<?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/bdb2c251b80e4a39ab2dd156f3e15193&quot; frameborder=&quot;0&quot; width=&quot;1110&quot; height=&quot;832&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>832</height><width>1110</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>832</thumbnail_height><thumbnail_width>1110</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/bdb2c251b80e4a39ab2dd156f3e15193-edc88cd9881e7e82.gif</thumbnail_url><duration>244.6702</duration><title>Exploring a Life Sciences Research AI Agent with Crew AI and Ory</title><description>In this video, I demonstrate a Streamlit app that utilizes a crew of agents built with the Crew AI framework, leveraging an Ory endpoint powered by the latest open-source GPT model with 120 billion parameters. The app is specifically designed for life sciences research, enabling users to query and retrieve detailed reports from the PubMed data source. I walk through the process of submitting a technical query and showcase the comprehensive report generated by the AI agent, which includes summaries, research landscapes, and references. I encourage you to explore the app and check the blog post for more details and code. Stay tuned for future sessions where I will dive deeper into the agent-building process.</description></oembed>