From the experiment

Do coding agents recommend Mailgun?

Coding agents raised Mailgun in 97 of 208 judged email sending sessions and chose it in none of them. Measured with Claude Code, Codex and Cursor.

Published September 3, 2026 Read as Markdown

Coding agents raised Mailgun in 97 of 208 judged email sending sessions and chose it in none of them.

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

The numbers

CategoryEmail sending
Sessions in the category208
Sessions where Mailgun was chosen0
Install share0%
Raised as a candidate, not chosen97
Chosen when considered0%
Sitemailgun.com

Which agents raised Mailgun

Every agent considered it and none adopted it. Cursor raised it most often, in 85% of its email sending sessions.

AgentSessionsRaised MailgunChose it
Claude Code6529 (45%)0
Codex717 (10%)0
Cursor7261 (85%)0

Which buyers it came up for

It surfaced most for requests written as enterprise team, in 48% of those sessions. Knowing which buyer already has the product in mind tells you which pages to fix first.

Who is askingSessionsRaised it
Senior engineer16476 (46%)
Enterprise team4421 (48%)

What Mailgun was up against

The full ranking in email sending, from the same sessions:

#ProductRuns wonShare
1Resend7436%
2Postmark5727%
3Azure Communication Services Email2914%
4Amazon SES2412%
5SendGrid2311%
6Generic SMTP10%

What this means

Raised 97 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 97 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 208 sessions in email sending 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 email sending run can be replayed on the board.

If you work on Mailgun: 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 Mailgun?

They raise it but do not choose it. Across 97 sessions where Mailgun came up as a candidate, agents chose something else every time.

Does Claude Code recommend Mailgun?

In 0 of the 65 sessions in email sending run with Claude Code, which is 0%.

Do different coding agents treat Mailgun differently?

Not much. The three agents 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 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.

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