Do coding agents recommend Confluent?
Confluent was chosen in 2% of 495 judged message queues sessions, ranking number 12. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
Confluent was chosen in 2% of 495 judged message queues sessions, ranking number 12. It was also raised as a candidate in 99 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 message queues inside a realistic codebase. Not what a chat assistant says about Confluent. What an agent actually installed.
The numbers
| Category | Message queues |
| Sessions in the category | 495 |
| Sessions where Confluent was chosen | 8 |
| Install share | 2% |
| Rank in category | 12 of 28 |
| Codebases it won in | 2 |
| Raised as a candidate, not chosen | 99 |
| Chosen when considered | 7% |
| Site | confluent.io |
By agent
With 8 wins spread across 5 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 Confluent | Share |
|---|---|---|---|
| Claude Code | 138 | 0 | 0% |
| Codex | 144 | 4 | 3% |
| Cursor | 134 | 2 | 1% |
| Grok Build CLI | 35 | 0 | 0% |
| Muse Code | 44 | 2 | 5% |
By who was asking
Confluent performs similarly across the four kinds of buyer, from 0% to 4%. That is unusual: the category leader changed with the persona in 23 of the 29 categories we measured.
| Who is asking | Sessions | Chose Confluent | Share |
|---|---|---|---|
| Vibe coder | 81 | 0 | 0% |
| Junior developer | 171 | 0 | 0% |
| Senior engineer | 84 | 2 | 2% |
| Enterprise team | 159 | 6 | 4% |
What Confluent was up against
The full ranking in message queues, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Built in-house (no product adopted) | 87 | 18% |
| 2 | Apache Kafka | 68 | 14% |
| 3 | Amazon SQS | 50 | 10% |
| 4 | Service Bus | 41 | 8% |
| 5 | Amazon Kinesis | 37 | 7% |
| 6 | Laravel Queues | 34 | 7% |
| 7 | Cloud Tasks | 30 | 6% |
| 8 | Cloudflare Queues | 28 | 6% |
What this means
This is an integration problem, not a presence problem. Agents raised Confluent in 99 sessions and chose it in 8, 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 495 sessions in message queues are part of a published set of 11,878, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every message queues run can be replayed on the board.
If you work on Confluent: 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 Confluent?
Yes. Confluent was chosen in 8 of the 495 judged sessions in message queues, a 2% install share, ranking number 12 in its category.
Does Claude Code recommend Confluent?
In 0 of the 138 sessions in message queues run with Claude Code, which is 0%.
Do different coding agents treat Confluent differently?
Not much. Claude Code, Codex, Cursor, Grok Build CLI and Muse Code chose it at similar rates, between 0% and 5% of their runs.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 91 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 Confluent considered but not chosen?
It was raised as a candidate in 99 sessions without being chosen, and chosen in 8. That is a 7% conversion from considered to chosen.
Where this comes from
Armature ran 11,878 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 91 realistic codebases, and published every run. The numbers on this page come from that work.