From the experiment

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.

Published September 23, 2026 Read as Markdown

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

CategoryProduct analytics
Sessions in the category508
Sessions where Metabase was chosen29
Install share6%
Rank in category2 of 17
Codebases it won in8
Raised as a candidate, not chosen170
Chosen when considered15%
Sitemetabase.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.

AgentSessionsChose MetabaseShare
Claude Code15043%
Codex15032%
Cursor14964%
Grok Build CLI291034%
Muse Code30620%

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 askingSessionsChose MetabaseShare
Vibe coder5148%
Junior developer20431%
Senior engineer202199%
Enterprise team5136%

What Metabase was up against

The full ranking in product analytics, from the same sessions:

#ProductRuns wonShare
1PostHog27554%
2Built in-house (no product adopted)8216%
3Metabase (this page)296%
4Vercel Analytics275%
5Amplitude194%
6Segment173%
7Mixpanel122%
8Looker Studio82%

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.

Read next

All library pages