From the experiment

Do coding agents recommend Amazon S3?

Amazon S3 is the most chosen file storage service, taking 46% of 90 judged file storage sessions. Measured with Claude Code, Codex and Cursor.

Published September 3, 2026 Read as Markdown

Amazon S3 is the most chosen file storage service, taking 46% of 90 judged file storage sessions. It was also raised as a candidate in 44 further sessions without being chosen.

This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in file storage inside a realistic codebase. Not what a chat assistant says about Amazon S3. What an agent actually installed.

The numbers

CategoryFile storage
Sessions in the category90
Sessions where Amazon S3 was chosen41
Install share46%
Rank in category1 of 5
Codebases it won in6
Raised as a candidate, not chosen44
Chosen when considered48%
Siteaws.amazon.com

By agent

The three agents treat Amazon S3 very differently. Codex chose it in 53% of its sessions in this category and Claude Code in 33%, a spread of 20 points.

AgentSessionsChose Amazon S3Share
Claude Code301033%
Codex301653%
Cursor301550%

A single blended install share would report the midpoint and hide both ends. If most of your users run Claude Code, your real position here is 33%, not 46%.

By who was asking

Amazon S3 does much better with one kind of buyer than another. It won 74% of sessions asked as senior engineer and 0% of those asked as enterprise team.

Who is askingSessionsChose Amazon S3Share
Junior developer181372%
Senior engineer272074%
Enterprise team3600%

What Amazon S3 was up against

The full ranking in file storage, from the same sessions:

#ProductRuns wonShare
1Amazon S3 (this page)4146%
2Azure Blob Storage1820%
3Google Cloud Storage1820%
4Cloudflare R21213%
5Tigris11%

What this means

Leading a category is a position to defend rather than a result to celebrate. In our data, leaders lose ground in exactly two situations: when the person asking is an enterprise buyer with procurement constraints, and when a competitor's documentation is easier for an agent to integrate correctly.

The defence is unglamorous. Keep the quickstart running. Keep the version current on the page. Keep the names aligned. Stay in the templates.

Where these numbers come from

The 90 sessions in file storage are part of a published set of 5,292, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.

Every file storage run can be replayed on the board.

If you work on Amazon S3: 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 Amazon S3?

Yes. Amazon S3 was chosen in 41 of the 90 judged sessions in file storage, a 46% install share, ranking first in its category.

Does Claude Code recommend Amazon S3?

In 10 of the 30 sessions in file storage run with Claude Code, which is 33%.

Do different coding agents treat Amazon S3 differently?

Yes, and by a wide margin. Codex chose it in 53% of its runs and Claude Code in 33%.

How was this measured?

Real coding agents at pinned versions were run in sandboxes inside 51 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 Amazon S3 considered but not chosen?

It was raised as a candidate in 44 sessions without being chosen, and chosen in 41. That is a 48% conversion from considered to chosen.

Where this comes from

Armature ran 5,292 judged sessions with Claude Code, Codex and Cursor inside 51 realistic codebases, and published every run. The numbers on this page come from that work.

Read next

All library pages