From the experiment

Do coding agents recommend Amazon SQS?

Amazon SQS was chosen in 9% of 288 judged message queues sessions, ranking second. Measured with Claude Code, Codex and Cursor.

Published September 15, 2026 Read as Markdown

Amazon SQS was chosen in 9% of 288 judged message queues sessions, ranking second. It was also raised as a candidate in 168 further sessions without being chosen.

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

The numbers

CategoryMessage queues
Sessions in the category288
Sessions where Amazon SQS was chosen27
Install share9%
Rank in category2 of 25
Codebases it won in6
Raised as a candidate, not chosen168
Chosen when considered14%
Siteaws.amazon.com

By agent

The three agents land within 14 points of each other on Amazon SQS, which is closer than most products in this experiment manage.

AgentSessionsChose Amazon SQSShare
Claude Code9644%
Codex961718%
Cursor9666%

By who was asking

Amazon SQS does much better with one kind of buyer than another. It won 21% of sessions asked as enterprise team and 1% of those asked as junior developer.

Who is askingSessionsChose Amazon SQSShare
Vibe coder4848%
Junior developer12011%
Senior engineer48715%
Enterprise team721521%

What Amazon SQS was up against

The full ranking in message queues, from the same sessions:

#ProductRuns wonShare
1Built in-house (no product adopted)4917%
2Apache Kafka3914%
3Amazon SQS (this page)279%
4Service Bus248%
5Laravel Queues207%
6Amazon Kinesis197%
7Cloudflare Queues197%
8Cloud Tasks155%

What this means

This is an integration problem, not a presence problem. Agents raised Amazon SQS in 168 sessions and chose it in 27, 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 288 sessions in message queues are part of a published set of 7,852, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.

Every message queues run can be replayed on the board.

If you work on Amazon SQS: 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 SQS?

Yes. Amazon SQS was chosen in 27 of the 288 judged sessions in message queues, a 9% install share, ranking second in its category.

Does Claude Code recommend Amazon SQS?

In 4 of the 96 sessions in message queues run with Claude Code, which is 4%.

Do different coding agents treat Amazon SQS differently?

Yes, and by a wide margin. Codex chose it in 18% of its runs and Claude Code in 4%.

How was this measured?

Real coding agents at pinned versions were run in sandboxes inside 90 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 SQS considered but not chosen?

It was raised as a candidate in 168 sessions without being chosen, and chosen in 27. That is a 14% conversion from considered to chosen.

Where this comes from

Armature ran 7,852 judged sessions with Claude Code, Codex and Cursor inside 90 realistic codebases, and published every run. The numbers on this page come from that work.

Read next

All library pages