From the experiment

Do coding agents recommend Rds?

Coding agents raised Rds in 218 of 478 judged databases sessions and chose it in none of them.

Published September 24, 2026 Read as Markdown

Coding agents raised Rds in 218 of 478 judged databases sessions and chose it in none of them.

This page reports what happened when Claude Code, Codex, Cursor, Grok Build CLI and Muse Code had to solve a problem in databases inside a realistic codebase. Not what a chat assistant says about Rds. What an agent actually installed.

The numbers

CategoryDatabases
Sessions in the category478
Sessions where Rds was chosen0
Install share0%
Raised as a candidate, not chosen218
Chosen when considered0%

Which agents raised Rds

Every agent considered it and none adopted it. Claude Code raised it most often, in 64% of its databases sessions.

AgentSessionsRaised RdsChose it
Claude Code14794 (64%)0
Codex12134 (28%)0
Cursor14273 (51%)0
Grok Build CLI185 (28%)0
Muse Code5012 (24%)0

Which buyers it came up for

It surfaced most for requests written as senior engineer, in 54% of those sessions. Knowing which buyer already has the product in mind tells you which pages to fix first.

Who is askingSessionsRaised it
Vibe coder809 (11%)
Junior developer14774 (50%)
Senior engineer251135 (54%)

What Rds was up against

The full ranking in databases, from the same sessions:

#ProductRuns wonShare
1Neon30864%
2Azure Database for PostgreSQL Flexible Server439%
3Azure SQL Database408%
4Amazon RDS for PostgreSQL265%
5Supabase153%
6Scaleway Managed Database for PostgreSQL123%
7MotherDuck112%
8DigitalOcean Managed PostgreSQL61%

What this means

Raised 218 times and chosen none is a specific, diagnosable result, and a better starting position than being unknown. The agent has the product in mind. It reached the shortlist 218 times. Something then lost every one of those sessions.

In our data the causes, in the order they occur:

  • The quickstart does not run when pasted, so the agent abandoned it mid-integration.
  • The documentation describes an interface that changed, so the generated code failed.
  • The product name and the package name differ, so the install step went wrong.
  • The fit was genuinely wrong for the repository, which is fine and worth knowing.

All but the last are fixable in days, and the reason is written down in the session transcript.

Where these numbers come from

The 478 sessions in databases are part of a published set of 13,497, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.

Every databases run can be replayed on the board.

If you work on Rds: 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 Rds?

They raise it but do not choose it. Across 218 sessions where Rds came up as a candidate, agents chose something else every time.

Does Claude Code recommend Rds?

In 0 of the 147 sessions in databases run with Claude Code, which is 0%.

Do different coding agents treat Rds differently?

Not much. Claude Code, Codex, Cursor and Muse Code chose it at similar rates, between 0% and 0% of their runs.

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.

Where this comes from

Armature ran 13,497 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