From the experiment

Do coding agents recommend Fly Machines?

Coding agents raised Fly Machines in 62 of 401 judged code sandboxes sessions and chose it in none of them.

Published September 23, 2026 Read as Markdown

Coding agents raised Fly Machines in 62 of 401 judged code sandboxes 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 code sandboxes inside a realistic codebase. Not what a chat assistant says about Fly Machines. What an agent actually installed.

The numbers

CategoryCode sandboxes
Sessions in the category401
Sessions where Fly Machines was chosen0
Install share0%
Raised as a candidate, not chosen62
Chosen when considered0%
Sitefly.io

Which agents raised Fly Machines

Claude Code, Codex, Cursor and Muse Code considered it and none adopted it. Claude Code raised it most often, in 23% of its code sandboxes sessions.

AgentSessionsRaised Fly MachinesChose it
Claude Code11226 (23%)0
Codex13610 (7%)0
Cursor11925 (21%)0
Grok Build CLI170 (0%)0
Muse Code171 (6%)0

Which buyers it came up for

It surfaced most for requests written as senior engineer, in 16% of those sessions. Knowing which buyer already has the product in mind tells you which pages to fix first.

Who is askingSessionsRaised it
Senior engineer35959 (16%)
Enterprise team423 (7%)

What Fly Machines was up against

The full ranking in code sandboxes, from the same sessions:

#ProductRuns wonShare
1E2B17042%
2Modal10426%
3Daytona6015%
4Vercel Sandbox5915%
5Anthropic Code Execution31%
6Runloop Devboxes31%
7Cloudflare Workers20%

What this means

Raised 62 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 62 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 401 sessions in code sandboxes are part of a published set of 11,878, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.

Every code sandboxes run can be replayed on the board.

If you work on Fly Machines: 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 Fly Machines?

They raise it but do not choose it. Across 62 sessions where Fly Machines came up as a candidate, agents chose something else every time.

Does Claude Code recommend Fly Machines?

In 0 of the 112 sessions in code sandboxes run with Claude Code, which is 0%.

Do different coding agents treat Fly Machines differently?

Not much. Claude Code, Codex and Cursor 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 11,878 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