Do coding agents recommend OpenTelemetry?
OpenTelemetry came up in 59% of judged observability sessions and was adopted in none: on this board it is substrate, not a candidate.
OpenTelemetry came up in 59% of judged observability sessions and was adopted in none: on this board it is substrate, not a candidate.
This page reports what happened when Claude Code, Codex, Cursor, Grok Build CLI and Muse Code had to solve a problem in observability inside a realistic codebase. Not what a chat assistant says about OpenTelemetry. What an agent actually installed.
The numbers
| Category | Observability |
| Sessions in the category | 593 |
| Sessions where OpenTelemetry was chosen | 0 |
| Install share | 0% |
| Raised as a candidate, not chosen | 349 |
| Chosen when considered | 0% |
| Site | opentelemetry.io |
Which agents raised OpenTelemetry
OpenTelemetry came up in 59% of observability sessions and was adopted in none. At that rate it is not a candidate that keeps losing: it is the thing already in the repository, or the standard the alternatives get measured against. Cursor named it in 85% of its sessions.
| Agent | Sessions | Raised OpenTelemetry | Chose it |
|---|---|---|---|
| Claude Code | 150 | 94 (63%) | 0 |
| Codex | 180 | 88 (49%) | 0 |
| Cursor | 150 | 127 (85%) | 0 |
| Grok Build CLI | 24 | 17 (71%) | 0 |
| Muse Code | 89 | 23 (26%) | 0 |
Which buyers it came up for
It surfaced most for requests written as enterprise team, in 85% of those sessions. Knowing which buyer already has the product in mind tells you which pages to fix first.
| Who is asking | Sessions | Raised it |
|---|---|---|
| Vibe coder | 20 | 1 (5%) |
| Junior developer | 20 | 4 (20%) |
| Senior engineer | 493 | 293 (59%) |
| Enterprise team | 60 | 51 (85%) |
What OpenTelemetry was up against
The full ranking in observability, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Sentry | 211 | 36% |
| 2 | Grafana | 86 | 15% |
| 3 | Amazon CloudWatch | 59 | 10% |
| 4 | Built in-house (no product adopted) | 41 | 7% |
| 5 | Better Stack | 26 | 4% |
| 6 | Checkly | 25 | 4% |
| 7 | New Relic | 24 | 4% |
| 8 | Datadog | 24 | 4% |
What this means
Read this row as context, not as a loss. On this board OpenTelemetry is the thing underneath rather than one of the candidates: the database already in the repository, the protocol the alternatives implement, or the runtime they all run on. Our judge has an explicit rule for the clearest case: a vendor-neutral standard is never recorded as the winner, because it is the wiring and not the destination.
Where that reading does not apply, the causes below are the ones we see.
In our data the causes, in the order they occur:
- The quickstart does not run when pasted, so the agent abandoned it mid-integration.
- The documentation describes an interface that changed, so the generated code failed.
- The product name and the package name differ, so the install step went wrong.
- The fit was genuinely wrong for the repository, which is fine and worth knowing.
All but the last are fixable in days, and the reason is written down in the session transcript.
Where these numbers come from
The 593 sessions in observability 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 observability run can be replayed on the board.
If you work on OpenTelemetry: 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 OpenTelemetry?
They raise it but do not choose it. Across 349 sessions where OpenTelemetry came up as a candidate, agents chose something else every time.
Does Claude Code recommend OpenTelemetry?
In 0 of the 150 sessions in observability run with Claude Code, which is 0%.
Do different coding agents treat OpenTelemetry differently?
Not much. Claude Code, Codex, Cursor and Muse Code chose it at similar rates, between 0% and 0% of their runs.
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.
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.