<?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/4df32534b50046cb8e0571ccbe5b7efb&quot; frameborder=&quot;0&quot; width=&quot;1366&quot; height=&quot;1024&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1024</height><width>1366</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1024</thumbnail_height><thumbnail_width>1366</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/4df32534b50046cb8e0571ccbe5b7efb-1799d67eafb4afa6.gif</thumbnail_url><duration>533.315</duration><title>Verix, Verifiable AI Execution for Multi Agents</title><description>This Loom explains Verix, a cryptographic execution framework for multi-agent AI work on Stellar without trust. It shows how agents are registered as versioned infrastructure modules priced in USDC and gated by proof verification policies, with payments released only after on-chain escrow proof verification via hash-chain receipts. The demo submits a market research task for Google with an estimated cost of $0.05, a spend cap of $10, and wallet balance checks via the Horizon API. After execution, it reviews hashed receipts and verifies proofs before releasing payouts per milestone, all tracked on the trust list.</description></oembed>