<?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/4fae5d86c3d844d69a4b16e0861a83e0&quot; frameborder=&quot;0&quot; width=&quot;1660&quot; height=&quot;1245&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1245</height><width>1660</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1245</thumbnail_height><thumbnail_width>1660</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/4fae5d86c3d844d69a4b16e0861a83e0-0ce28f301abfe55b.gif</thumbnail_url><duration>255.06</duration><title>Reliable AI Agent Payments with ERC Scoring</title><description>This Loom explains an agent-based system for deciding which external APIs to pay for, using independent verification and scoring. An AI agent powered by Nebulous DeepSeek proposes a Circle Agent, which is governed by wallet policy caps and an allow list and paid via the X402 protocol. A separate Hunter agent checks quality and whether a watch list exists, then results are saved in the ERC 804 registry for identification with two scores covering quality and watch risk. The decision is pay, trial, or refuse, with a dashboard to tune policy strictness and simulate runs, and the process can attach evidence and risk to feeds.</description></oembed>