<?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/7d78996a63f34a45a721420419a7d25c&quot; frameborder=&quot;0&quot; width=&quot;1920&quot; height=&quot;1440&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1440</height><width>1920</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1440</thumbnail_height><thumbnail_width>1920</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/7d78996a63f34a45a721420419a7d25c-6a89f68c25e2a28d.gif</thumbnail_url><duration>2395.457</duration><title>Agent-Led IP Search Workflow Demo</title><description>This Loom explains how to transform IP searches into an agent-led workflow using PatSnap’s Eureka agents. It highlights that 68% of patented practitioners reported adopting AI-assisted search in the 2025 AI PLA practice survey, up from about 31% in 2022, and demonstrates a novelty search and an FTO (freedom to operate) search end to end. The demos show interactive feature extraction, multi-strategy searching grounded in live patents and literature, and transparent claim charting with evidence and high, medium, and low risk tags, plus exportable reports. The FTO agent can take a few minutes longer due to iterative self-optimizing search and claim comparison, and the presenter notes that outputs accelerate legal work but are not legal opinions.</description></oembed>