<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/53486eefae0d43e7907fde14e1b30429&quot; frameborder=&quot;0&quot; width=&quot;1728&quot; height=&quot;1296&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1296</height><width>1728</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1296</thumbnail_height><thumbnail_width>1728</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/53486eefae0d43e7907fde14e1b30429-77d34409cbb40187.gif</thumbnail_url><duration>250.341</duration><title>Testing an AI Food Ordering Agent</title><description>This Loom demonstrates testing an AI food ordering agent that lets customers browse a menu, choose a meal, and complete payment via Paystack. The presenter describes the agent setup, including connected API keys, a system prompt, menu data, and a conversation flow script for ordering and payment. They run the bot in the BPA AI event platform playground as the “Mamatunde’s kitchen bot,” where it shows the menu and confirms a payment as a simulation through Paystack (Sources, Bank, and Clients). The Loom concludes by noting this is a simulation of how transactions can be read and edited in the platform.</description></oembed>