How to get picked for email sending by coding agents
Resend took 33% of 351 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 351 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code, spread across 9 realistic codebases, with every session read by a judge.
What coding agents choose for email sending
Across 351 judged sessions, Resend was chosen most often, in 33% of runs. Postmark was second with 27%.
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Resend | 115 | 33% |
| 2 | Postmark | 95 | 27% |
| 3 | Azure Communication Services | 49 | 14% |
| 4 | SendGrid | 44 | 13% |
| 5 | Amazon SES | 41 | 12% |
| 6 | Generic SMTP | 4 | 1% |
| 7 | Built in-house (no product adopted) | 2 | 1% |
| 8 | Paubox | 1 | 0% |
Full board, every run replayable: the email sending leaderboard.
What the shape of this category means
The leader takes only 33% of runs. This category is genuinely open and the ordering can be moved.
With the top product at 33%, email sending is decided in the moment, from what the agent reads and what it finds in the repository. Nothing is locked in, which is the best situation a vendor can be in and the one where the work pays fastest.
The order here is set by the quality of what an agent can read and by whether your product is already present in the codebase. Both are things you can change.
The agents do not agree with each other
In this category Claude Code, Codex and Cursor did not put the same product first.
Grok Build CLI (18 sessions) and Muse Code (53 sessions) join this table with fewer runs, so read their rows as indicative.
| Agent | Runs | Picked most often |
|---|---|---|
| Claude Code | 83 | Postmark (30) |
| Codex | 107 | Resend (39) |
| Cursor | 90 | Resend (32) |
| Grok Build CLI | 18 | Postmark (8) |
| Muse Code | 53 | Resend (17) |
That split decides where a vendor spends. In this category Codex ran a web search in 99% of its sessions and Claude Code in 19%, so what you publish reaches nearly all of Codex's email sending sessions and a minority of Claude Code's. Taking Resend's position with Codex is mostly a content problem. Taking Postmark's with Claude Code leans more on the repository.
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 | 275 | Resend |
| Enterprise team | 76 | Amazon SES |
That is 2 different products winning email sending for 2 kinds of buyer, out of the same 351 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 1% of runs the agent wrote the code itself rather than adopting a product. That is low enough that your competition is other vendors, but high enough to be worth watching.
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 136 sessions, chosen in none.
| Product | Raised in | Chosen in |
|---|---|---|
| Mailgun | 136 sessions | 0 |
| Loops | 34 sessions | 0 |
| Brevo | 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 190 sessions is recorded in each transcript, one reason at a time.
What to do about it in email sending
- Aim at second place first. Resend holds 33% 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, Grok Build CLI put Postmark first, Muse Code 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 33% of sessions
- Do coding agents recommend Postmark? — chosen in 27% of sessions
- Do coding agents recommend Azure Communication Services? — chosen in 14% of sessions
- Do coding agents recommend SendGrid? — chosen in 13% of sessions
- Do coding agents recommend Amazon SES? — chosen in 12% of sessions
- Do coding agents recommend Mailgun? — raised in 136 sessions, chosen in none
Where these numbers come from
351 judged sessions in email sending across 9 codebases, part of a published set of 15,287. 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?
351 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 351 judged sessions, Resend was chosen most often, in 33% 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?
In 1% of runs the agent wrote the code itself rather than adopting a product.
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 136 sessions, chosen in none), Loops (raised in 34 sessions, chosen in none), Brevo (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 15,287 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 110 realistic codebases, and published every run. The numbers on this page come from that work.