From the experiment

Do coding agents recommend Google Cloud?

Google Cloud was chosen in 17% of 215 judged cloud sessions, ranking second. Measured with Claude Code, Codex and Cursor.

Published September 3, 2026 Read as Markdown

Google Cloud was chosen in 17% of 215 judged cloud sessions, ranking second. It was also raised as a candidate in 87 further sessions without being chosen.

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

One thing to read first: every one of those wins came from a single codebase. That is a result about one repository rather than about cloud in general, and the splits below cannot separate the two. Treat them as a description of that repository.

The numbers

CategoryCloud
Sessions in the category215
Sessions where Google Cloud was chosen36
Install share17%
Rank in category2 of 8
Codebases it won in1
Raised as a candidate, not chosen87
Chosen when considered29%
Sitecloud.google.com

By agent

The three agents agree closely on Google Cloud, choosing it at rates within 0 points of each other.

AgentSessionsChose Google CloudShare
Claude Code721217%
Codex721217%
Cursor711217%

By who was asking

Google Cloud does much better with one kind of buyer than another. It won 50% of sessions asked as enterprise team and 0% of those asked as senior engineer.

Who is askingSessionsChose Google CloudShare
Senior engineer14300%
Enterprise team723650%

What Google Cloud was up against

The full ranking in cloud, from the same sessions:

#ProductRuns wonShare
1AWS13362%
2Google Cloud (this page)3617%
3Cloudflare178%
4Inngest84%
5Upstash84%
6Vercel Queues31%
7Cloudflare + Upstash21%
8Render10%

What this means

A solid second or third position in a category means the agent is genuinely choosing rather than reaching automatically. That is a winnable position, because the inputs it uses can be changed.

The fastest gains are usually in the sessions that were nearly won: read them, find the step where the agent moved on, and fix that step.

Where these numbers come from

The 215 sessions in cloud 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 cloud run can be replayed on the board.

If you work on Google Cloud: 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 Google Cloud?

Yes. Google Cloud was chosen in 36 of the 215 judged sessions in cloud, a 17% install share, ranking second in its category.

Does Claude Code recommend Google Cloud?

In 12 of the 72 sessions in cloud run with Claude Code, which is 17%.

Do different coding agents treat Google Cloud differently?

Not much. The three agents chose it at similar rates, between 17% and 17% of their runs.

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 Google Cloud considered but not chosen?

It was raised as a candidate in 87 sessions without being chosen, and chosen in 36. That is a 29% 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