<?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/024dddc50f8647d4b7856fbbd9f78e63&quot; frameborder=&quot;0&quot; width=&quot;1662&quot; height=&quot;1246&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1246</height><width>1662</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1246</thumbnail_height><thumbnail_width>1662</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/024dddc50f8647d4b7856fbbd9f78e63-8de0e1d8b037be13.gif</thumbnail_url><duration>96.988</duration><title>Automating Jira to PR Workflow in Slack</title><description>I kicked off a Resolve Jira flow from Slack and the agent immediately acknowledged it and started the workflow. It cloned the repo, created a branch, identified the fitting connector, in this case Databricks, ran analysis, then implemented the change, while streaming detailed updates to me. After implementation it ran evals, generated a SQL artifact, and then pinged me with a link to the PR and a Confluence summary page with acceptance criteria and notes. No action was explicitly requested from viewers, even though evals can fail and still provide useful follow ups.</description></oembed>