Do coding agents recommend Metabase?
Metabase was chosen in 6% of 508 judged product analytics sessions, ranking second. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
Metabase was chosen in 6% of 508 judged product analytics sessions, ranking second. It was also raised as a candidate in 170 further sessions without being chosen.
This page reports what happened when Claude Code, Codex, Cursor, Grok Build CLI and Muse Code had to solve a problem in product analytics inside a realistic codebase. Not what a chat assistant says about Metabase. What an agent actually installed.
The numbers
| Category | Product analytics |
| Sessions in the category | 508 |
| Sessions where Metabase was chosen | 29 |
| Install share | 6% |
| Rank in category | 2 of 17 |
| Codebases it won in | 8 |
| Raised as a candidate, not chosen | 170 |
| Chosen when considered | 15% |
| Site | metabase.com |
By agent
The agents treat Metabase very differently. Muse Code chose it in 20% of its sessions in this category and Codex in 2%, a spread of 18 points. Grok Build CLI ran fewer than 30 sessions here, too few to compare.
| Agent | Sessions | Chose Metabase | Share |
|---|---|---|---|
| Claude Code | 150 | 4 | 3% |
| Codex | 150 | 3 | 2% |
| Cursor | 149 | 6 | 4% |
| Grok Build CLI | 29 | 10 | 34% |
| Muse Code | 30 | 6 | 20% |
A single blended install share would report the midpoint and hide both ends. If most of your users run Codex, your real position here is 2%, not 6%.
By who was asking
Metabase performs similarly across the four kinds of buyer, from 1% to 9%. That is unusual: the category leader changed with the persona in 23 of the 29 categories we measured.
| Who is asking | Sessions | Chose Metabase | Share |
|---|---|---|---|
| Vibe coder | 51 | 4 | 8% |
| Junior developer | 204 | 3 | 1% |
| Senior engineer | 202 | 19 | 9% |
| Enterprise team | 51 | 3 | 6% |
What Metabase was up against
The full ranking in product analytics, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | PostHog | 275 | 54% |
| 2 | Built in-house (no product adopted) | 82 | 16% |
| 3 | Metabase (this page) | 29 | 6% |
| 4 | Vercel Analytics | 27 | 5% |
| 5 | Amplitude | 19 | 4% |
| 6 | Segment | 17 | 3% |
| 7 | Mixpanel | 12 | 2% |
| 8 | Looker Studio | 8 | 2% |
What this means
This is an integration problem, not a presence problem. Agents raised Metabase in 170 sessions and chose it in 29, so it reaches the shortlist and then loses. Something at the last step is costing the session, and in our data that is usually a quickstart that does not run when pasted, documentation describing an interface that changed, or a package name that does not match the product name.
That is the cheaper of the two problems to have. The reason is written down in each losing transcript.
Where these numbers come from
The 508 sessions in product analytics are part of a published set of 11,878, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every product analytics run can be replayed on the board.
If you work on Metabase: the judge recorded a reason for every session where it was raised and passed over. Those reasons are in the transcripts.
<!-- generated by scripts/write-data-pages.mjs -->
Common questions
Do coding agents recommend Metabase?
Yes. Metabase was chosen in 29 of the 508 judged sessions in product analytics, a 6% install share, ranking second in its category.
Does Claude Code recommend Metabase?
In 4 of the 150 sessions in product analytics run with Claude Code, which is 3%.
Do different coding agents treat Metabase differently?
Yes, and by a wide margin. Muse Code chose it in 20% of its runs and Codex in 2%.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 91 realistic codebases and asked to solve real tasks. A simulated project owner approved or questioned each recommendation before any code was written, and a judge from a model family that builds none of the agents read every session blind.
How often is Metabase considered but not chosen?
It was raised as a candidate in 170 sessions without being chosen, and chosen in 29. That is a 15% conversion from considered to chosen.
Where this comes from
Armature ran 11,878 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 91 realistic codebases, and published every run. The numbers on this page come from that work.