Do coding agents recommend Amazon Kinesis?
Amazon Kinesis was chosen in 7% of 288 judged message queues sessions, ranking fifth. Measured with Claude Code, Codex and Cursor.
Amazon Kinesis was chosen in 7% of 288 judged message queues sessions, ranking fifth. It was also raised as a candidate in 50 further sessions without being chosen.
This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in message queues inside a realistic codebase. Not what a chat assistant says about Amazon Kinesis. What an agent actually installed.
One thing to read first: every one of those wins came from a single codebase. That is a result about one repository rather than about message queues in general, and the splits below cannot separate the two. Treat them as a description of that repository.
The numbers
| Category | Message queues |
| Sessions in the category | 288 |
| Sessions where Amazon Kinesis was chosen | 19 |
| Install share | 7% |
| Rank in category | 5 of 25 |
| Codebases it won in | 1 |
| Raised as a candidate, not chosen | 50 |
| Chosen when considered | 28% |
| Site | aws.amazon.com |
By agent
With 19 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 Amazon Kinesis | Share |
|---|---|---|---|
| Claude Code | 96 | 8 | 8% |
| Codex | 96 | 7 | 7% |
| Cursor | 96 | 4 | 4% |
By who was asking
Amazon Kinesis does much better with one kind of buyer than another. It won 40% of sessions asked as senior engineer and 0% of those asked as enterprise team.
| Who is asking | Sessions | Chose Amazon Kinesis | Share |
|---|---|---|---|
| Vibe coder | 48 | 0 | 0% |
| Junior developer | 120 | 0 | 0% |
| Senior engineer | 48 | 19 | 40% |
| Enterprise team | 72 | 0 | 0% |
What Amazon Kinesis was up against
The full ranking in message queues, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Built in-house (no product adopted) | 49 | 17% |
| 2 | Apache Kafka | 39 | 14% |
| 3 | Amazon SQS | 27 | 9% |
| 4 | Service Bus | 24 | 8% |
| 5 | Laravel Queues | 20 | 7% |
| 6 | Amazon Kinesis (this page) | 19 | 7% |
| 7 | Cloudflare Queues | 19 | 7% |
| 8 | Cloud Tasks | 15 | 5% |
What this means
Amazon Kinesis was raised in 50 sessions and chosen in 19. That ratio is balanced enough that the ceiling is presence rather than integration: the product converts reasonably when it is on the table, and it is not on the table often enough.
Where these numbers come from
The 288 sessions in message queues 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 message queues run can be replayed on the board.
If you work on Amazon Kinesis: 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 Amazon Kinesis?
Yes. Amazon Kinesis was chosen in 19 of the 288 judged sessions in message queues, a 7% install share, ranking fifth in its category.
Does Claude Code recommend Amazon Kinesis?
In 8 of the 96 sessions in message queues run with Claude Code, which is 8%.
Do different coding agents treat Amazon Kinesis differently?
Not much. The three agents chose it at similar rates, between 4% and 8% of their runs.
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 Amazon Kinesis considered but not chosen?
It was raised as a candidate in 50 sessions without being chosen, and chosen in 19. That is a 28% 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.