Do coding agents recommend SendGrid?
SendGrid was chosen in 13% of 351 judged email sending sessions, ranking fourth. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
SendGrid was chosen in 13% of 351 judged email sending sessions, ranking fourth. It was also raised as a candidate in 195 further sessions without being chosen.
This page reports what happened when Claude Code, Codex, Cursor, Grok Build CLI and Muse Code 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 | 351 |
| Sessions where SendGrid was chosen | 44 |
| Install share | 13% |
| Rank in category | 4 of 7 |
| Codebases it won in | 3 |
| Raised as a candidate, not chosen | 195 |
| Chosen when considered | 18% |
| Site | sendgrid.com |
By agent
The agents treat SendGrid very differently. Muse Code chose it in 25% of its sessions in this category and Codex in 9%, a spread of 16 points. Grok Build CLI ran fewer than 30 sessions here, too few to compare.
| Agent | Sessions | Chose SendGrid | Share |
|---|---|---|---|
| Claude Code | 83 | 10 | 12% |
| Codex | 107 | 10 | 9% |
| Cursor | 90 | 9 | 10% |
| Grok Build CLI | 18 | 2 | 11% |
| Muse Code | 53 | 13 | 25% |
A single blended install share would report the midpoint and hide both ends. If most of your users run Codex, your real position here is 9%, not 13%.
By who was asking
SendGrid does much better with one kind of buyer than another. It won 16% of sessions asked as senior engineer and 0% of those asked as enterprise team.
| Who is asking | Sessions | Chose SendGrid | Share |
|---|---|---|---|
| Senior engineer | 275 | 44 | 16% |
| Enterprise team | 76 | 0 | 0% |
What SendGrid was up against
The full ranking in email sending, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Resend | 115 | 33% |
| 2 | Postmark | 95 | 27% |
| 3 | Azure Communication Services | 49 | 14% |
| 4 | SendGrid (this page) | 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% |
What this means
This is an integration problem, not a presence problem. Agents raised SendGrid in 195 sessions and chose it in 44, 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 351 sessions in email sending are part of a published set of 15,287, 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 44 of the 351 judged sessions in email sending, a 13% install share, ranking fourth in its category.
Does Claude Code recommend SendGrid?
In 10 of the 83 sessions in email sending run with Claude Code, which is 12%.
Do different coding agents treat SendGrid differently?
Yes, and by a wide margin. Muse Code chose it in 25% of its runs and Codex in 9%.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 110 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 195 sessions without being chosen, and chosen in 44. That is a 18% conversion from considered to chosen.
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.