From the experiment

Do coding agents recommend Amazon SES?

Amazon SES was chosen in 12% of 208 judged email sending sessions, ranking fourth. Measured with Claude Code, Codex and Cursor.

Published September 3, 2026 Read as Markdown

Amazon SES was chosen in 12% of 208 judged email sending sessions, ranking fourth. It was also raised as a candidate in 61 further sessions without being chosen.

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 Amazon SES. What an agent actually installed.

The numbers

CategoryEmail sending
Sessions in the category208
Sessions where Amazon SES was chosen24
Install share12%
Rank in category4 of 6
Codebases it won in3
Raised as a candidate, not chosen61
Chosen when considered28%
Siteaws.amazon.com

By agent

The three agents land within 7 points of each other on Amazon SES, which is closer than most products in this experiment manage.

AgentSessionsChose Amazon SESShare
Claude Code6558%
Codex711115%
Cursor72811%

By who was asking

Amazon SES does much better with one kind of buyer than another. It won 48% of sessions asked as enterprise team and 2% of those asked as senior engineer.

Who is askingSessionsChose Amazon SESShare
Senior engineer16432%
Enterprise team442148%

What Amazon SES was up against

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

#ProductRuns wonShare
1Resend7436%
2Postmark5727%
3Azure Communication Services Email2914%
4Amazon SES (this page)2412%
5SendGrid2311%
6Generic SMTP10%

What this means

Amazon SES was raised in 61 sessions and chosen in 24. That ratio is balanced enough that the ceiling is presence rather than integration: the product converts reasonably when it is on the table, and it is not on the table often enough.

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 Amazon SES: 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 SES?

Yes. Amazon SES was chosen in 24 of the 208 judged sessions in email sending, a 12% install share, ranking fourth in its category.

Does Claude Code recommend Amazon SES?

In 5 of the 65 sessions in email sending run with Claude Code, which is 8%.

Do different coding agents treat Amazon SES differently?

Not much. The three agents chose it at similar rates, between 8% and 15% 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 Amazon SES considered but not chosen?

It was raised as a candidate in 61 sessions without being chosen, and chosen in 24. That is a 28% 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