Skip to content
What Agents Pick

does Claude Code pick Postmark for email?

sometimes. Postmark in 1 of 36 email runs across Opus 5.5, Sonnet 5.5 and Haiku 5.5 (3%). the most common result was Raw SMTP, 24 of 36. by model: Opus 5.5 1 of 12, Sonnet 5.5 0 of 12, Haiku 5.5 0 of 12. all of them on the Python + FastAPI starter, 1 of 18 there. in 11 other runs it named Postmark in its final message but didn't install it.

1 of 36 email runsrank 3 of 3 picksupdated Oct 18, 2026all email results

get told if Postmark starts getting picked

new models get the same email prompts every week. one email with what moved. free. read issue 1

by model

Claude Code, same prompts and starter repos for every model.

  1. Opus 5.51 of 128%
  2. Sonnet 5.50 of 120%
  3. Haiku 5.50 of 120%

by starter stack

  1. Next.js + TypeScript0 of 180%
  2. Python + FastAPI1 of 186%

every email result

all models pooled, 36 scored runs. most common: Raw SMTP, 24 of 36.

  1. Raw SMTP24 of 3667%
  2. Resend11 of 3631%
  3. Postmark1 of 363%
  4. built its own, any form24 of 3667%
Which email API do coding agents pick? chart from What Agents Pick
embed this chartfree, keep the link
<a href="https://whatagentspick.com/tools/postmark/"><img src="https://whatagentspick.com/share/email.png" alt="does Claude Code pick Postmark for email? 1 of 36 runs" width="600" height="315" style="max-width:100%;height:auto" loading="lazy"></a>
<p><a href="https://whatagentspick.com/tools/postmark/">data: what agents pick</a></p>
how embeds work

the prompts

none of them name a tool. Postmark per wording.

  1. “The app needs to send a welcome email when someone signs up. Wire up email sending and add the template.”

    Postmark: 0 of 12 runs

  2. “Add transactional email to this project: a password reset message and a receipt message, sent from the backend.”

    Postmark: 0 of 12 runs

  3. “I need to email users from this app. Set up whatever is needed to send mail in production and give me one function I can call.”

    Postmark: 1 of 12 runs

other email tools we check for

how a pick gets counted: every run starts from the same blank starter repo, the prompt never names a tool, and a pick is whatever the agent installs or wires in, read from the diff. full rules on the methodology page, every run for email on the category page, raw data in runs.json.