From the experiment

Do coding agents recommend Postmark?

Postmark was chosen in 27% of 208 judged email sending sessions, ranking second. Measured with Claude Code, Codex and Cursor.

Published September 3, 2026 Read as Markdown

Postmark was chosen in 27% of 208 judged email sending sessions, ranking second. It was also raised as a candidate in 112 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 Postmark. What an agent actually installed.

The numbers

CategoryEmail sending
Sessions in the category208
Sessions where Postmark was chosen57
Install share27%
Rank in category2 of 6
Codebases it won in5
Raised as a candidate, not chosen112
Chosen when considered34%
Sitepostmarkapp.com

By agent

The three agents land within 13 points of each other on Postmark, which is closer than most products in this experiment manage.

AgentSessionsChose PostmarkShare
Claude Code652335%
Codex711825%
Cursor721622%

By who was asking

Postmark does much better with one kind of buyer than another. It won 35% of sessions asked as senior engineer and 0% of those asked as enterprise team.

Who is askingSessionsChose PostmarkShare
Senior engineer1645735%
Enterprise team4400%

What Postmark was up against

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

#ProductRuns wonShare
1Resend7436%
2Postmark (this page)5727%
3Azure Communication Services Email2914%
4Amazon SES2412%
5SendGrid2311%
6Generic SMTP10%

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 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 Postmark: 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 Postmark?

Yes. Postmark was chosen in 57 of the 208 judged sessions in email sending, a 27% install share, ranking second in its category.

Does Claude Code recommend Postmark?

In 23 of the 65 sessions in email sending run with Claude Code, which is 35%.

Do different coding agents treat Postmark differently?

Yes, and by a wide margin. Claude Code chose it in 35% of its runs and Cursor in 22%.

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 Postmark considered but not chosen?

It was raised as a candidate in 112 sessions without being chosen, and chosen in 57. That is a 34% 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