view.

In Data sources, you manage the content your AI agent uses in its answers. Each website, file, question and answer, or text is one data source. Together, these sources form the agent's knowledge base.

> **Note — Changes are saved as drafts first:**
>
> New or edited content becomes available to the agent only after you choose
> **Update knowledge base** and publication succeeds. Previously published
> content remains available during the update.

Adding a data source does not train the underlying model. The agent uses the content you add as the basis for its answers.

## How Data sources works

Your daily work happens on one page:

1. See the latest knowledge-base update, automatic refresh setting, and usage at the top of the page.
2. Add a source from one of four source cards.
3. Search, filter, and open existing sources in one list.
4. Inspect, edit, and test a selected source in the panel on the right.

## What you can add

| Data source         | When to use it                                          | Example                                   |
| ------------------- | ------------------------------------------------------- | ----------------------------------------- |
| Website             | Content is public and maintained on your website        | Service pages, pricing, and help articles |
| File                | Information is in an existing document                  | PDF brochure, DOCX guide, or spreadsheet  |
| Question and answer | You need one controlled answer to a customer question   | Delivery time and its approved answer     |
| Text                | Content is short and does not need its own file or page | Special opening hours or campaign terms   |

Choose the format that is maintained most reliably. If content changes on a website, add it as a website. If it lives in an internal guide, upload a file or add a text source.

## Add a website

Choose **Website**. The panel offers three ways to add content:

- **Fetch links** discovers pages for you to review.
- **Use sitemap** uses a sitemap URL when one is available.
- **Single page** adds one exact URL.

1. **Enter an address**

   Enter the full website or page URL, for example `https://company.com`.
2. **Refine if needed**

   Check advanced settings before fetching if you need more control.
   Otherwise, continue to selecting content.

   **Path filters, query parameters, and fetch speed**

   Open advanced settings to exclude paths, handle query parameters, or slow
   down fetching.
3. **Choose content**

   After discovery, search and review the found URLs, select relevant pages,
   and exclude anything unnecessary.
4. **Save the selection**

   Save the pages you selected.

   **Expected result:** the selected sources are saved as drafts.
   Publish the changes under [Update the knowledge base](#update-the-knowledge-base).

> **Tip — Choose quality before quantity:**
>
> Add the most important service, pricing, help, and delivery pages. Archives,
> tag pages, campaign pages, and pages with little content can make answers less
> reliable.

## Add a file

1. Choose **File**.
2. Drop files into the upload area or choose them from your computer.
3. Follow the upload queue in the panel. Review file-specific errors; you do not need to restart the entire upload.

Supported formats are PDF, DOCX, TXT, Markdown, CSV, and HTML. The old `.doc` format is not supported; convert it to DOCX or PDF first.

If processing fails, check the format, size, and protection. A scanned PDF may look readable to a person while containing an image instead of machine-readable text.

## Add a question and answer

Choose **Question and answer** when you need one controlled answer for one or more customer phrasings. Give it a clear title, add questions in the customer’s own words, and format the answer in the editor.

A good question and answer:

- uses natural customer language;
- answers one subject at a time;
- includes relevant conditions and limits;
- does not conflict with other data sources.

**Import questions and answers from a spreadsheet**

To add multiple ready-made questions and answers, choose **Import from spreadsheet**.
Review the guided import's preview and row-specific errors before saving.

## Add text

Choose **Text**, give the content a title, and write it in the editor. The editor shows formatted content as it will be saved and the text size in relation to the limit.

Text is useful for special opening hours, campaign terms, or short information that is not yet on your website. Keep one text source focused on one topic; create separate sources for separate topics.

## Search, filter, and open a data source

The source list brings every data source together. It shows the source name, type, status, content amount, and last update.

- Use search to find a title or URL.
- Filter by data-source type or status.
- Open a data source from its name to see its details.
- If you have management permission, you can select multiple sources for shared actions.

On mobile, the same information is shown in compact source cards so that important status and actions remain easy to read.

## Inspect a source in the drawer

When you open a data source, the panel on the right includes these views as appropriate for the source type:

| View            | What you can do                                                       |
| --------------- | --------------------------------------------------------------------- |
| Overview        | Check status, content amount, errors, and the latest update           |
| URLs or Content | Inspect website pages or edit text and question-and-answer content    |
| Test search     | Try a customer question to see whether the right information is found |
| Settings        | Manage source-specific settings and recover from errors               |
| History         | Review earlier source updates and their outcomes                      |

For a website source, you can restore an excluded URL, remove a URL from the knowledge base, or retry a failed URL when needed.

## Update the knowledge base

**Update knowledge base** publishes pending data-source changes for the AI agent on every plan.

1. Choose **Update knowledge base**.
2. Follow the current stage, processed source count, and any failed or skipped sources in the update panel.
3. Review the completed update's result on the same page. Then try an important customer question in **Test search**.

**Expected result:** successfully published content is available to the agent.

> **Warning — Check failed sources too:**
>
> An update can succeed only in part. Successful changes are published. A failed
> source's previously published content remains in use if it exists; a new
> source is unavailable until publication succeeds. Open the errors, fix their
> cause, and retry the failed sources.

**Automatic refresh** updates website sources weekly on Starter, Pro, Business, and Enterprise plans. Free uses manual updates. File, question-and-answer, and text changes are always published with the manual **Update knowledge base** action.

## Understand statuses

| Status          | Meaning                                                        | What to do                                                  |
| --------------- | -------------------------------------------------------------- | ----------------------------------------------------------- |
| Ready           | Content is available in search                                 | Test important questions before publishing                  |
| Processing      | Content is being fetched or prepared                           | Wait for completion; ready content remains available        |
| Needs attention | Some content did not finish processing                         | Open the source, review the error, and retry if appropriate |
| Needs update    | Content may be out of date                                     | Update the knowledge base or review source settings         |
| Skipped         | Content was not added because it did not meet quality criteria | Choose a more useful or content-rich source                 |

## Before publishing

- Essential service, pricing, delivery, and contact content is ready.
- Outdated or conflicting data sources have been archived or corrected.
- Necessary repeated questions and answers have been added.
- You have tested natural customer questions in **Test search**.
- Someone owns data-source maintenance when company information changes.
## Next steps

- [Publish](/en/help/ai-agent/publish) — Publish an AI agent as a chat widget or an embedded conversation.
