Do coding agents recommend Cursor Automations?
Cursor Automations was chosen in 8% of 179 judged ai sre sessions, ranking fourth. Measured with Claude Code, Codex and Cursor.
Cursor Automations was chosen in 8% of 179 judged ai sre sessions, ranking fourth. It was also raised as a candidate in 8 further sessions without being chosen.
This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in ai sre inside a realistic codebase. Not what a chat assistant says about Cursor Automations. What an agent actually installed.
The numbers
| Category | Ai sre |
| Sessions in the category | 179 |
| Sessions where Cursor Automations was chosen | 15 |
| Install share | 8% |
| Rank in category | 4 of 26 |
| Codebases it won in | 5 |
| Raised as a candidate, not chosen | 8 |
| Chosen when considered | 65% |
| Site | cursor.com |
By agent
With 15 wins spread across three agents, the rates below are small numbers and a difference between them is not yet a finding. They are here because the direction is worth knowing, not because the gap is established.
| Agent | Sessions | Chose Cursor Automations | Share |
|---|---|---|---|
| Claude Code | 71 | 0 | 0% |
| Codex | 72 | 1 | 1% |
| Cursor | 36 | 14 | 39% |
By who was asking
Cursor Automations performs similarly across the four kinds of buyer, from 7% to 10%. That is unusual: the category leader changed with the persona in 23 of the 28 categories we measured.
| Who is asking | Sessions | Chose Cursor Automations | Share |
|---|---|---|---|
| Vibe coder | 30 | 3 | 10% |
| Junior developer | 60 | 5 | 8% |
| Senior engineer | 30 | 3 | 10% |
| Enterprise team | 59 | 4 | 7% |
What Cursor Automations was up against
The full ranking in ai sre, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Sentry Seer | 47 | 26% |
| 2 | Resolve AI | 35 | 20% |
| 3 | Datadog Bits AI Dev Agent + Datadog Bits Investigation | 26 | 15% |
| 4 | Cursor Automations (this page) | 15 | 8% |
| 5 | Claude Code GitHub Action | 11 | 6% |
| 6 | Cursor Cloud Agents | 9 | 5% |
| 7 | incident.io AI SRE | 4 | 2% |
| 8 | Cursor Automations + Cursor Cloud Agents | 3 | 2% |
What this means
Agents almost never raise Cursor Automations without choosing it: 8 sessions raised against 15 chosen. When it gets considered, it usually wins. The constraint is how rarely it gets considered at all, which is a presence problem: templates, framework integrations and pages that answer the configuration and production questions agents actually search for.
Where these numbers come from
The 179 sessions in ai sre are part of a published set of 7,852, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every ai sre run can be replayed on the board.
If you work on Cursor Automations: 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 Cursor Automations?
Yes. Cursor Automations was chosen in 15 of the 179 judged sessions in ai sre, a 8% install share, ranking fourth in its category.
Does Claude Code recommend Cursor Automations?
In 0 of the 71 sessions in ai sre run with Claude Code, which is 0%.
Do different coding agents treat Cursor Automations differently?
Yes, and by a wide margin. Cursor chose it in 39% of its runs and Claude Code in 0%.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 90 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 Cursor Automations considered but not chosen?
It was raised as a candidate in 8 sessions without being chosen, and chosen in 15. That is a 65% conversion from considered to chosen.
Where this comes from
Armature ran 7,852 judged sessions with Claude Code, Codex and Cursor inside 90 realistic codebases, and published every run. The numbers on this page come from that work.