<?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/5a944bed4229433193441a3eee91da4f&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/5a944bed4229433193441a3eee91da4f-89f9c4d3c67eb7ad.gif</thumbnail_url><duration>84.095</duration><title>Testing MCP for Batch Workflow Updates</title><description>This Loom tests an MCP tool against localhost to create batch workflows without letting the LLM modify active workflows. The author initially drafts a workflow for all Australian users matching a webhook, includes a distinct ID, and checks the audience size and workflow summary before sending a real webhook run for that person, then confirms and sees the batch job queued. When asked to change the audience to US, the system refuses to modify active workflows and instead creates and enables a new draft pointed at the US audience.</description></oembed>