Do coding agents recommend New Relic?
New Relic was chosen in 4% of 593 judged observability sessions, ranking sixth. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
New Relic was chosen in 4% of 593 judged observability sessions, ranking sixth. It was also raised as a candidate in 195 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 observability inside a realistic codebase. Not what a chat assistant says about New Relic. What an agent actually installed.
The numbers
| Category | Observability |
| Sessions in the category | 593 |
| Sessions where New Relic was chosen | 24 |
| Install share | 4% |
| Rank in category | 6 of 21 |
| Codebases it won in | 6 |
| Raised as a candidate, not chosen | 195 |
| Chosen when considered | 11% |
| Site | newrelic.com |
By agent
Claude Code, Codex, Cursor and Muse Code land within 13 points of each other on New Relic, which is closer than most products in this experiment manage. Grok Build CLI ran fewer than 30 sessions here, too few to compare.
| Agent | Sessions | Chose New Relic | Share |
|---|---|---|---|
| Claude Code | 150 | 0 | 0% |
| Codex | 180 | 24 | 13% |
| Cursor | 150 | 0 | 0% |
| Grok Build CLI | 24 | 0 | 0% |
| Muse Code | 89 | 0 | 0% |
By who was asking
New Relic performs similarly across the four kinds of buyer, from 0% to 5%. That is unusual: the category leader changed with the persona in 24 of the 31 categories we measured.
| Who is asking | Sessions | Chose New Relic | Share |
|---|---|---|---|
| Vibe coder | 20 | 0 | 0% |
| Junior developer | 20 | 0 | 0% |
| Senior engineer | 493 | 21 | 4% |
| Enterprise team | 60 | 3 | 5% |
What New Relic 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 (this page) | 24 | 4% |
| 8 | Datadog | 24 | 4% |
What this means
This is an integration problem, not a presence problem. Agents raised New Relic in 195 sessions and chose it in 24, 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 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 New Relic: 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 New Relic?
Yes. New Relic was chosen in 24 of the 593 judged sessions in observability, a 4% install share, ranking sixth in its category.
Does Claude Code recommend New Relic?
In 0 of the 150 sessions in observability run with Claude Code, which is 0%.
Do different coding agents treat New Relic differently?
Yes, and by a wide margin. Codex chose it in 13% of its runs and Claude Code in 0%.
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.
How often is New Relic considered but not chosen?
It was raised as a candidate in 195 sessions without being chosen, and chosen in 24. That is a 11% conversion from considered to chosen.
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.