# [[How to use Grafana Assistant with self-hosted Grafana]] <iframe width="560" height="315" src="https://www.youtube.com/embed/0000000" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe> plugins:: "" Related:: "" ## Pre-production ### Thumbnail ![[How to use Grafana Assistant for Grafana OSS.png]] ### Title 1. ### Hook In case you missed it, possibly the biggest news to come from GrafanaCON is that Grafana Assistant, the purpose-built LLM for all things Grafana, is now publicly available to opensource Grafana users. In this video, I'm going to show you how to enable it AND use it to go from nothing to THIS dashboard with a single prompt. ### Structure - First: Let's get one thing out of the way. It's not free. That's because we also pay to use the best models and then we've added some of our own architecture and logic around them - Second: You will still need a Grafana Cloud account to pay for Assistant, but you don't need to actually use that Grafana instance. Think of it this way: Having a Grafana Cloud subscription gives you access to use Assistant in OSS. - Prerequisites - OSS Grafana v13 or higher - a Grafana Cloud account (free tier or more) - Enabling Assistant - Go to plugins, search for Assistant. - Click Install. - Refresh the page. Then go to the Connection tab. - Click Start Connection - Select the organization and stack you want, and then click Authorize connection. - Click Close. - Link Assistant to your Grafana Cloud account - Initial dashboard - Every Grafana instance comes with a test data source: TestData. Enable that. - Ask Assistant to create us a dashboard for server health. ### Outro I've only shown you how Assistant can build dashboards, but Assistant can actually do way more. You can ask it questions about data that you have in Grafana, run investigations to troubleshoot production incidents, teach it skills, manage alerts, teach you how to use Grafana... and this list just keeps growing. If you want to learn more about how we handle your data, or just more details about Assistant, click here. Thanks for watching! ### Related videos and resources ### Pinned comment ``` ``` ### Timestamps 00:00 Intro ## Post-production - [ ] Create captions using Rev, then edit them. - [ ] Take a thumbnail photo and create one for YouTube (1280 x 720). - [ ] Add description. - [ ] Include the title and any keywords in the first few sentences, but in a natural way. - [ ] Add related videos and resources as links. - [ ] Add end screen. - [ ] Add cards if necessary. - [ ] Add chapters/timestamps for YouTube if longer than 5 minutes. - [ ] Add mid-roll ads/check monetization settings. - [ ] Add pinned comment. - [ ] Post video preview on Patreon. - [ ] Schedule on YouTube. - [ ] Add video to relevant playlist(s), or create a playlist if necessary. - [ ] Schedule on Mastodon. - [ ] Create a blog post on [site](https://nicolevanderhoeven.com). - [ ] Add to [video-database](obsidian://open?vault=obsidian-playbook&file=video-database%2FVideo%20database). - [ ] Add to other notes in my vault as appropriate.