How to get picked for email sending by coding agents
Resend took 36% of 208 judged email sending sessions. What the numbers say a vendor in this category should do.
If you sell email providers, this page is the part of the market no dashboard shows you: what a coding agent does when a developer asks for email sending and never compares vendors.
The numbers come from 208 judged sessions with Claude Code, Codex and Cursor, spread across 9 realistic codebases, with every session read by a judge.
What coding agents choose for email sending
Across 208 judged sessions, Resend was chosen most often, in 36% of runs. Postmark was second with 27%.
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Resend | 74 | 36% |
| 2 | Postmark | 57 | 27% |
| 3 | Azure Communication Services Email | 29 | 14% |
| 4 | Amazon SES | 24 | 12% |
| 5 | SendGrid | 23 | 11% |
| 6 | Generic SMTP | 1 | 0% |
Full board, every run replayable: the email sending leaderboard.
What the shape of this category means
The leader takes 36% of runs and there is a real second place. The category has a default but it is not settled.
Resend at 36% with Postmark at 27% is a default with a real challenger behind it. The agent is choosing rather than reaching, which means the inputs it uses can move the answer.
The work is to be the easiest correct answer: a quickstart that runs when pasted, documentation that states the current version, and pages that answer the exact configuration questions agents search for.
The agents do not agree with each other
In this category the three agents we ran put different products first.
| Agent | Runs | Picked most often |
|---|---|---|
| Claude Code | 65 | Postmark (23) |
| Codex | 71 | Resend (27) |
| Cursor | 72 | Resend (27) |
That split decides where a vendor spends. Codex ran a web search in 53% of decision runs and Claude Code in 1.6%, so the pages you publish are live in half of Codex's email sending sessions and almost none of Claude Code's. Taking Resend's position with Codex is a content problem. Taking Postmark's with Claude Code is a repository problem.
Who is asking changes the answer
Every request in this experiment was written as a specific kind of person. In this category the leader changes with the person.
| Who is asking | Runs | Picked most often |
|---|---|---|
| Senior engineer | 164 | Resend |
| Enterprise team | 44 | Azure Communication Services Email |
That is 2 different products winning email sending for 2 kinds of buyer, out of the same 208 sessions. Nobody here is winning email sending. They are each winning one kind of buyer.
If you sell to more than one of them, you need pages for each. See how to win the enterprise persona.
What you are really competing against
In this category agents never chose to build it themselves. Every session ended with a product. That is good news: you are in a straight vendor comparison, and the levers that work are the ones you control.
Considered, and never chosen
Because the judge records every product an agent raised and not only the one it picked, this board also shows who kept reaching the shortlist and losing. In email sending the clearest case is Mailgun: on the table in 97 sessions, chosen in none.
| Product | Raised in | Chosen in |
|---|---|---|
| Mailgun | 97 sessions | 0 |
| Loops | 20 sessions | 0 |
Being rejected is a better position than being unknown, and a cheaper one to fix. The product is already in the agent's head and on the list. Whatever ended those 117 sessions is recorded in each transcript, one reason at a time.
What to do about it in email sending
- Skip the build-versus-buy argument. No email sending session in this experiment ended with the agent writing its own implementation. Every one adopted a product, so the whole contest is against the other names in the table above.
- Aim at second place first. Resend holds 36% and Postmark holds 27%. The gap between the default and the field is where the reachable sessions are.
- Report install share per persona, not as one number. In email sending the leader changes with who is asking, so a blended figure averages markets that behave differently.
- Measure per agent. Claude Code put Postmark first, Codex put Resend first, Cursor put Resend first. A blended number for email sending describes a market that does not exist.
The work that applies to every category rather than to this one is written up separately: audit your documentation, write a quickstart an agent can follow, and how to measure install share.
Every email provider on this board
One page per product, with its install share, the per-agent split, and how often it was raised without being chosen.
- Do coding agents recommend Resend? — chosen in 36% of sessions
- Do coding agents recommend Postmark? — chosen in 27% of sessions
- Do coding agents recommend Azure Communication Services Email? — chosen in 14% of sessions
- Do coding agents recommend Amazon SES? — chosen in 12% of sessions
- Do coding agents recommend SendGrid? — chosen in 11% of sessions
- Do coding agents recommend Mailgun? — raised in 97 sessions, chosen in none
Where these numbers come from
208 judged sessions in email sending across 9 codebases, part of a published set of 5,292. Real coding agents at pinned versions, in sandboxes, inside realistic codebases, with a simulated project owner in the loop and a blind judge on every session. The full method is on one page: how we measured this.
Every email sending run can be replayed on the board.
<!-- generated by scripts/write-data-pages.mjs -->
Common questions
How many codebases is this based on?
208 judged sessions across 9 realistic codebases. A category only runs on repositories where its seam is open, so coverage differs: some categories ran on more than ten codebases and some on two.
What email provider do coding agents choose?
Across 208 judged sessions, Resend was chosen most often, in 36% of runs. Postmark was second with 27%. The result changes by agent and by who is asking.
Do Claude Code and Codex pick the same email provider?
No. Claude Code picked Postmark, Codex picked Resend, Cursor picked Resend. Measuring one agent tells you about part of the market only.
How often do agents build email sending themselves instead of installing something?
Never, in this category. Every one of the sessions ended with the agent adopting a product rather than writing the code itself.
How can a vendor improve its position here?
Make the quickstart run when pasted, state the current version on the documentation page, use one name across product, package and import, write pages for the symptoms users describe rather than only the category name, and get into the repository through templates and framework integrations.
Which email providers do agents consider but never choose?
Mailgun (raised in 97 sessions, chosen in none), Loops (raised in 20 sessions, chosen in none). Being considered and not chosen is a different problem from being unknown, and it is usually fixable.
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.