> For the complete documentation index, see [llms.txt](https://support.kea.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://support.kea.ai/kea-ai-customer-faqs/in-store-best-practices.md). # In-Store Best Practices Your AI is **constantly** learning. Like any new team member, the first few weeks are an onboarding period where we fine-tune its performance using **real customer interactions and feedback**. Most restaurants find that both the AI and their guests quickly adapt to the new ordering experience, with customer familiarity typically increasing within 2–3 weeks. During this adjustment period, it's completely normal to receive questions, comments, or occasional concerns from guests as they become familiar with ordering through your AI phone agent. We take every piece of customer feedback **very seriously**. It's one of the most valuable tools we have for continuously training and improving your AI to better serve your guests, as if it were a new employee we are onboarding and training together.\ \ **Please encourage your team to monitor, document, and report any customer concerns during this period.** The more information we receive, the faster we can investigate, make improvements, and ensure your guests have the best possible experience. ### Staff Actions When a guest shares feedback about their experience with the AI phone agent, your response can make a lasting impression. Follow your restaurant's normal guest recovery process while keeping these best practices in mind: * Thank the guest and apologize for any inconveniences * Let the guest know of the WHY * If appropriate, explain why your restaurant introduced the AI phone agent. * For example: "*We introduced our AI phone assistant to help ensure every call gets answered, reduce hold times, and allow our team to spend more time focusing on guests in the restaurant*." * Reassure the guest: Let the guest know their feedback won't disappear into a void. * Follow Your Standard Guest Recovery Process * A great recovery experience can leave a guest with an even stronger impression than if no issue had occurred at all. ### Before the Guest Leaves *Please gather as much of the following information as possible:* #### Customer Information * Customer's name and phone number used to place the order * Approximate time the call was placed * Store location (if applicable) #### Order Information * What was incorrect about the order? * Ex) "*Customer ordered Gluten Free but did not print correctly on the ticket and order was made incorrectly*." * Ex) "*The AI added an extra side of fries instead of telling the guest that their burger already came with fries.*" * What was the customer expecting? * Ex) "*The AI used a rude tone*" or "*The AI repeated the order back to me too many times.*" * Was the issue related to: * Missing item * Incorrect item * Wrong modifier or customization * Quantity issue * Pickup time * Other #### Photos (Highly Recommended) If possible, take photos of: * The printed kitchen ticket * The customer receipt * The completed order (if applicable) These images help us compare what the AI heard, what was sent to the POS, and what was ultimately prepared. ### What Happens Next? Once you've gathered the information, send it to your Kea support contact or submit it through your normal support channel. Call/text 650-709-2993 Our team will: * Review the call recording * Compare the conversation with the POS order * Identify where the issue occurred * Make any necessary AI or menu improvements * Follow up with recommendations if needed **Most reported issues are resolved through menu updates or operational improvements. Every piece of feedback helps us continuously improve your AI and refine your restaurant's phone ordering experience. The more feedback we receive, the better we can optimize your AI for future guests.** --- # 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://support.kea.ai/kea-ai-customer-faqs/in-store-best-practices.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.