From the experiment

Do coding agents recommend Amazon CloudWatch?

Amazon CloudWatch was chosen in 8% of 360 judged observability sessions, ranking third. Measured with Claude Code, Codex and Cursor.

Published September 3, 2026 Read as Markdown

Amazon CloudWatch was chosen in 8% of 360 judged observability sessions, ranking third. It was also raised as a candidate in 3 further sessions without being chosen.

This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in observability inside a realistic codebase. Not what a chat assistant says about Amazon CloudWatch. What an agent actually installed.

The numbers

CategoryObservability
Sessions in the category360
Sessions where Amazon CloudWatch was chosen30
Install share8%
Rank in category3 of 16
Codebases it won in2
Raised as a candidate, not chosen3
Chosen when considered91%
Siteaws.amazon.com

By agent

The three agents land within 8 points of each other on Amazon CloudWatch, which is closer than most products in this experiment manage.

AgentSessionsChose Amazon CloudWatchShare
Claude Code12065%
Codex1201513%
Cursor12098%

By who was asking

Amazon CloudWatch performs similarly across the four kinds of buyer, from 0% to 10%. That is unusual: the category leader changed with the persona in 14 of the 18 categories we measured.

Who is askingSessionsChose Amazon CloudWatchShare
Vibe coder1200%
Junior developer1200%
Senior engineer3003010%
Enterprise team3600%

What Amazon CloudWatch was up against

The full ranking in observability, from the same sessions:

#ProductRuns wonShare
1Sentry13337%
2Grafana5214%
3Amazon CloudWatch (this page)308%
4Built in-house (no product adopted)226%
5Checkly175%
6Datadog164%
7Better Stack154%
8New Relic154%

What this means

Agents almost never raise Amazon CloudWatch without choosing it: 3 sessions raised against 30 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 360 sessions in observability 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 observability run can be replayed on the board.

If you work on Amazon CloudWatch: 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 CloudWatch?

Yes. Amazon CloudWatch was chosen in 30 of the 360 judged sessions in observability, a 8% install share, ranking third in its category.

Does Claude Code recommend Amazon CloudWatch?

In 6 of the 120 sessions in observability run with Claude Code, which is 5%.

Do different coding agents treat Amazon CloudWatch differently?

Not much. The three agents chose it at similar rates, between 5% 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 Amazon CloudWatch considered but not chosen?

It was raised as a candidate in 3 sessions without being chosen, and chosen in 30. That is a 91% 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.

Read next

All library pages