> This page is for version Scripted.
> For other versions, use one of these documentation indexes:
> - Generative (default): https://developers.ada.cx/generative/llms.txt
> - Scripted: https://developers.ada.cx/scripted/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://developers.ada.cx/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://developers.ada.cx/_mcp/server.

# Let chatters search your knowledge base content

> **Info**
>
> This guide is for organizations that have knowledge bases that can serve
> content via API.
>
> If you use Zendesk Guide or Salesforce Knowledge, you can use Ada’s
> Article Suggestions feature, which automates knowledge base search for
> those tools. See [Let chatters search your Zendesk or Salesforce knowledge base content](/scripted/docs/use-ada-with-your-website/serve-your-website-information-in-chat/let-chatters-search-your-zendesk-or-salesforce-knowledge-base-content)
> to set up Article Suggestions.

## Overview\[#UUID-88ad738c-92b5-f11c-3095-f80a134b855d_id_360053500593_id_h_01EGR9JT0AE0XKQ4T9WD8XYFD2]

With use of the HTTP Request block, your bot can provide curious
chatters with a list of relevant articles from your knowledge base.
Knowledge Base Search is a graceful fallback when a question falls
outside of your bot’s training and helps chatters get access to more
information as soon as it becomes available.

## Requirements\[#UUID-88ad738c-92b5-f11c-3095-f80a134b855d_id_360053500593_id_h_01EGR9K1FQ5X66SDJ902YJEKG9]

In order to set up the Knowledge Base Search, you will need:

* [HTTP Request block](/scripted/docs/build-and-maintain-your-bot/work-with-blocks-and-apps/make-api-requests-using-the-http-request-block)

* [Conditional block](/scripted/docs/build-and-maintain-your-bot/work-with-blocks-and-apps/target-content-to-chatters-using-the-conditional-block)

* A knowledge base solution with an API

## Set up the Request block for the knowledge base fallback\[#UUID-88ad738c-92b5-f11c-3095-f80a134b855d_id_360053500593_id_h_01EGR9K84SH7742XFP9FDG0SRV]

> **Note**
>
> We have chosen to use a Not Understood Answer to host the HTTP Request
> block, but a similar flow can be set up in any other Answer.

Follow the steps below to ensure that when a “Not Understood” Answer is
surfaced, your bot will respond to the chatter with 3 relevant support
articles.

1. Open up your “Not Understood” Answer.

   ![](/_fern-files/_img/d1c9b093805b9a29a21eda0585b0d08cee82d49baadd27f870e6130401ef4647.webp)

2. Insert the HTTP Request block into your Not Understood Answer, just
   below the Text block.

3. Add the knowledge base endpoint API in the URL section.

   For example, if you were using the Zendesk Guide API, the endpoint
   you would use is:

   `https://SUBDOMAIN.zendesk.com/api/v2/help_center/articles/search.json?query=`

   You would include *your* specific subdomain in the URL. For more
   information on this step, see [Admin's guide to the Zendesk API](https://support.zendesk.com/hc/en-us/articles/4408827565338) in
   Zendesk's documentation.

   If you are using a different knowledge base, insert the API endpoint
   that applies.

   ![](/_fern-files/_img/8d0ca4d5725a29b0eb428d2bcda0ca21dc8ccffef0873e886332dd26b194b27d.webp)

4. To ensure your bot surfaces articles directly related to the
   chatter’s question, insert a metavariable for *last_question_asked*
   in the URL. For a refresher on variables, check out [Use variables in Answers](/scripted/docs/build-and-maintain-your-bot/personalize-conversations/use-variables-in-answers).

5. Next, choose a basic Error Answer, with a message such as “Try again
   with different words.” This error message will only be served if
   there is an error in the flow configuration.

   ![](/_fern-files/_img/c0fa38e50e4a22d84fc0ab022183471bf66c4949ef48a38b19e6a3f8eded47ba.webp)

6. In the **Save as Variable** section, you’ll need to create and
   insert the Variables that will help surface 3 articles to the
   chatter. Each article requires a variable for the article URL. You
   will need to manually create three variables by clicking the green
   plus button. Please copy the example we have provided below.

   ![](/_fern-files/_img/c21e011ed8d589cab48acd789439c718be871df5ca8907bc0f714d84673bfb36.webp)

   The variables you will need are:

   * html_url

   * html_url2

   * html_url3

   In the **Data Key** section, you’ll need to mirror these inputs:

   * results\[0].html_url

   * results\[1].html_url

   * results\[2].html_url

7. Next, add in 3 Conditional blocks.

   1. For the first condition and value the variable should meet, set
      it up so that the *html_url* variable is *not null*. This means
      that if at least the first article is surfaced from the API
      call, this flow will proceed.
   ![](/_fern-files/_img/31d27aa22617387febf910ad21a7c4b9be381951e0f04dd0815e808999b2383f.webp)
   3. Within the first Conditional block, insert the Link Message
      block.
   4. In the URL field, insert the variable for *html_url*. The link
      text and the title will be auto-generated.
   5. Make sure that **Generate Preview** and **Open in a New Window**
      are both toggled on.
   6. Next, you will need to insert a fallback message after this
      initial block. This message will only be served to chatters if
      there are no articles that match their last message.
   ![](/_fern-files/_img/9cc9abc9032e0a5d4a86b87cbc38b7664edbd49d96ac42b65abb8cc951df1b0d.webp)
   8. The second Conditional block should also include a Link Message
      block, and the variable you created for *html_url2.* The third
      Conditional block should mirror this format, but with the
      *html_url3* variable in the URL field.
   ![](/_fern-files/_img/afb3e9707a04bcae61a0d36544d22faf90ea89f34ae3085aef13048f3a9bd13f.webp)

When a chatter asks a question that your bot has not been trained to
answer, they will receive a list of relevant articles from your
knowledge base, as illustrated below.

![](/_fern-files/_img/853939d884c7fc778c97c3643807065988f41316f3b0e0c2ce693ee06ab3cabb.webp)

---

Have any questions? Contact your Ada team, or email us at [](<mailto:help@ada.support%20%E2%80%9CHelp Docs inquiry%E2%80%9D>).