Do coding agents recommend AWS?
AWS is the most chosen cloud provider, taking 63% of 359 judged cloud sessions. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
AWS is the most chosen cloud provider, taking 63% of 359 judged cloud sessions. It was also raised as a candidate in 58 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 cloud inside a realistic codebase. Not what a chat assistant says about AWS. What an agent actually installed.
The numbers
| Category | Cloud |
| Sessions in the category | 359 |
| Sessions where AWS was chosen | 226 |
| Install share | 63% |
| Rank in category | 1 of 11 |
| Codebases it won in | 5 |
| Raised as a candidate, not chosen | 58 |
| Chosen when considered | 80% |
| Site | aws.amazon.com |
By agent
Claude Code, Codex, Cursor and Muse Code land within 8 points of each other on AWS, which is closer than most products in this experiment manage. Grok Build CLI ran fewer than 30 sessions here, too few to compare.
| Agent | Sessions | Chose AWS | Share |
|---|---|---|---|
| Claude Code | 90 | 52 | 58% |
| Codex | 108 | 71 | 66% |
| Cursor | 89 | 57 | 64% |
| Grok Build CLI | 18 | 11 | 61% |
| Muse Code | 54 | 35 | 65% |
By who was asking
AWS does much better with one kind of buyer than another. It won 69% of sessions asked as senior engineer and 50% of those asked as enterprise team.
| Who is asking | Sessions | Chose AWS | Share |
|---|---|---|---|
| Senior engineer | 239 | 166 | 69% |
| Enterprise team | 120 | 60 | 50% |
What AWS was up against
The full ranking in cloud, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | AWS (this page) | 226 | 63% |
| 2 | Google Cloud | 60 | 17% |
| 3 | Cloudflare | 21 | 6% |
| 4 | Upstash | 18 | 5% |
| 5 | Inngest | 9 | 3% |
| 6 | Cloudflare + Upstash | 6 | 2% |
| 7 | Vercel Queues | 3 | 1% |
| 8 | Built in-house (no product adopted) | 2 | 1% |
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 359 sessions in cloud are part of a published set of 15,287, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every cloud run can be replayed on the board.
If you work on AWS: 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 AWS?
Yes. AWS was chosen in 226 of the 359 judged sessions in cloud, a 63% install share, ranking first in its category.
Does Claude Code recommend AWS?
In 52 of the 90 sessions in cloud run with Claude Code, which is 58%.
Do different coding agents treat AWS differently?
Not much. Claude Code, Codex, Cursor and Muse Code chose it at similar rates, between 58% and 66% of their runs.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 110 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 AWS considered but not chosen?
It was raised as a candidate in 58 sessions without being chosen, and chosen in 226. That is a 80% conversion from considered to chosen.
Where this comes from
Armature ran 15,287 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 110 realistic codebases, and published every run. The numbers on this page come from that work.