# How Kea AI Reads Your Menu

To deliver accurate, natural ordering experiences, kea’s AI relies on your menu as its **sole source of truth**. The AI doesn’t “guess” or invent—it strictly follows what’s available and structured in your POS menu. To ensure the AI performs well:

* **Every menu item needs a clear description**. This allows the AI to understand what’s included, infer intent (like “egg plate” = Breakfast Plate), and match customer phrasing to menu items.
  * Pizza sizing is a common example—some restaurants call a 12-inch pizza a small, while others consider a 14-inch pizza a small. To avoid confusion, it's important to include this context directly in the item name (e.g. “12-inch Small Pizza”). We avoid trying to standardize this across all restaurants, as it could lead to mismatches. Over time, as more orders come in, the AI will learn how your customers refer to your specific sizes.
* **Modifiers are essential** for handling customizations. Without proper modifiers (e.g. "no onions", "extra sauce"), the AI cannot adjust orders or fulfill special requests as we don't want the AI to make it up and then confuse your kitchen staff.
* **Option groups should be structured smartly**—separate default ingredients from extras, and avoid “No X” exclusion options. This helps the AI know what comes standard and what can be added or removed.
* **Group size/quantity variations under one item** (e.g. “Chicken Wings” with size options), instead of listing separate menu items i.e. 6 Chicken Wings; 12 Chicken Wings; 18 Chicken Wings. This aligns with how customers typically speak and improves order matching.
* **Use unique, clear menu item names**, avoiding small variations that may confuse the AI. i.e. 
* **Spell things out**—avoid abbreviations like “pc” or alternate spellings that could be misread or mispronounced.
  * Sm → Small or Lg → Large.

In short, the better structured and more descriptive your menu is, the more accurate and natural the AI experience will be for your customers!


---

# Agent Instructions: 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:

```
GET https://support.kea.ai/menus-and-voice-ai/how-kea-ai-reads-your-menu.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.