<?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/96978b7195064a358c521465b9bdd2ff&quot; frameborder=&quot;0&quot; width=&quot;1280&quot; height=&quot;960&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>960</height><width>1280</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>960</thumbnail_height><thumbnail_width>1280</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/96978b7195064a358c521465b9bdd2ff-8435f63bbb35d65d.gif</thumbnail_url><duration>108.367</duration><title>Enhancing Assistant Memory with Data Storage Solutions</title><description>Good morning, everyone. In this video, I share my progress on a new test I&apos;ve been working on, which involves using a data store to save and reference information from previous conversations. I&apos;ve implemented this with a model called per-procity, utilizing a database from Make that is accessible with a subscription. I recommend limiting the stored data to three to five entries for efficiency. Please check out the data store for more details, and I encourage you to explore how this can enhance our interactions.</description></oembed>