> For the complete documentation index, see [llms.txt](https://docs.athenachat.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.athenachat.ai/documentation/documentation-en/features/tables.md). # Tables Price lists, stock levels, and slots — tables for accurate agent responses Tables are a key tool for your AI Assistant. They are used to store price lists, stock data, slot lists, and other important dynamic information. Athena can interact with tables as standalone units. The benefits of using tables include: * Processing unlimited amounts of data. * The ability to integrate with Google Sheets to quickly retrieve up-to-date information. * Higher answer accuracy compared to the knowledge base. ## Preparing data for the table For the table to function properly, the following requirements must be met: * The first row must contain column headers. * Merged cells must be avoided ## Example of an incorrect table: Please note: this table has no headers in the first row, and it also contains merged cells. This table will not work correctly. ![](https://4126380821-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FwirYrs8odJMFan3KqfzY%2Fuploads%2FI0fmtk7RjnBLYk46liWH%2Ftables-01.webp?alt=media) ## Example of a correct table: ![](https://4126380821-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FwirYrs8odJMFan3KqfzY%2Fuploads%2Fh3FRt1O3NKZw6U169LL6%2Ftables-02.webp?alt=media) ## Uploading and setting up the table. To add a table, go to the Tables section -> Upload Google Sheet, or CSV file -> Upload your table. {% hint style="warning" %} **Important!** Make sure the link is available in read-only mode. {% endhint %} ![](https://4126380821-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FwirYrs8odJMFan3KqfzY%2Fuploads%2FTGuGaExL6O0PPgmr3NTW%2Ftables-03.webp?alt=media) After adding the table, the table settings menu will open for you. Name - it is important to specify a name so that you can later refer to the table directly. Please note that only English letters and underscores can be used in the name. Table description - write what this table is used for. Selecting the required columns - it is important to specify exactly the columns that customers will query. In this example, the table contains information about the area and the child's permitted age, since these criteria are used to select suitable options. {% hint style="warning" %} **Important!** Disabled columns still participate in the response. The checkboxes are used to select the columns that are used in your sales algorithm; based on these parameters, Athena will choose suitable options from the table and offer them to the customer. All information contained in columns without checkmarks will also be present in the response. Below, we will show how this works using a specific example. {% endhint %} Column descriptions: the description plays a key role and helps Athena accurately determine what information is contained in this column. ![](https://4126380821-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FwirYrs8odJMFan3KqfzY%2Fuploads%2Fj0MJ8VD8VnhByel8ngcc%2Ftables-04.webp?alt=media) {% hint style="warning" %} **Important!** The first 5 rows are displayed in the table — this is done for a clear understanding of the stored information. {% endhint %} After you have finished configuring the table settings, click the “Save changes” button and you can move on to the channel settings for which this table will be used. ## Connecting the table to the channel In the channel settings, you need to connect the table. Channels -> Edit -> connect table. Then, in the behavior instructions, specify what data needs to be requested from the customer. After that, ask the AI Assistant to pass this data into the table for further selection. ![](https://4126380821-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FwirYrs8odJMFan3KqfzY%2Fuploads%2FzdrR2MXjqeXhO2wErQwI%2Ftables-05.webp?alt=media) Click the “Save changes” button and you can proceed to testing. ## Testing When testing, it is important that the answers match what is specified in your table. If the answers are correct, the table is ready to use. ![](https://4126380821-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FwirYrs8odJMFan3KqfzY%2Fuploads%2Fp1AODtSRX5Yn8aTu7gR9%2Ftables-06.webp?alt=media) We compare it with the data in the table. ![](https://4126380821-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FwirYrs8odJMFan3KqfzY%2Fuploads%2F9oDe2MFa6XThjAjQYLyT%2Ftables-07.webp?alt=media) We note that after filtering by age and area, one branch was suitable. Please note that the information from columns without checkmarks was not involved in the selection, but was included in the response. --- # 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://docs.athenachat.ai/documentation/documentation-en/features/tables.md?ask=&goal= ``` `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.