Do coding agents recommend SendGrid?
SendGrid was chosen in 11% of 208 judged email sending sessions, ranking fifth. Measured with Claude Code, Codex and Cursor.
SendGrid was chosen in 11% of 208 judged email sending sessions, ranking fifth. It was also raised as a candidate in 130 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 SendGrid. What an agent actually installed.
The numbers
| Category | Email sending |
| Sessions in the category | 208 |
| Sessions where SendGrid was chosen | 23 |
| Install share | 11% |
| Rank in category | 5 of 6 |
| Codebases it won in | 2 |
| Raised as a candidate, not chosen | 130 |
| Chosen when considered | 15% |
| Site | sendgrid.com |
By agent
The three agents agree closely on SendGrid, choosing it at rates within 5 points of each other.
| Agent | Sessions | Chose SendGrid | Share |
|---|---|---|---|
| Claude Code | 65 | 8 | 12% |
| Codex | 71 | 6 | 8% |
| Cursor | 72 | 9 | 13% |
By who was asking
SendGrid performs similarly across the four kinds of buyer, from 0% to 14%. That is unusual: the category leader changed with the persona in 14 of the 18 categories we measured.
| Who is asking | Sessions | Chose SendGrid | Share |
|---|---|---|---|
| Senior engineer | 164 | 23 | 14% |
| Enterprise team | 44 | 0 | 0% |
What SendGrid was up against
The full ranking in email sending, from the same sessions:
| # | 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 (this page) | 23 | 11% |
| 6 | Generic SMTP | 1 | 0% |
What this means
This is an integration problem, not a presence problem. Agents raised SendGrid in 130 sessions and chose it in 23, so it reaches the shortlist and then loses. Something at the last step is costing the session, and in our data that is usually a quickstart that does not run when pasted, documentation describing an interface that changed, or a package name that does not match the product name.
That is the cheaper of the two problems to have. The reason is written down in each losing transcript.
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 SendGrid: 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 SendGrid?
Yes. SendGrid was chosen in 23 of the 208 judged sessions in email sending, a 11% install share, ranking fifth in its category.
Does Claude Code recommend SendGrid?
In 8 of the 65 sessions in email sending run with Claude Code, which is 12%.
Do different coding agents treat SendGrid differently?
Not much. The three agents chose it at similar rates, between 8% and 13% 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 SendGrid considered but not chosen?
It was raised as a candidate in 130 sessions without being chosen, and chosen in 23. That is a 15% 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.