<?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/0aa7ef0d83a746b2a7195cca2b83f585&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/0aa7ef0d83a746b2a7195cca2b83f585-6671355866946fbd.gif</thumbnail_url><duration>240.006</duration><title>Automated Technical Prospecting with AI Drafts 🤖</title><description>Most companies personalize with outdated facts like the university someone studied, but I focus on technical relevance that high level prospects like CTOs and VPs actually respond to. I built a custom Go microservice that uses headless Chrome to extract deep engineering data from modern sites in seconds, and it processes hundreds of leads concurrently. Then I use Grok with a Llama 3 70B scale approach and a deterministic prompt to identify pain points and draft a highly technical email, achieving over 90 percent technical relevancy. The AI draft is pushed back into HubSpot as a custom property. No action was explicitly requested from viewers.</description></oembed>