Metabase

We’ve built a Claude skill that teaches you Metabase . It keeps track of what it has already covered, uses your own data for examples, and is designed for learning not just one-off questions. Why use AI for learning Metabase Compared to static guides, an LLM can be much more engaging, ask you questions, and then use your answers to decide what else to cover or where to maybe add some information. In fact, perhaps the most useful aspect of Claude is its ability to be pedantic. If you give it a vague answer to a question, or you’re half right and half wrong, it will tell you what specifically you got right and where you might need some help. It can be slightly annoying at times, but it really helps to hone your skills. In addition, you can ask an LLM questions. It will present the material to you and ask you questions, but it is there to help you. You can ask it to explain, to clarify, to expand on points. This allows you to be much more active in your learning than when just reading mat

TL;DR AI is everywhere, and everyone’s exploring what it can do while feeling out the limits. Metabase is building the infrastructure to make sure you can use AI with confidence. AI analytics without structured, contextual data? Not recommended. We introduced Data Studio for curating your semantic layer, so your data team manages a trustworthy foundation for AI answers. Everyone should be able to use LLMs to work with data, so we made AI a core part of our product — even in open source — and gave you the keys to host and power it as you choose. An AI-first data strategy still needs a human in charge. Tokens creep, bills climb, and people sometimes feel emboldened to ask things they wouldn’t otherwise. We make sure you can govern access, set limits, and monitor usage. Connecting the dots across releases We’ve shipped a bunch of new stuff since the start of the year: Metabot! MCP! Metabot in Slack! Data Studio! AI SQL and Python generation! Dashboards as code! All that stuff is cool, but

We’re excited to announce that Metabase is now available as a plugin in ChatGPT and Codex, part of OpenAI’s new data analytics launch. You can now connect your Metabase instance directly to Codex, ask questions, find insights, save questions, and dashboards. The tables and metrics curated in your Metabase’s semantic layer are now available for you to inspect, find insights, and do data analyses using OpenAI’s Codex. The answers you get in Codex reflect the trusted context you’ve already built in Metabase. This launch is officially part of OpenAI’s new data analytics plugin, a package of industry-leading connectors verified and validated by OpenAI, for easier management of key business metrics. What you can do With the Metabase plugin in Codex, you can: Ask questions in plain language. Pose product and business questions the way you’d ask a teammate (“why did signups dip last week?”) and get answers grounded in your actual data. Diagnose metric movements. Dig into the why behind the num

Material Event filed 2026-05-29

Open source software is in for a rough 2026 summer. If you’re an Open Source maintainer, there’s something afoot you should already know about. If you’re an OSS user , you should be aware of it as it’ll explain some behavior around you that might otherwise seem odd. TL;DR: High volume, LLM-powered scanning for security vulnerabilities is going to uncover lots of security issues in anything with public source code. This all started a few months ago Historically, Metabase averaged 10 submissions per month to our [email protected], most of which were trivial or not actually vulnerabilities. Many were false positives from scanning tools, and we spent most of our time explaining to the reporter that what they found wasn’t actually a problem. At the turn of the year, things changed. Starting in January, we’ve been averaging 10 submissions per week, and many of these are legit. Most are not serious, and we’ve quietly fixed them, thanked the researcher, and went our merry way. However, it

Open source software is in for a rough 2026 summer. If you’re an Open Source maintainer, there’s something afoot you should already know about. If you’re an OSS user , you should be aware of it as it’ll explain some behavior around you that might otherwise seem odd. TL;DR: High volume, LLM-powered scanning for security vulnerabilities is going to uncover lots of security issues in anything with public source code. This all started a few months ago Historically, Metabase averaged 10 submissions per month to our [email protected], most of which were trivial or not actually vulnerabilities. Many were false positives from scanning tools, and we spent most of our time explaining to the reporter that what they found wasn’t actually a problem. At the turn of the year, things changed. Starting in January, we’ve been averaging 10 submissions per week, and many of these are legit. Most are not serious, and we’ve quietly fixed them, thanked the researcher, and went our merry way. However, it

We ran the Metabase AI Hackathon to celebrate every AI feature in Metabase going open source. The submissions were genuinely fun to go through: analytics agents, new products, an entire API with machine learning, a couple of things that made us laugh, a couple that made us think “oh, that’s actually clever.” Picking two was harder than we expected. Here are the winners: Meta Chess, by Marat Surmashev A live dashboard where Claude and Codex play chess against each other, with Metabase as the entire game platform, not a passive viewer. This one uses two of our newest features in tandem. The agents sync through the MCP server : read the board state, check whose turn it is, and see the opponent’s last move. What spectators watching the dashboard see and what the agents see is the same source of truth. The dashboard itself is built with file-based development : the live chessboard, the last-move highlight, and the move history are all Metabase YAML cards shipped through the serialization v2

Development tools can sometimes struggle when dealing with large codebases. This gives performance nerds like me a reason to investigate. In this case, I ended up cutting clojure-lsp’s startup time in half and memory allocation by two thirds. Part 1: The mystery of heap headroom Devs working on Metabase were complaining about LSP taking too long to boot, so I wondered how long it could be. A few seconds? Half a minute? Imagine my surprise when I saw this: ( time ( clojure-lsp.api/analyze-project-only! { :project-root ( clojure.java.io/file "/path/to/metabase" )})) "Elapsed time: 178981.918417 msecs" Three minutes is a long time. The first suspect was heap size. There is a good rule of a thumb: if some process in Clojure (or any JDK language) takes longer to complete than anticipated, or doesn’t finish at all, you should check the heap. I used VisualVM to inspect our Clojure process and ran the benchmarking command, which gave us something like this: What’s going on here? My laptop has

Material Event filed 2026-05-04

Quarterly Report filed 2026-04-30

Material Event filed 2026-04-29